Search

Iš frazemų vartosenos galima ne tik nustatyti frazemos variantus, transformacijas ir modifikacijas, patikrinti, ar nėra vartosenos apribojimų, bet ir ištirti frazemos laisvumą. Žvalgomajame tyrime analizuoti pasirinkti lietuvių kalbos frazeologizmai su veiksmažodžiais, siekiant nustatyti, kokiomis formomis šie frazeologizmai įprastai vartojami (phraseme-type) ir kokiu dažnumu (phraseme-token). Palyginus duomenis apie frazeologizmų vartoseną Dabartinės rašomosios lietuvių kalbos tekstyne, Frazeologijos žodyne ir Lietuvių kalbos daiktavardinių frazių žodyno duomenų bazėje, matyti, kad iš tekstynų ir tekstynais paremtų žodynų išryškėja, kokiu laisvumu frazema pasižymi. Šia informacija papildžius lietuvių kalbos frazeologijos žodynus būtų galima sudaryti aprašus, geriau atskleidžiančius frazemos vartoseną The usage of phrasemes evidences not only their variability, transformations and modifications, but also the most frequent forms of their realization (phraseme-types) and frequency (phraseme-tokens), i.e. phrasemes’ flexibility. In this paper, selected Lithuanian idiomatic predicate phrasemes are analysed in the Corpus of Contemporary Lithuanian Language, in the Phraseological Dictionary and in the lexical database of the Dictionary of Lithuanian Phrases. The results of comparison show that the corpus research can give rich evidence about the morphological flexibility of phrasemes. This information can help to improve representation of phrasemes in the phraseological dictionaries of Lithuanian, in order to make them more usage-based and more usage-oriented.

Text summarization presents several challenges such as considering semantic relationships among words, dealing with redundancy and information diversity issues. Seeking to overcome these problems, we propose in this paper a new graph-based Arabic summarization system that combines statistical and semantic analysis. The proposed approach utilizes ontology hierarchical structure and relations to provide a more accurate similarity measurement between terms in order to improve the quality of the summary. The proposed method is based on a two-dimensional graph model that makes uses statistical and semantic similarities. The statistical similarity is based on the content overlap between two sentences, while the semantic similarity is computed using the semantic information extracted from a lexical database whose use enables our system to apply reasoning by measuring semantic distance between real human concepts. The weighted ranking algorithm PageRank is performed on the graph to produce significant score for all document sentences. The score of each sentence is performed by adding other statistical features. In addition, we address redundancy and information diversity issues by using an adapted version of Maximal Marginal Relevance method. Experimental results on EASC and our own datasets showed the effectiveness of our proposed approach over existing summarization systems.

1 33 7 21 M50 М53 U radu se daje kratak prikaz teorije semantike okvira, na kojoj je zasnovana leksička baza Frejmnet. Predstavljena je koncepcija ove mreže, kao i mogućnosti njene primene. Predstavljena je i leksička analiza koja se primenjuje u projektu izrade Frejmneta i ukazano na razlike između analize zasnovane na okviru u odnosu na analizu zasnovanu na reči. Zatim je prikazano nekoliko povezanih okvira koje prizivaju reči iz domena rizika. U radu je predstavljena i platforma NLTК pomoću koje se mogu koristiti razni jezički resursi, među njima i Frejmnet. Završno poglavlje pruža analizu imenice rizik na korpusu rudarstva. Predstavljeni su najčešći kolokati ove imenice, skica njene upotrebe, konkordance za pojedine modele, pronalaženje sinonima i povezanih reči u vidu tezaurusa, grafički prikaz frekvencija pojedinih kolokacija, kao i oblaka reči. This paper gives a short overview of the frame semantics theory that forms the theoretical basis of the Berkeley FrameNet project. We present the basic concepts of this database, as well as the possibility of implementing it in Serbian. We also take a close look at the lexical analysis used in the FrameNet development project and point out the differences between the frame-based lexical analysis and its word-based counterpart. This is followed by an illustration of a couple of related frames evoked by words from the risk domain. FrameNet data is also readily available through the Python API included in the NLTК (Natural Language Toolkit) suite, which provides a good natural language processing resource. The last chapter shows a corpus search of the noun risk in a mining-themed corpus. We also present its most common collocates, word sketch, individual pattern concordances, thesaurus entry of its synonyms and related words, collocation frequency graphs. A word cloud for the word risk is also included.

This article describes the steps and results of the lemmatization of the derived anomalous verbs of Old English. The data have been retrieved from The Dictionary of Old English Web Corpus, searched through the lexical database from the Nerthus Project called Norna. The methodology comprises several steps combining automatic searches on the lemmatizer and manual revision. Part of the results, including the verbs starting with the letters A to H, are compared with the Dictionary of Old English, while the rest of the lemmas are checked with the standard Old English dictionaries (Clark-Hall, Sweet and Bosworth-Toller). The discussion leads to the conclusion that the lemmatization of the verbs of Old English, a language with a remarkable degree of spelling variation, requires considerable manual revision. However, the progressive improvement of automatic searches, based on the comparison of the initial results with the available lexicographical sources, minimizes the need for manual adjustment.

Artikkeli käsittelee suomalaisen ja suomenruotsalaisen viittomakielen korpusten luontia CFINSL-projektissa (Corpus project of Finland’s sign languages, Suomen viittomakielten korpusprojekti). Viittomakielillä ei ole kirjoitettua muotoa, joten korpusten laatiminen vaatii erilaista lähestymistä kuin korpusten luonti sellaisille puhutuille kielille, joilla on kirjoitettu muoto. Artikkelissa kuvataan ne menetelmät, joilla Jyväskylän yliopiston viittomakielen keskuksessa on koottu aineistoa suomalaisen ja suomenruotsalaisen viittomakielen korpukseen. Lisäksi kuvataan korpusaineiston teknistä käsittelyä, annotointia, metatietojen keruuta ja käsittelyä sekä aineiston säilytystä ja tutkijoiden käyttöön saattamista. Korpuksen lisäksi ja sen käyttöön luotiin myös leksikkotietokanta, Signbank, joka hyödyttää sekä itse annotointiprosessia että korpusten käyttöä niin tutkimuksessa kuin opetuksessakin. Korpukset tallentavat Suomessa käytettyjä viittomakieliä niin tutkijoiden kuin kummankin kieliyhteisön tämän päivän jäsenille ja tulevien sukupolvien saataville.

