Search

The advancements in technology, particularly in the field of Natural Language Processing (NLP) and Artificial Intelligence (AI) can be advantageous for the agricultural sector to enhance the yield. Establishing an agricultural ontology as part of the development would spur the expansion of cross-domain agriculture. Semantic and syntactic knowledge of the domain data is required for building such a domain-based ontology. To process the data from text documents, a standard technique with syntactic and semantic features are needed because the availability of pre-determined agricultural domain-based data is insufficient. In this research work, an Agricultural Ontologies Construction framework (AOC) is proposed for creating the agricultural domain ontology from text documents using NLP techniques with Robustly Optimized BERT Approach (RoBERTa) model and Graph Convolutional Network (GCN). The anaphora present in the documents are resolved to produce precise ontology from the input data. In the proposed AOC work, the domain terms are extracted using the RoBERTa model with Regular Expressions (RE) and the relationships between the domain terms are retrieved by utilizing the GCN with RE. When compared to other current systems, the efficacy of the proposed AOC method achieves an exceptional result, with precision and recall of 99.6% and 99.1% respectively. [ABSTRACT FROM AUTHOR]

Automatic term extraction from a biomedical text is a well-known problem in the area of natural language processing. It is carried out by employing four kinds of measures: linguistic and rule-based, dictionary-based, statistical, and machine learning. Automatic term extraction indicates whether or not two or more words come together in the text more often than by chance to form a biomedical term that is automatically extracted using an automated system. A fuzzy set-theoretic approach is presented in this article and compares with the existing statistical measures. The experimental result shows that the fuzzy measure offers better precision than the popular statistical measures for extracting biomedical terms, especially when we have compared more than 60% ranked list of extracted terms. [ABSTRACT FROM AUTHOR]

Manual term extraction is similar to literal meaning: A translator browses text, classifies words, and prepares for translation. Terminology, as a centralized carrier of expertise, creation, popularization, and disappearance, dynamically reflects the development and evolution of an industry. The automatic extraction of terminology is a key technology for creating a professional terminology database, and it is also a key topic in the field of natural language processing. The purpose of this paper is to study how to analyse a term extraction algorithm based on machine learning and a comprehensive feature strategy. Focusing on the problems of poor generality and single statistical features of current term extraction algorithms, this paper proposes an improved domain ontology term extraction algorithm based on a comprehensive feature strategy. Moreover, automatic term extraction experiments based on a word-based maximum entropy model and a conditional random field model based on machine learning are conducted in this paper. Its word-based conditional random field model outperforms the maximum entropy model. The experimental results show that the algorithm based on the comprehensive feature strategy improves the accuracy by 8.6% compared with the TF-IDF algorithm and the C-value term extraction algorithm. This algorithm can be used to effectively extract the terms in a text and has good generality. [ABSTRACT FROM AUTHOR]

Intent classification is an essential task for goal-oriented dialogue systems for automatically identifying customers' goals. Although intent classification performs well in general settings, domain-specific user goals can still present a challenge for this task. To address this challenge, we automatically generate knowledge graphs for targeted data sets to capture domain-specific knowledge and leverage embeddings trained on these knowledge graphs for the intent classification task. As existing knowledge graphs might not be suitable for a targeted domain of interest, our automatic generation of knowledge graphs can extract the semantic information of any domain, which can be incorporated within the classification process. We compare our results with state-of-the-art pre-trained sentence embeddings and our evaluation of three data sets shows improvement in the intent classification task in terms of precision. [ABSTRACT FROM AUTHOR]

The development of terminologies for domains where these are lacking is a time-consuming and costly task. This article takes a methodological perspective and addresses a general methodological question: how can we, with limited funding, utilise to a maximal degree, existing language resources to create a terminology at a relatively low cost? Although an important player in the maritime industries for many centuries, Norway has not prioritised the systematic development of an official maritime terminology. The article therefore focuses specifically on efforts to develop a national resource for maritime domains. The article describes efforts to create a corpus of popular science and a parallel corpus of technical texts. Six different term extraction methods are applied. These include corpus-based statistical analyses of frequency, collocation and keyness, as well as bilingual term extraction. Finally, the pros and cons of each method are evaluated by means of a cost-benefit analysis. [ABSTRACT FROM AUTHOR]

With the utility infrastructure domain becoming more technologically advanced with the modeling of all types of information across varying sectors, it is imperative to develop a domain ontology to enable the interoperability across the heterogeneous landscape of information modeling. This paper develops an ontology for the utility infrastructure domain by coupling the semantics of City Geography Markup Language (CityGML) Utility Network application domain extension (ADE)—a candidate open standard for modeling utilities—and domain glossaries, lists of utility terms with their textual definitions. First, a base ontology is formalized by abstracting the modeling information in the ADE through a series of semantic mappings. Second, a novel integrated natural language processing (NLP) approach is devised to automatically learn the semantics from the glossaries. The learning process includes the extraction of utility product terms using conditional random field (CRF) and the classification of semantic relationships between the terms using long short-term memory (LSTM) networks. Finally, the semantics learned from the glossaries are incorporated into the base ontology to result in a domain ontology for utility infrastructure. The NLP approach was evaluated using human-annotated test sets, and results show an average accuracy of 96% in term extraction and 86% in semantic relationship classification. For the case demonstration, a glossary of water product terms was learned to enrich the base ontology and the resulting ontology was evaluated to be an accurate, sufficient, and shared conceptualization of the domain. The newly developed ontology is expected to function effectively as an interoperability facilitator for the utility infrastructure domain, attributed to the semantic compatibility with existing utility modeling initiatives and the enriched/expandable semantic vocabulary. [ABSTRACT FROM AUTHOR]

This paper describes a new system for semi-automatically building, extending and managing a terminological thesaurus — a multilingual terminology dictionary enriched with relationships between the terms themselves to form a thesaurus. The system allows to radically enhance the workow of current terminology expert groups, where most of the editing decisions still come from introspection. The presented system supplements the lexicographic process with natural language processing techniques, which are seamlessly integrated to the thesaurus editing environment. The system's methodology and the resulting thesaurus are closely connected to new domain corpora in the six languages involved. They are used for term usage examples as well as for the automatic extraction of new candidate terms. The terminological thesaurus is now accessible via a web-based application, which (a) presents rich detailed information on each term, (b) visualizes term relations, and (c) displays real-life usage examples of the term in the domain-related documents and in the context-based similar terms. Furthermore, the specialized corpora are used to detect candidate translations of terms from the central language (Czech) to the other languages (English, French, German, Russian and Slovak) as well as to detect broader Czech terms, which help to place new terms in the actual thesaurus hierarchy. This project has been realized as a terminological thesaurus of land surveying, but the presented tools and methodology are reusable for other terminology domains. [ABSTRACT FROM AUTHOR]

This experimental study examines whether use of a corpus-based terminological preparation procedure, managed by a term extraction tool (Syllabs Tools) and a concordance tool (on the Sketch Engine platform), enables trainee interpreters (Chinese A, English B) to achieve greater accuracy in a simultaneous interpreting (SI) task on a specialised topic. Twenty-two interpreting students on a one-year MA course in the UK were divided into a test group (10 students) and a control group (12 students). Nine days before the experiment, which involved SI from the A into the B language as well as vice versa, both groups were given preparatory documentation in both languages. In addition, the test group received term lists automatically generated by the extraction tool and used the Sketch Engine concordance tool. The control group extracted terms manually and did not have the concordance tool. Terminological accuracy in SI was found to be significantly higher, with fewer omissions, even when terms occurred in rapid succession, in the test group. All students afterwards participated in focus group discussions, providing feedback on the effectiveness of their preparation and an estimate of the time they had dedicated to it. In addition, their recall of terms was tested two months later by completion of a 15-item quiz and was found to be significantly better in the test group. [ABSTRACT FROM AUTHOR]