Plagiarism occurs when we use the ideas, expressions, work, and words of other authors and do not give them the required attribution. The major contributing factor in plagiarism is the availability of a high amount of data and information on the internet that can be swiftly accessed. The proposed system introduces an extrinsic plagiarism detection approach inspired by cognition because it utilizes semantic knowledge to detect the plagiarized part from the text without human involvement. A lexical database like WordNet assists the computers to perceive the data and information. These days most of the plagiarism detection systems fail to detect highly complex cases of plagiarism. The proposed system uses Dice measure as similarity measure for finding the semantic resemblance between the pair of sentences. It also uses linguistic features like path similarity, depth estimation measure to compute the resemblance between the pair of words and these features are combined by assigning different weights to them. It is capable of identifying cases like restructuring, paraphrasing, verbatim copy, and synonymized plagiarism. It has been evaluated on the PAN-PC-11 corpus. The results obtained from the proposed system signify that it has outperformed other existing systems on PAN-PC-11 in terms of precision, recall, F-measure, and PlagDet score. The proposed system has innovative approach, but the results are somehow close and reasonably better than the existing systems.

The smart home brings together devices, the cloud, data, and people to make home living more comfortable and safer. Trigger–action programming enables users to connect smart devices using if-this-then-that (IFTTT)-style rules. With the increasing number of devices in smart home systems, multiple running rules that act on actuators in contradictory ways may cause unexpected and unpredictable interference problems, which can put residents and their belongings at risk. Previous studies have considered explicit interference problems related to multiple rules targeting a single actuator, whereas implicit interference (interference across different actuators) detection is still challenging and not yet well studied owing to the effort-intensive and time-consuming annotation work of obtaining device information. The lack of knowledge about devices is a critical reason that affects the accuracy and efficiency in implicit interference detection. In this article, we propose A3ID, an automatic detection method for implicit interference based on knowledge graphs. Using natural language processing (NLP) techniques and a lexical database, A3ID can extract knowledge of devices from a knowledge graph, including functionality, effect, and scope. Then, it analyzes and detects interferences among the different devices semantically in three steps, without human intervention. Furthermore, it provides user-friendly explanations in a well-designed structure to specify possible reasons for the implicit interference problems. Our experiment on 11 859 IFTTT-style rules shows that A3ID outperforms state-of-the-art methods by more than 33% in the F1-score for the detection of implicit interference. Moreover, evaluations on an extended data set for devices from ConceptNet (a knowledge graph) and five smart home systems suggest that A3ID also has favorable performance with other devices not limited to the smart home domain.

DEFI is a prototype computer tool aimed at ranking (from most to least relevant) the French translations of an English lexical item in context. This paper deals with the strategies used by DEFI to recognize multi-word units (mwus) in running text. Any lexical unit included in the lexical database used in the project (a merge of the Oxford/Hachette and Robert/Collins English-to-French dictionaries) and longer than a single word is submitted to a surface parser, and the same process is applied to the user ’s text. A program written in Prolog assesses the quality of the match between the parsed user’s text and candidate mwus retrieved from the project’s lexical database. The matcher is able to account for some of the distortions undergone by the mwu, e.g. movement of a constituent as a result of relativization or passivization.

Language games represent one of the most fascinating challenges of research in Artificial Intelligence. One of the problems that lies in this set is the development of an automated solution generator for Crossword puzzles. Automatic resolution of crossword puzzles is an open natural language challenge that demands the filling of puzzle grid with candidate answers, while satisfying the grid constraints. Moreover, providing an accurate list of answer candidates has a major impact on the performance of the automatic crossword resolution task. This paper proposes a semantic-based search approach for generating candidate answer lists for definition type clues by taking advantage of the lexical relations encoded in WordNet, the lexical database for English.

The ability to process language data has become fundamental to the development of technologies in various areas of human life in the digital world. The development of digitally readable linguistic resources, methods, and tools is, therefore, also a key challenge for the contemporary Slovene language. This challenge has been recognized in the Slovene language community both at the professional and state level and has been the subject of many activities over the past ten years, which will be presented in this paper. The idea of a comprehensive dictionary database covering all levels of linguistic description in modern Slovene, from the morphological and lexical levels to the syntactic level, has already formulated within the framework of the European Social Fund’s Communication in Slovene (2008-2013) project; the Slovene Lexical Database was also created within the framework of this project. Two goals were pursued in designing the Slovene Lexical Database (SLD): creating linguistic descriptions of Slovene intended for human users that would also be useful for the machine processing of Slovene. Ever since the construction of the first Slovene corpus, it has become evident that there is a need for a description of modern Slovene based on real language data, and that it is necessary to understand the needs of language users to create useful language reference works. It also became apparent that only the digital medium enables the comprehensiveness of language description and that the design of the database must be adapted to it from the start. Also, the description must follow best practices as closely as possible in terms of formats and international standards, as this enables the inclusion of Slovene into a wider network of resources, such as Open Linked Data, babelNet and ELExIS. Due to time pressures and trends in lexicography, procedures to automate the extraction of linguistic data from corpora and the inclusion of crowdsourcing into the lexicographic process were taken into consideration. Following the essential idea of creating an all-inclusive digital dictionary database for Slovene, a few independent databases have been created over the past two years: the Collocations Dictionary of Modern Slovene, and the automatically generated Thesaurus of Modern Slovene, both of which also exist as independent online dictionary portals. One of the novelties that we put forward together with both dictionaries is the ‘responsive dictionary’ concept, which includes crowdsourcing methods. Ultimately, the Digital Dictionary Database provides all (other) levels of linguistic description: the morphological level with the Sloleks database upgrade, the phraseological level with the construction of a multi-word expressions lexicon, and the syntactic level with the formalization of Slovene verb valency patterns. Each of these databases contains its specific language data that will ultimately be included in the comprehensive Slovene Digital Dictionary Database, which will represent basic linguistic descriptions of Slovene both for the human and machine user., Ideja sveobuhvatne rječničke baze koja uključuje sve razine jezičnoga opisa suvremenoga slovenskog jezika od morfološke i leksičke do sintaktičke prvotno je formulirana u okviru projekta Sporazumijevanje na slovenskomu jeziku (2008. – 2013.). U cilju ostvarenja ideje o stvaranju sveobuhvatne digitalne rječničke baze stvorene su dvije neovisne baze podataka: Kolokacijski rječnik suvremenoga slovenskoga jezika i automatski generiran Tezaurus modernoga slovenskoga jezika. Jedna od novina u obama rječnicima koncept je responzivnoga rječnika, koji uključuje masovnu podršku. Digitalna rječnička baza sadržava sve razine jezičnoga opisa: morfološku nadograđenu Sloleksom, izraznu s opisom konstrukcija višerječnih jedinica te sintaktičku s formalizacijom modela glagolskih valencija. Svaka od postojećih baza podataka sadržava specifične jezične podatke koji će biti uključeni u sveobuhvatnu Slovensku digitalnu rječničku bazu podataka, koja će sadržavati temeljni jezikoslovni opis slovenskoga jezika čiji korisnici mogu biti ljudi i strojevi.