The identification of terms in scientific and patent documents is a crucial issue for applications like information retrieval, text categorization, and also for machine translation. This paper describes a method to improve Chinese-Japanese statistical machine translation of patents by re-tokenizing the training corpus with aligned bilingual multi-word terms. We automatically extract multi-word terms from monolingual corpora by combining statistical and linguistic filtering methods. An automatic alignment method is used to identify corresponding terms. The most promising bilingual multi-word terms are extracted by setting some threshold on translation probabilities and further filtering by considering the components of the bilingual multi-word terms in characters as well as the ratio of their lengths in words. We also use kanji (Japanese)-hanzi (Chinese) character conversion to confirm and extract more promising bilingual multi-word terms. We obtain a high quality of correspondence with 93% in bilingual term extraction and a significant improvement of 1.5 BLEU score in a translation experiment. © 2017 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc. [ABSTRACT FROM AUTHOR]

We evaluate five term scoring methods for automatic term extraction on four different types of text collections: personal document collections, news articles, scientific articles and medical discharge summaries. Each collection has its own use case: author profiling, boolean query term suggestion, personalized query suggestion and patient query expansion. The methods for term scoring that have been proposed in the literature were designed with a specific goal in mind. However, it is as yet unclear how these methods perform on collections with characteristics different than what they were designed for, and which method is the most suitable for a given (new) collection. In a series of experiments, we evaluate, compare and analyse the output of six term scoring methods for the collections at hand. We found that the most important factors in the success of a term scoring method are the size of the collection and the importance of multi-word terms in the domain. Larger collections lead to better terms; all methods are hindered by small collection sizes (below 1000 words). The most flexible method for the extraction of single-word and multi-word terms is pointwise Kullback-Leibler divergence for informativeness and phraseness. Overall, we have shown that extracting relevant terms using unsupervised term scoring methods is possible in diverse use cases, and that the methods are applicable in more contexts than their original design purpose. [ABSTRACT FROM AUTHOR]

Timeliness and precision for detection of infectious animal disease outbreaks from the information published on the web is crucial for prevention against their spread. The work in this paper is part of the methodology for monitoring the web that we currently develop for the French epidemic intelligence team in animal health. We focus on the new and exotic infectious animal diseases that occur worldwide and that are of potential threat to the animal health in France. In order to detect relevant information on the web, we present an innovative approach that retrieves documents using queries based on terms automatically extracted from a corpus of relevant documents and validated with a consensus of domain experts (Delphi method). As a decision support tool to domain experts we introduce a new measure for ranking of extracted terms in order to highlight the more relevant terms. To categorise documents retrieved from the web we use Naïve Bayes (NB) and Support Vector Machine (SVM) classifiers. We evaluated our approach on documents on African swine fever (ASF) outbreaks for the period from 2011 to 2014, retrieved from the Google search engine and the PubMed database. From 2400 terms extracted from two corpora of relevant ASF documents, 135 terms were relevant to characterise ASF emergence. The domain experts identified as highly specific to characterise ASF emergence the terms which describe mortality, fever and haemorrhagic clinical signs in Suidae . The new ranking measure correctly ranked the ASF relevant terms until position 161 and fairly until position 227, with areas under ROC curves (AUCs) of 0.802 and 0.709 respectively. Both classifiers were accurate to classify a set of 545 ASF documents (NB of 0.747 and SVM of 0.725) into appropriate categories of relevant (disease outbreak) and irrelevant (economic and general) documents. Our results show that relevant documents can serve as a source of terms to detect infectious animal disease emergence on the web. Our method is generic and can be used both in animal and public health domain. [ABSTRACT FROM AUTHOR]

In this paper we make two contributions. First, we describe a multi-component system called BiTES (Bilingual Term Extraction System) designed to automatically gather domain-specific bilingual term pairs from Web data. BiTES components consist of data gathering tools, domain classifiers, monolingual text extraction systems and bilingual term aligners. BiTES is readily extendable to new language pairs and has been successfully used to gather bilingual terminology for 24 language pairs, including English and all official EU languages, save Irish. Second, we describe a novel set of methods for evaluating the main components of BiTES and present the results of our evaluation for six language pairs. Results show that the BiTES approach can be used to successfully harvest quality bilingual term pairs from the Web. Our evaluation method delivers significant insights about the strengths and weaknesses of our techniques. It can be straightforwardly reused to evaluate other bilingual term extraction systems and makes a novel contribution to the study of how to evaluate bilingual terminology extraction systems. [ABSTRACT FROM AUTHOR]