This article describes the first release version of a new lexicostatistical database of Northern Eurasia, which includes Europe as the most well-researched linguistic area. Unlike in other areas of the world, where databases are restricted to covering a small number of concepts as far as possible based on often sparse documentation, good lexical resources providing wide coverage of the lexicon are available even for many smaller languages in our target area. This makes it possible to attain near-completeness for a substantial number of concepts. The resulting database provides a basis for rich benchmarks that can be used to test automated methods which aim to derive new knowledge about language history in underresearched areas.

The similarity between words constitutes significant support to tasks in natural language processing. Several works use Lexical resources such as WordNet for semantic similarity and synonym identification. Nevertheless, words out-of-vocabulary or missing links between senses are perceived problems of this approach. Distributional-based proposals like word embeddings have successfully been used to meet such problems, but the lack of contextual information can prevent the achievement of even better results. The distributional models that include contextual information can bring advantages to this area, but these models are still scarcely explored. Therefore, this work studies the advantages of incorporating syntactic information in the distributional models, fostering for better results in semantic similarity approaches. For that purpose, the current work explore existing lexical and distributional techniques regarding the measurement of word similarity in Brazilian Portuguese. Experiments were carried out with the lexical database WordNet, using different techniques over a standard dataset. The results indicate that word embeddings can cover words out of vocabulary and have better results in comparison with lexical approaches. The main contribution of this article is a new approach to apply syntactic context in the training process of word embeddings to a Brazilian Portuguese corpus. The comparison of this model with the outcome of the previous experiments shows sound results and presents relevant complementary aspects.

Being less resource languages, Indian-Indian and English-Indian language MT system developments faces the difficulty to translate various lexical phenomena. In this paper, we present our work on a comparative study of 440 phrase-based statistical trained models for 110 language pairs across 11 Indian languages. We have developed 110 baseline Statistical Machine Translation systems. Then we have augmented the training corpus with Indowordnet synset word entries of lexical database and further trained 110 models on top of the baseline system. We have done a detailed performance comparison using various evaluation metrics such as BLEU score, METEOR and TER. We observed significant improvement in evaluations of translation quality across all the 440 models after using the Indowordnet. These experiments give a detailed insight in two ways : (1) usage of lexical database with synset mapping for resource poor languages (2) efficient usage of Indowordnet sysnset mapping. More over, synset mapped lexical entries helped the SMT system to handle the ambiguity to a great extent during the translation., Comment: 4 pages with 3 tables submitted to LREC 2018

Purpose This paper aims to describe the structure of an aligned Serbian-German literary corpus (SrpNemKor) contained in a digital library Bibliša. The goal of the research was to create a benchmark Serbian-German annotated corpus searchable with various query expansions. Design/methodology/approach The presented research is particularly focused on the enhancement of bilingual search queries in a full-text search of aligned SrpNemKor collection. The enhancement is based on using existing lexical resources such as Serbian morphological electronic dictionaries and the bilingual lexical database Termi. Findings For the purpose of this research, the lexical database Termi is enriched with a bilingual list of German-Serbian translated pairs of lexical units. The list of correct translation pairs was extracted from SrpNemKor, evaluated and integrated into Termi. Also, Serbian morphological e-dictionaries are updated with new entries extracted from the Serbian part of the corpus. Originality/value A bilingual search of SrpNemKor in Bibliša is available within the user-friendly platform. The enriched database Termi enables semantic enhancement and refinement of user’s search query based on synonyms both in Serbian and German at a very high level. Serbian morphological e-dictionaries facilitate the morphological expansion of search queries in Serbian, thereby enabling the analysis of concepts and concept structures by identifying terms assigned to the concept, and by establishing relations between terms in Serbian and German which makes Bibliša a valuable Web tool that can support research and analysis of SrpNemKor.

To objectively and quantitatively study transcribed protocols of design problem solving conversations, we propose a semantic analysis approach based on dynamic semantic networks of nouns constructed with WordNet 3.1 lexical database. We examined the applicability of the semantic approach focused on a dynamic evaluation of the design problem solving process in educational settings. Using a case of real- world design problem-solving conversations, we show that the approach is able to determine the time dynamics of semantic factors such as level of abstraction, polysemy or information content, and quantify convergence/divergence of semantic similarity in design conversations between students, instructors and real clients. The approach can also be used to evaluate the aforementioned semantic factors for successful and unsuccessful ideas generated in the process of design problem solving, or to assess the effect of external feedback on the developed design solution. The proposed semantic analysis approach allows fast computation of the semantic factors in real time thereby demavonstrating a potential for both monitoring and support of the design problem solving process.

Generating novel design concepts is a cornerstone for producing innovative products. Although many methods have been proposed for supporting the task, their performance depends on human ability. The goal of this research is to build a method supporting designers to generate novel design concepts with the knowledge of what factors have positive effects on the novelty. Toward the goal, this research assumes that the more distant two function concepts chosen, the more novel idea would come up with by the combination of the two concepts. Based on the assumption, this paper introduces a notion of novelty potential of the combination of two function concepts, and proposes a method to assess it by the function similarity. It is calculated with the integration of a lexical database for natural language called WordNet and a distributional semantics method called word2vec. The proposed method is adapted to case studies in which students perform design concept generation for given design tasks. The correlation analysis is performed to verify the assessment performance of the proposed method. This paper discusses its possibility based on the results of the case studies.