For the issue that it is only a few labeled samples in really text classification environment which will affect the classification accuracy, this paper proposed a classification algorithm based on latent Dirichlet allocation using probabilistic topic model. Firstly, it used standard term frequency-inverse document frequency function to represent each document into term weight vector. Then, it used probabilistic topic model as pretreatment to simplify the document, and done term extraction from document. Finally, it used latent Dirichlet allocation model to do relational learning and used classification based on graph to finish classification. The effectiveness of proposed method has been verified by experiments on common resource library Reu-ters-21578. Experimental results show that proposed method has higher classification accuracy than support vector machine which has well classification effect in most cases. [ABSTRACT FROM AUTHOR]

The paper examines the possible usage of event templates derived from Frame-Based Terminology (Faber et al. 2005, 2006, 2007) as an aid to the extraction and management of legal terminology embedded in the multi-level legal system of the European Union. The method proposed here, which combines semi-automatic term extraction and a simplified event template containing six categories, is applied to an English corpus of EU texts focusing on victims of crime and their rights. Such a combination allows for the extraction of category-relevant terminological units and additional information, which can then be used for populating a terminological knowledge base organised on the basis of the same event template, but which also employs additional classification criteria to account for the multidimensionality encountered in the corpus. [ABSTRACT FROM AUTHOR]

In this paper, we describe a methodology used to create a test corpus for the evaluation of term extractors. This methodology relies on term annotation: terms in a corpus on automotive engineering are selected based on specific criteria pertaining to the terminological setting as well as linguistic and formal properties of terms and term variations. The test corpus accounts for the variety of ways in which terms are realized in running text, and provides a means of automatically evaluating the relevance of term candidate lists produced by term extractors. Due to the XML annotation scheme used, the corpus can be customized, e.g. by filtering out some of the annotated terms based on the type of term or term variation, or frequency. In this paper, we focus on the methodological aspects of this work. [ABSTRACT FROM AUTHOR]

Highlights: [•] A graph of terms can be effectively used for text classification. [•] Such a graph is extracted from documents thanks to a LDA based methodology. [•] Proposed method achieves good performances on standard datasets. [•] The approach can discover solutions matching user information needs. [Copyright &y& Elsevier]

Abstract: Existing term extraction systems have predominantly targeted large and well-written document collections, which provide reliable statistical and linguistic evidence to support term extraction. In this article, we address the term extraction challenges posed by sparse, ungrammatical texts with domain-specific contents, such as customer complaint emails and engineers’ repair notes. To this aim, we present ExtTerm, a novel term extraction system. Specifically, as our core innovations, we accurately detect rare (low frequency) terms, overcoming the issue of data sparsity. These rare terms may denote critical events, but they are often missed by extant TE systems. ExtTerm also precisely detects multi-word terms of arbitrarily lengths, e.g. with more than 2 words. This is achieved by exploiting fundamental theoretical notions underlying term formation, and by developing a technique to compute the collocation strength between any number of words. Thus, we address the limitation of existing TE systems, which are primarily designed to identify terms with 2 words. Furthermore, we show that open-domain (general) resources, such as Wikipedia, can be exploited to support domain-specific term extraction. Thus, they can be used to compensate for the unavailability of domain-specific knowledge resources. Our experimental evaluations reveal that ExtTerm outperforms a state-of-the-art baseline in extracting terms from a domain-specific, sparse and ungrammatical real-life text collection. [Copyright &y& Elsevier]

Companies must translate their content if they want to operate multinationally. Both quality and speed of translation are key factors in determining market share in the target market. Proactively managing terminology, including pre-translating key terms for a translation project, has beneficial effects on these factors. However, in commercial environments, the volumes of content and subsequently of the required terminology are typically large. Therefore, integrating terminology into the translation pipeline requires a process that is as automated as possible. Term extraction is the cornerstone of this process, but to maximize efficiency it requires a post-processing strategy that repurposes existing lexical resources. Terms extracted from corpora and subsequently translated should be channeled into the company termbase so that they can be leveraged for other purposes. These and other effective practices for processing extracted terms are discussed, based on the author's experiences in one large company. [ABSTRACT FROM AUTHOR]

This paper evaluates the possibilities of recognizing term candidates through their formal and semantic characteristics. From a cognitive-linguistic stance, the semantic motivation of the word-formation patterns of collocations and compounds in domain-specific texts is assumed to promote their termhood. The semantic motivation to integrate into a multi-word unit is assumed to originate in the generally agreed on generic reference of the modifying constituent. This hypothesis is investigated empirically in a corpus-linguistic experiment. Term candidates instantiating different derivational patterns of adjective-noun constructions have been manually sorted by experts into approved and non-approved terms. Our subsequent linguistic categorization into the morpho-semantic constructions instantiated by the term candidates could be verified quantitatively in terms of relative frequencies. These frequencies clearly divide the term candidates into instances of term-promoting and term-impeding constructions. Obviously, the experts have approved the terms of those constructions which come up with a high relative frequency in the corpus. [ABSTRACT FROM AUTHOR]

In this paper, we address the problem of document re-ranking in information retrieval, which is usually conducted after initial retrieval to improve rankings of relevant documents. To deal with this problem, we propose a method which automatically constructs a term resource specific to the document collection and then applies the resource to document re-ranking. The term resource includes a list of terms extracted from the documents as well as their weighting and correlations computed after initial retrieval. The term weighting based on local and global distribution ensures the re-ranking not sensitive to different choices of pseudo relevance, while the term correlation helps avoid any bias to certain specific concept embedded in queries. Experiments with NTCIR3 data show that the approach can not only improve performance of initial retrieval, but also make significant contribution to standard query expansion. [ABSTRACT FROM AUTHOR]

Term recognition identifies domain-relevant terms which are essential for discovering domain concepts and for the construction of terminologies required by a wide range of natural language applications. Many techniques have been developed in an attempt to numerically determine or quantify termhood based on term characteristics. Some of the apparent shortcomings of existing techniques are the ad-hoc combination of termhood evidence, mathematically-unfounded derivation of scores and implicit assumptions concerning term characteristics. We propose a probabilistic framework for formalising and combining qualitative evidence based on explicitly defined term characteristics to produce a new termhood measure. Our qualitative and quantitative evaluations demonstrate consistently better precision, recall and accuracy compared to three other existing ad-hoc measures. [ABSTRACT FROM AUTHOR]

Abstract: AMTEx is a medical document indexing method, specifically designed for the automatic indexing of documents in large medical collections, such as MEDLINE, the premier bibliographic database of the US National Library of Medicine (NLM). AMTEx combines MeSH, the terminological thesaurus resource of NLM, with a well-established method for extraction of terminology, the C/NC-value method. The performance evaluation of two AMTEx configurations is measured against the current state-of-the-art, the MetaMap Transfer (MMTx) method in four experiments, using two types of corpora: a subset of MEDLINE (PMC) full document corpus and a subset of MEDLINE (OHSUMED) abstracts, for each of the indexing and retrieval tasks, respectively. The experimental results demonstrate that AMTEx performs better in indexing in 20–50% of the processing time compared to MMTx, while for the retrieval task, AMTEx performs better in the full text (PMC) corpus. [Copyright &y& Elsevier]

Term extraction may be defined as a text mining activity whose main purpose is to obtain all the terms included in a text of a given domain. Since the eighties, and mainly due to the rapid scientific advances as well as the evolution of the communication systems, there has been a growing interest in obtaining the terms found in written documents. A number of techniques and strategies have been proposed for satisfying this requirement. At present it seems that term extraction has reached a maturity stage. Nevertheless, many of the systems proposed fail to qualitatively present their results, almost every system evaluates its abilities in an ad hoc manner (if any, many times). Often, the authors do not explain their evaluation methodology; therefore comparisons between different implementations are difficult to draw. In this paper, we review the state-of-the-art of term extraction systems evaluation in the framework of natural language systems evaluation. The main approaches are presented, with a focus on their limitations. As an instantiation of some ideas for overcoming these limitations, the evaluation framework is applied to YATE, a hybrid term extractor. [ABSTRACT FROM AUTHOR]