Corpus-based research has formed the backbone of linguistic research in recent decades. Large text corpora are used for solving various kinds of linguistic problems, including those of quantitative linguistics, cognitive linguistics, and psycholinguistics. This paper reports the creation of two corpora of contemporary Vietnamese. It also describes the construction of these two equally sized Vietnamese corpora (a corpus from Vietnamese film subtitles, subtlex-viet, and a general corpus of varieties of online newspapers and stories, genlex-viet). We document the general steps of the construction and extraction of linguistic information from the language corpora and provide a road map for others who would like to create similar corpora. The resultant corpora are available in three versions: plain text, tokenized, and POS tagged. In the second half of the paper, the construction of a lexical database derived from the corpora is described. The database includes measures such as frequency of occurrence, dispersion, Mutual Information, Inverse Document Frequency, as well as vector space measures based on Latent Semantic Analysis and Hyperspace Analogue to Language. We conclude by reporting a comparison of the lexical predictors and a validation using psycholinguistic data from visual lexical decision experiments.

In this article, we present Procura-PALavras (P-PAL), a Web-based interface for a new European Portuguese (EP) lexical database. Based on a contemporary printed corpus of over 227 million words, P-PAL provides a broad range of word attributes and statistics, including several measures of word frequency (e.g., raw counts, per-million word frequency, logarithmic Zipf scale), morpho-syntactic information (e.g., parts of speech [PoSs], grammatical gender and number, dominant PoS, and frequency and relative frequency of the dominant PoS), as well as several lexical and sublexical orthographic (e.g., number of letters; consonant-vowel orthographic structure; density and frequency of orthographic neighbors; orthographic Levenshtein distance; orthographic uniqueness point; orthographic syllabification; and trigram, bigram, and letter type and token frequencies), and phonological measures (e.g., pronunciation, number of phonemes, stress, density and frequency of phonological neighbors, transposed and phonographic neighbors, syllabification, and biphone and phone type and token frequencies) for 53,000 lemmatized and 208,000 nonlemmatized EP word forms. To obtain these metrics, researchers can choose between two word queries in the application: (i) analyze words previously selected for specific attributes and/or lexical and sublexical characteristics, or (ii) generate word lists that meet word requirements defined by the user in the menu of analyses. For the measures it provides and the flexibility it allows, P-PAL will be a key resource to support research in all cognitive areas that use EP verbal stimuli. P-PAL is freely available at http://p-pal.di.uminho.pt/tools., This study was conducted at the Psychology Research Centre (PSI/01662), University of Minho. It was supported by the Portuguese Foundation for Science and Technology and the Portuguese Ministry of Science, Technology, and Higher Education through national funds, and co-financed by FEDER through European funds (Grant POCI-01-0145-FEDER-007653).

We apply an analytical method to decompose inflected verbs in Bengali. We treat these verbs as autonomous and isolated linguistic units that are physically free from their contextualized frames of occurrence in sentences. The basic goal behind applying this strategy is to retrieve various kinds of morphological information from inflected Bengali verbs. Other goals are to develop a verb root database, a verb suffix database, and a semi-supervised verb analysis system. To achieve these goals, we apply a rule-based suffix stripping method based on knowledge and information obtained from a manual analysis of a large number of inflected verbs that are used in the Bengali written corpus. Our system first accepts an inflected verb as a lexical input, treats it as a word of an unbroken string of characters, applies stripping rules for root and suffix segmentation, matches segmented parts with respective roots and suffix lists, extracts relevant information from a machine-readable inbuilt dictionary, and displays outputs with information about the constituents that are used to generate the final inflected form. The outputs are root lists, suffix lists, morph lists, grammatical rules, and matching algorithms all of which are necessary for developing a morphological analyzing system for Bengali. The lexical database, morph lists, and metadata that are produced through this method are also useful for developing systems which work for lexical information retrieval and lexical teaching. The method that we use here can be applied for decomposing inflected verbs of other Indian languages by replacing the respective root and suffix databases and concatenation rules.

Cloud-based enterprise search services (e.g., AWS Kendra) have been entrancing big data owners by offering convenient and real-time search solutions to them. However, the problem is that individuals and organizations possessing confidential big data are hesitant to embrace such services due to valid data privacy concerns. In addition, to offer an intelligent search, these services access the user’s search history that further jeopardizes his/her privacy. To overcome the privacy problem, the main idea of this research is to separate the intelligence aspect of the search from its pattern matching aspect. According to this idea, the search intelligence is provided by an on-premises edge tier and the shared cloud tier only serves as an exhaustive pattern matching search utility. We propose Smartness at Edge (SAED mechanism that offers intelligence in the form of semantic and personalized search at the edge tier while maintaining privacy of the search on the cloud tier. At the edge tier, SAED uses a knowledge-based lexical database to expand the query and cover its semantics. SAED personalizes the search via an RNN model that can learn the user’s interest. A word embedding model is used to retrieve documents based on their semantic relevance to the search query. SAED is generic and can be plugged into existing enterprise search systems and enable them to offer intelligent and privacy-preserving search without enforcing any change on them. Evaluation results on two enterprise search systems under real settings and verified by human users demonstrate that SAED can improve the relevancy of the retrieved results by on average ≈24% for plain-text and ≈75% for encrypted generic datasets.

In this chapter, we describe a process of lemmatization of inflected nouns in Bengali as a part of lexical processing. Inflected nouns are used at a very high frequency in Bengali texts. We first collect a large number of inflected nouns from a Bengali corpus and compile a noun database. Then we apply a process of lemmatization to separate inflections from nominal bases. There are several intermediate stages in lemmatization which are applied following grammatical mapping rules (GMRs). These rules isolate inflections from nominal bases. The GMRs are first designed manually after analyzing a large set of inflected nouns to collect necessary data and information. At subsequent stages, these GMRs are developed in a machine-readable format so that the lemmatizer can separate the inflections from inflected nouns with the least human intervention. This strategy is proved to be largely successful in the sense that most of the inflected Bengali nouns, which are stored in a noun database, are rightly lemmatized. This multilayered process also generates an exhaustive list of nominal inflections and a large list of lemmatized nouns. At the subsequent stage, nouns are semantically classified for their use in translation, dictionary compilation, lexical decomposition, and language teaching. We have also applied this method to lemmatize inflected pronouns and adjectives which follow a similar pattern of inflection and affixation in Bengali.

FrameNet is a lexical semantic resource based on the linguistic theory of frame semantics. A number of framenet development strategies have been reported previously and all of them involve exploration of corpora and a fair amount of manual work. Despite previous efforts, there does not exist a well-thought-out automatic/semi-automatic methodology for frame construction. In this paper we propose a data-driven methodology for identification and semi-automatic construction of frames. As a proof of concept, we report on our initial attempts to build a wider-scale framenet for the legal domain (LawFN) using the proposed methodology. The constructed frames are stored in a lexical database and together with the annotated example sentences they have been made available through a web interface.

Despite the remarkable advances made in recent years to facilitate the lexicographer’s work of interpreting and synthesizing the complexity of language uncovered by corpora, an uncritical use of cutting-edge corpus tools and resources can instill a false sense of assurance. In this paper, authentic examples pertaining to wordlist use, collocation research and example selection that arose when compiling a real-world lexical database are discussed through the lens of problems that can easily slip through the cracks in e-lexicography. In doing so, we emphasize the importance of solid training and sound lexicographic judgment when using corpora, corpus tools and corpus-derived resources, and provide an opportunity to reflect on how e-lexicography can be further refined in the future.

The exponentially evolving size of information today has made it difficult to find relevant information quickly and efficiently. A good extractive text summarizer not only provides the most significant information from the document but also helps the user to decide the relevance of the information. The proposed method is a knowledge-based, generic, extractive text summarization technique. Our approach is based on the centrality of a sentences in the graphical representation of the documents. The graph is constructed using the pair-wise softcosine similarity measures between the sentences derived using the S semantic relations presented in WordNet lexical database. Eigenvector centrality measure outperforms the weighted degree, betweenness and closeness centrality measures. The resultant summary is compared against the gold-standard summaries of BBC news articles from year 2004 to 2005 and DUC 2007 datasets. The ROUGE-I, -2 and -Lmetrices are used to evaluate the results and found that our approach performs better than LexRank, TextRank, Luhn and LSA baseline text summarizers.

'Synonym' is an imperative instrument of commonsense knowledge that we apply to make a good sense and sound judgement of our reading. To investigate the ability of machine comprehension models in handling the synonym commonsense knowledge, we developed an innovative approach to automatically generate a dataset based on the Stanford Question Answering Dataset (SQuAD 2.0). The brand-new dataset consists of additional distracting sentences or questions spawned using synonym commonsense knowledge. We formulated new questions by replacing noun entities of the original ones in SQuAD 2.0 with their synonyms. This approach followed the two fundamental principles of SQuAD 2.0 dataset: relevancy and plausibility (incorrect answers are more challenging if they are relevant and plausible). It improves the robustness/abstraction of the question set. To improve the synonym selection strategy in Word Sense Disambiguation (WSD) problem, we designed a new algorithm Multiple Source Adapted Lesk Algorithm (MSALA). Rather than only using WordNet as the source of gloss for adapted Lesk algorithm, we used both lexical database WordNet and commonsense database ConceptNet. This fusion provides a rich hierarchy of semantic relations for the MSALA algorithm. Using this method, we devised 11,000 questions and evaluated the performance of the state-of-the-art question answering system-BERT. Our result shows that the accuracy of the contemporary BERT-Base model dropped from 74.98% to 63.24%. This 10+% accuracy drop revealed the limitations of BERT in handling synonym commonsense knowledge.

Due to technological revolution over the years, bullying which was confined to physical boundaries has now moved online. Denigration or insult is one form of cyberbullying. According to Sri Lanka Computer Emergency Readiness Team, social media cyberbullying incidents are escalating. Insulting words are dynamic, and same word can have several meanings according to the context. Simply because a comment contains such a word, it cannot be classified as bullying. Hence, when labeling comments, simple keyword spotting techniques are inadequate. Other languages have addressed this issue using lexical databases such as WordNet which provides synonyms and homonyms of words. Since there is no proper lexical database developed for Sinhala language, detecting a word as bullying is a challenge. Therefore, we used rules to overcome this issue. Twitter comments with profane words were collected, outliers were removed, and remaining tweets were pre-processed. To determine insult in the text, five rules were used for feature extraction. Afterward, we applied Support Vector Machine (SVM), K-nearest neighbor (KNN) and Naive Bayes algorithms. The results show that SVM with an RBF kernel performs better with an F1-score of 91%. Novelty of this research is the focus on Sinhala language cyberbully detection which has not been addressed before.

2 98 81 19 M50 М53 In this paper, we will present an approach in transforming Serbian language Morphological dictionaries from a DELA text format to a lexical database dubbed Leximirka. Considering the benefits of storing data within a database when compared to storing them in textual documents, we will outline some of the functionality that the database has made possible. We will also show how hand-made rules that use category labels lexical entries are marked with can be used to link lexical entries. The initial morphological dictionaries were Serbian Morphological Dictionaries. However, we will show multilingual application of Leximirka using French Morphological Dictionaries.

The semantic analysis field has a crucial role to play in the research related to text analytics. Calculating the semantic similarity between sentences is a long-standing problem in the area of natural language processing, and it differs significantly as the domain of operation differs. In this paper, we present a methodology that can be applied across multiple domains by incorporating corpora-based statistics into a standardized semantic similarity algorithm. To calculate the semantic similarity between words and sentences, the proposed method follows an edge-based approach using a lexical database. When tested on both benchmark standards and mean human similarity dataset, the methodology achieves a high correlation value for both word ( $r=0.8753$ ) and sentence similarity ( $r=0.8793$ ) concerning Rubenstein and Goodenough standard and the SICK dataset ( $r=0.8324 $ 1 ) outperforming other unsupervised models. 1 Eliminating the outliers which constitutes to 3.75% of 4927 statement pairs