The recognition and extraction of terms and their variants in texts are crucial processes in text mining. We use the ILC platform, an automatic controlled indexing platform, to perform these linguistic processes. We present a methodology for enhancing the recognition of syntactic term variation in English, using syntactic and morpho-syntactic features. Principal spurious variants of terms are ascribed to incorrect word dependencies. To overcome these problems, we consider each term variant as a window on the sentence and introduce two criteria: an internal syntactic criterion which checks that the dependencies between words in the window are respected, and an external criterion which defines boundaries, making it possible to ensure that the window is well positioned in the sentence. The use of these criteria improves filtering of the variants and assists the expert in validating the indexing. [ABSTRACT FROM AUTHOR]

After a recent breakthrough in the early 90's, text analysis is acknowledged as one of the promising ways to rapidly build better grounded semantic resources such as terminologies and ontologies. This domain has recently undergone significant evolutions with a massive reference to machine learning algorithms and information extraction techniques together with linguistic- and statistic-based natural language processing. This position paper promotes three main ideas: (i) that highly domain-specific or task-specific, even idiosyncratic ontologies, are very useful, especially when they are linked to broader consensual schemes and they can be built with reasonable effort; (ii) that corpus-based ontologies can capture the perspective of a domain; and (iii) that supervised ontology learning from text makes feasible the development of specialized ontologies adapted for specific uses. We propose the establishment of an inventory of tools for building ontologies from text, give a first classification of such tools, and present an initial review of some recent methods and tools. [ABSTRACT FROM AUTHOR]

This paper presents an original natural language processing (NLP) approach for building of back-of-the-book indexes. Our indexing system, IndDoc, exploits some terminological tools and automatically builds an index draft of the analysis of the document text. The indexer then has to validate that index draft through a dedicated interface. This approach has been tested on several documents with promising results. Relying on our experience in developing and testing the IndDoc indexing system, we aim at assessing the contribution of terminological analysis as well as the level of maturity that computational terminology has reached in the indexing perspective. [ABSTRACT FROM AUTHOR]

Current term recognition algorithms have centred mostly on the notion of term based on the assumption that terms are monoreferential and as such independent of context. The characteristics and behaviour of terms in real texts are however far removed from this ideal because factors such as text type or communicative situation greatly influence the linguistic realisation of a concept. Context, therefore, is important for the correct identification of terms (Dubuc and Lauriston, 1997). Based on this assumption, we have shifted our emphasis from terms towards surrounding linguistic context, namely verbs, as verbs are considered the central elements in the sentence. More specifically, we have set out to examine whether verbs and verbal syntax in particular, could help us towards the task of automatic term recognition. Our findings suggest that term occurrence varies significantly in different argument structures and different syntactic positions. Additionally, deviant grammatical structures have proved rich environments for terms. The analysis was carried out in three different specialised subcorpora in order to explore how the effectiveness of verbal syntax as a potential indicator of term occurrence can be constrained by factors such as subject matter and text type. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new approach to enhance automatic recognition systems for domain-specific terms. The approach is based on the statistics about the relation between a compound noun and its constituents that are simple nouns. More precisely, we focus on how many nouns adjoin the noun in question to form compound nouns. We propose several scoring methods based on this approach and experimentally evaluate them on the NTCIR1 TMREC test collection. The results are very promising, especially in low and high recall. [ABSTRACT FROM AUTHOR]

Knowledge graphs are proving to be an increasingly important part of modern enterprises, and new applications of such enterprise knowledge graphs are still being found. In this paper, we report on the experience with the use of an automatic knowledge graph system called Saffron in the context of a large financial enterprise and show how this has found applications within this enterprise as part of the "Conversation Concepts Artificial Intelligence" tool. In particular, we analyse the use cases for knowledge graphs within this enterprise, and this led us to a new extension to the knowledge graph system. We present the results of these adaptations, including the introduction of a semi-supervised taxonomy extraction system, which includes analysts in-the-loop. Further, we extend the kinds of relations extracted by the system and show how the use of the BERTand ELMomodels can produce high-quality results. Thus, we show how this tool can help realize a smart enterprise and how requirements in the financial industry can be realised by state-of-the-art natural language processing technologies. [ABSTRACT FROM AUTHOR]