Deep neural networks (DNNs) have become the gold standard for solving challenging classification problems, especially given complex sensor inputs (e.g., images and video). While DNNs are powerful, they are also brittle, and their inner workings are not fully understood by humans, leading to their use as "black-box" models. DNNs often generalize poorly when provided new data sampled from slightly shifted distributions; DNNs are easily manipulated by adversarial examples; and the decision-making process of DNNs can be difficult for humans to interpret. To address these challenges, we propose integrating DNNs with external sources of semantic knowledge. Large quantities of meaningful, formalized knowledge are available in knowledge graphs and other databases, many of which are publicly obtainable. But at present, these sources are inaccessible to deep neural methods, which can only exploit patterns in the signals they are given to classify. In this work, we conduct experiments on the ADE20K dataset, using scene classification as an example task where combining DNNs with external knowledge graphs can result in more robust and explainable models. We align the atomic concepts present in ADE20K (i.e., objects) to WordNet, a hierarchically-organized lexical database. Using this knowledge graph, we expand the concept categories which can be identified in ADE20K and relate these concepts in a hierarchical manner. The neural architecture we present performs scene classification using these concepts, illuminating a path toward DNNs which can efficiently exploit high-level knowledge in place of excessive quantities of direct sensory input. We hypothesize and experimentally validate that incorporating background knowledge via an external knowledge graph into a deep learning-based model should improve the explainability and robustness of the model.

Transcending the boundaries of printed lexicographic resources is becoming easier in the digital age, with e-resources facilitating restrictions on the size and type of information that can be included. In this article we explore innovative ways of documenting and preserving African indigenous knowledge, often underrepresented in traditional dictionaries, in an existing digital lexical database. Our approach is based on the extension of the African Wordnet, a lexical database under construction for nine African languages, in this case applied to isiZulu. This article addresses the challenge of consolidating dispersed indigenous knowledge collected from a variety of sources such as conventional dictionaries, interdisciplinary publications and a flat-structured online database, in a digitised hierarchical wordnet structure. A representative sample of traditional domestic utensils in Zulu culture is used to demonstrate the conversion into a set of typical semantic relations in a wordnet structure. By focusing on filling lexical gaps between isiZulu and English as found in the Princeton WordNet, with culturally relevant synsets, the African Wordnet also becomes a useful resource for natural language processing. Finally, it is shown how the hierarchical classification of selected domestic utensils is visually presented in wordnet graphs in the WordnetLoom interface.

O VerboWeb é um banco de dados lexicais do português brasileiro, em desenvolvimento, que conta atualmente com mais de 1360 verbos classificados em classes e em subclasses, de acordo com suas propriedades sintático-semânticas. Neste artigo, apresentamos uma proposta de classificação verbal por propriedades léxico-gramaticais. Mostramos como se deu a classificação verbal utilizada no VerboWeb e os possíveis níveis de classificação dos verbos. Propomos que são necessárias para a descrição e análise do léxico verbal do português brasileiro dois níveis de classificação: classes e subclasses. Explicitamos a que nível de granularidade estão associadas as classes e subclasse do banco.

High internet usage in Indonesia brings a number of data user opinions. User opinion data can be processed into information that is useful for decision making, data searching and researching for production and marketing strategies. This research conducted a survey on some Indonesian Sentiment Analysis research articles. Some of these studies have different topics and data sources, butuse Sentiwordnet as a lexical database. The results of this survey show the performance of Sentiwordnet can improve classification accuracy in the Sentiment analysis system for Indonesian text. Keywords : user opinion, Indonesian, sentiwordnet, sentiment analysis

The proposed work aims to explore and compare the potency of syntactic-semantic based linguistic structures in plagiarism detection using natural language processing techniques. The current work explores linguistic features, viz., part of speech tags, chunks and semantic roles in detecting plagiarized fragments and utilizes a combined syntactic-semantic similarity metric, which extracts the semantic concepts from WordNet lexical database. The linguistic information is utilized for effective pre-processing and for availing semantically relevant comparisons. Another major contribution is the analysis of the proposed approach on plagiarism cases of various complexity levels. The impact of plagiarism types and complexity levels, upon the features extracted is analyzed and discussed. Further, unlike the existing systems, which were evaluated on some limited data sets, the proposed approach is evaluated on a larger scale using the plagiarism corpus provided by PAN11http://pan.webis.de. competition from 2009 to 2014. The approach presented considerable improvement in comparison with the top-ranked systems of the respective years. The evaluation and analysis with various cases of plagiarism also reflected the supremacy of deeper linguistic features for identifying manually plagiarized data.

Word sense disambiguation (WSD) refers to the task of finding the intended meaning of a word in a given sentence. WordNet® (lexical database based on psychological principals) based on WSD methods have been discussed extensively. WordNet® relates words through various relations and all the WSD approaches available in the literature till date rely on the notion of assigning equal importance to each relation. But actually in real-world situations, these relations do not exhibit equal importance, so they should not be given equal weight. The paper presents a novel method for exploiting the idea of WordNet® relations weight based on its importance and thus assigns the weights to the edges of the WordNet® graph, µ ∊ (0, 1]. This helps in fuzzifying the WordNet® graph, where nodes represent the words and weighted edges represent the relation of the words with strength∈ (0,1]. The values for edge weight assignment are obtained using test cases based on a simulated annealing method. The proposed method utilizes various Fuzzy graph connectivity measures to determine the significance of each node in the Fuzzy graph, resulting in identification of the intended meaning of the word. This method is tested on the SemCor dataset and observed that it gives better results when compared to state-of-the-art approaches.

In this article, we present StimulStat - a lexical database for the Russian language in the form of a web application. The database contains more than 52,000 of the most frequent Russian lemmas and more than 1.7 million word forms derived from them. These lemmas and forms are characterized according to more than 70 properties that were demonstrated to be relevant for psycholinguistic research, including frequency, length, phonological and grammatical properties, orthographic and phonological neighborhood frequency and size, grammatical ambiguity, homonymy and polysemy. Some properties were retrieved from various dictionaries and are presented collectively in a searchable form for the first time, the others were computed specifically for the database. The database can be accessed freely at http://stimul.cognitivestudies.ru .

This study concerns the impact of the collocation/phraseme disambiguation component within the complex system of the rule-based morphological disambiguation of Czech. This system constitutes one of the two main disambiguation subsystems that are responsible for the morphological disambiguation of the corpora of synchronic Czech within the Czech National Corpus project. We will show that although the part of texts constituted by collocations/phrasemes (generally multiword expressions – MWEs) is relatively small and consequently the errorfree morphological disambiguation of MWEs covers only a small portion of textual material, such perfectly disambiguated fragments in sentences help to improve the disambiguation of the rest, non-MWE part of sentences.

Plagiarism takes place when we use any person’s work without giving due acknowledgment. There are several fields where the text similarity is involved like web document retrieval, information mining, and searching related articles. Several approaches have been introduced for detecting plagiarism in the text documents based on the syntactic structure of the text, string similarity, fingerprinting, semantic meaning underlying the text, etc. The basic limitation of plagiarism detection systems these days is that they fail to detect tough cases of plagiarism. The proposed plagiarism detection approach is the hybrid of semantic and syntactic similarity between the text documents. This novel approach exploits linguistic information sources non-linearly using the lexical database for finding the relatedness between text documents. The proposed approach uses semantic knowledge to perform cognitive-inspired computing. The framework is capable of detecting intelligent plagiarism cases like a verbatim copy, paraphrasing, rewording in a sentence, and sentence transformation. The approach has been evaluated on the standard PAN-PC-11 dataset. The experiments show that our technique has outperformed other strong baseline techniques in terms of precision, recall, F-measure, and plagiarism detection (PlagDet) score.

Cognitive mechanisms for sign language lexical access are fairly unknown. This study investigated whether phonological similarity facilitates lexical retrieval in sign languages using measures from a new lexical database for American Sign Language. Additionally, it aimed to determine which similarity metric best fits the present data in order to inform theories of how phonological similarity is constructed within the lexicon and to aid in the operationalization of phonological similarity in sign language. Sign repetition latencies and accuracy were obtained when native signers were asked to reproduce a sign displayed on a computer screen. Results indicated that, as predicted, phonological similarity facilitated repetition latencies and accuracy as long as there were no strict constraints on the type of sublexical features that overlapped. The data converged to suggest that one similarity measure, MaxD, defined as the overlap of any 4 sublexical features, likely best represents mechanisms of phonological similarity in the mental lexicon. Together, these data suggest that lexical access in sign language is facilitated by phonologically similar lexical representations in memory and the optimal operationalization is defined as liberal constraints on overlap of 4 out of 5 sublexical features-similar to the majority of extant definitions in the literature.

The task of building an ontology from a textual corpus starts with the conceptualization phase, which extracts ontology concepts. These concepts are linked by semantic relationships. In this paper, we describe an approach to the construction of an ontology from an Arabic textual corpus, starting first with the collection and preparation of the corpus through normalization, removing stop words and stemming; then, to extract terms of our ontology, a statistical method for extracting simple and complex terms, called "the repeated segments method" are applied. To select segments with sufficient weight we apply the weighting method term frequency---inverse document frequency (TF---IDF), and to link these terms by semantic relationships we apply an automatic method of learning linguistic markers from text. This method requires a dataset of relationship pairs, which are extracted from two external resources: an Arabic dictionary of synonyms and antonyms and the lexical database Arabic WordNet. Finally, we present the results of our experimentation using our textual corpus. The evaluation of our approach shows encouraging results in terms of recall and precision.

This article describes the procedures employed during the development of the first comprehensive machine-readable Turkish Sign Language (TiD) resource: a bilingual lexical database and a parallel corpus between Turkish and TiD. In addition to sign language specific annotations (such as non-manual markers, classifiers and buoys) following the recently introduced TiD knowledge representation(Eryiğit etal.2016), the parallel corpus contains also annotations of dependency relations, which makes it the first parallel treebank between a sign language and an auditory-vocal language.

Scene graph is a graph representation that explicitly represents high-level semantic knowledge of an image such as objects, attributes of objects and relationships between objects. Various tasks have been proposed for the scene graph, but the problem is that they have a limited vocabulary and biased information due to their own hypothesis. Therefore, results of each task are not generalizable and difficult to be applied to other down-stream tasks. In this paper, we propose Entity Synset Alignment(ESA), which is a method to create a general scene graph by aligning various semantic knowledge efficiently to solve this bias problem. The ESA uses a large-scale lexical database, WordNet and Intersection of Union (IoU) to align the object labels in multiple scene graphs/semantic knowledge. In experiment, the integrated scene graph is applied to the image-caption retrieval task as a down-stream task. We confirm that integrating multiple scene graphs helps to get better representations of images.

The paper presents the application of non-specialized lexical database and semantic metrics on transcripts of co-design protocols. Three different and previously analyzed design protocols of co-creative sessions in the field of packaging design, carried out with different supporting tools, are used as test-bench to highlight the potential of this approach. The results show that metrics about the Information Content and the Similarity maps with sufficient precision the differences between ICT- and non-ICT-supported sessions so that it is possible to envision future refinement of the approach.

The equivalent term for data visualization is ‘visual communication,’ representing data visually. The theme of data visualization is to convey information clearly, efficiently to users by using graphics, and it helps to have an inner view of data. Data visualization mesmerizes users by changing tedious data into a visually colorful tale. For this, we need data visualization tools that are popular in understanding data easily and visually. When analyzing data, data visualization is one of the steps that aroused to present the data to the users. Big data has come up considerably in recent times and has become an integral part of modern database research. In fact, there is a need for analyzing large amount of data which is temporal. Other characteristics of these datasets are that these are dynamic, noisy and heterogeneous in nature. As a result, to transform these different types of datasets into an accessible and understandable format, we need big data visualization tools. Traditionally, in the beginning, visualization in big data area was done by traditional systems but this approach was not capable of handling variety in datasets. Also, these traditional systems are restricted to deal with the datasets of small size. So, here comes the need for modern systems to analyze variety of datasets in big data, and this modern system gives awareness of modern data visualization tools that supports a variety of big datasets. Henceforth, the comparative analysis on visualization tools and challenges allows user to go with the best visualization tool for analyzing the big data based on the nature of the dataset. Since their inception, several tools have been proposed to model and analyze the process of data visualization in big datasets. In this chapter, we propose to analyze these tools in the form of their strengths and weaknesses. Also, we have planned to discuss in detail their applications and suitability in dealing with different situations (Caldarola, Picariello, & Rinaldi in Experiences in wordnet visualization with labeled graph database. Berlin: Springer, pp. 80–99, [1], Caldarola, Picariello, Rinaldi, & Sacco in Exploration and visualization of big graphs—The DBpedia case study. KDIR (IC3K 2016), pp. 257–264, [2], Caldarola, & Rinaldi in Improving the visualization of wordnet large lexical database through semantic tag clouds. IEEE, pp. 34–41 [3]).

Healthcare systems have increased patients’ exposure to their own health materials to enhance patients’ health levels, but this has been impeded by patients’ lack of understanding of their health material. We address potential barriers to their comprehension by developing a context-aware text simplification system for health material. Given the scarcity of annotated parallel corpora in healthcare domains, we design our system to be independent of a parallel corpus, complementing the availability of data-driven neural methods when such corpora are available. Our system compensates for the lack of direct supervision using a biomedical lexical database: Unified Medical Language System (UMLS). Compared to a competitive prior approach that uses a tool for identifying biomedical concepts and a consumer-directed vocabulary list, we empirically show the enhanced accuracy of our system due to improved handling of ambiguous terms. We also show the enhanced accuracy of our system over directly-supervised neural methods in this low-resource setting. Finally, we show the direct impact of our system on laypeople’s comprehension of health material via a human subjects’ study (n=160).

Semantic Textual Similarity (STS) measures the degree of semantic equivalence between two snippets of text. It has applicability in a variety of Natural Language Processing (NLP) tasks. Due to the wide application range of STS in many fields, there is a constant demand for new methods as well as improvement in current methods. A surge of unsupervised and supervised systems has been proposed in this field but they pose a limitation in terms of scale. The restraints are caused either by the complex, non-linear sophisticated supervised learning models or by unsupervised learning models that employ a lexical database for word alignment. The model proposed here provides a spectral learning-based approach that is linear, scale-invariant, scalable, and fairly simple. The work focuses on finding semantic similarity by identifying semantic components from both the sentences that maximize the correlation amongst the sentence pair. We introduce an approach based on Canonical Correlation Analysis (CCA), using cosine similarity and Word Mover’s Distance (WMD) as a calculation metric. The model performs at par with sophisticated supervised techniques such as LSTM and BiLSTM and adds a layer of semantic components that can contribute vividly to NLP tasks.

The document descriptors are widely researched and developed in the NLP literature. This study deals with the task of designing context-aware document descriptors, which can be used for information retrieval (IR) based on generic queries. We propose a graph-based data structure that preserves contextual as well as structural information of the document. We also design a novel metric for calculating fuzzy similarity between two vectors. Three different types of contexts, collocational words co-occurring frequently with the keyword in the given paper (C1), collocational words co-occurring with the keyword in the defined corpus (C2), and words synonymous with the keywords in the WordNet lexical database (C3) were used. Each document in a corpus of research papers was represented with a context annotated graph (CAG). These graphs were vectorized, and similarity between paper vector and the query vector was calculated by using fuzzy similarity metric. We compare the results of generic search queries using average weighted precision (AWP) and discounted cumulative gain (DCG) performance metric. The descriptor with contextual information coupled with fuzzy similarity algorithm (AWP score of 0.915 and DCG score of 0.922) outperforms baseline of non-contextual, cosine similarity-based results (AWP score of 0.752 and DCG score of 0.796). We also concluded that contextual information gives better result with fuzzy similarity (AWP score of 0.915 and DCG score of 0.922) than with cosine similarity (AWP score of 0.865 and DCG score of 0.912).

Communication is an essential part of human life. For the person with hearing and speaking disability, it is inconvenient to communicate with other people. In this paper, an end-to-end system to convert English voice to Indian Sign Language (ISL) gloss (written form of sign language) is proposed which will help deaf to communicate with others and vice versa. This system accepts English voice as an input and, converts it into the text using the speech recognition. From the recognized English text, ISL gloss is generated using the lexical database called WordNet. The focus of our work is to build a robust sign language machine translation system to convert the English text to ISL gloss using the linguistic database WordNet.

The emergence of China as a global economic power in the 21st Century has brought about surging needs for cross-lingual and cross-cultural mediation, typically performed by translators. Advances in Artificial Intelligence and Language Engineering have been bolstered by Machine learning and suitable Big Data cultivation. They have helped to meet some of the translator’s needs, though the technical specialists have not kept pace with the practical and expanding requirements in language mediation. One major technical and linguistic hurdle involves words outside the vocabulary of the translator or the lexical database he/she consults, especially Multi-Word Expressions (Compound Words) in technical subjects. A further problem is in the multiplicity of renditions of a term in the target language. This paper discusses a proactive approach following the successful extraction and application of sizable bilingual Multi-Word Expressions (Compound Words) for language mediation in technical subjects, which do not fall within the expertise of typical translators, who have inadequate appreciation of the range of new technical tools available to help him/her. Our approach draws on the personal reflections of translators and teachers of translation and is based on the prior R&D efforts relating to 300,000 comparable Chinese-English patents. The subsequent protocol we have developed aims to be proactive in meeting four identified practical challenges in technical translation (e.g. patents). It has broader economic implication in the Age of Big Data (Tsou et al, 2015) and Trade War, as the workload, if not, the challenges, increasingly cannot be met by currently available front-line translators. We shall demonstrate how new tools can be harnessed to spearhead the application of language technology not only in language mediation but also in the “teaching” and “learning” of translation. It shows how a better appreciation of their needs may enhance the contributions of the technical specialists, and thus enhance the resultant synergetic benefits.

According to World Intellectual Property Organization (2017) report, over 3 million patents exist in the patent database, but only certain numbers have commercial potential. Generally, to assess the commercial potential of patent, it consumes time and requires various expertise. Currently, several models have been developed to address this matter, which to assess using questionnaire tool for portfolios by human. So that occurs bias any limitation exists that our research will address by artificial intelligence. Hence, this research applies a Natural Language Programming to assess for commercial potential of patent, consisting of five steps — (i) Morphological analysis based on the Lexical database, (ii) Syntactic analysis of sentence to check syntax sentence patterns, (iii) Sematic analysis to interpret the meaning of words derived from the previous step, (iv) Discourse integration from context of domain together with the main sentence providing more accurate sentence analysis, and (v) Pragmatic analysis to ensure the correct meaning of interpretation. Then, the obtained data is used to determine criterion factors and formulate the model for assessing commercial potential of patent using Natural Language programming. This finding should deliver an alternative effective patent assessment system, which addresses some current deficiency in patent's assessment for commercial potential.