Search

Faceted Search Systems (FSSs) have gained prominence as one of the dominant search approaches in vertical search systems. They provide facets to educate users about the information space and allow them to refine their search query and navigate back and forth between resources on a single results page. Despite the importance of this problem, it is rare to find studies dedicated solely to the investigation of facet ranking methods, nor to how this step, aside from other aspects of faceted search, affects the user’s search experience. The objective of this survey paper is to review the state of the art in research related to faceted search systems, with a focus on existing facet ranking approaches and the key challenges posed by this problem. In addition to that, this survey also investigates state-of-the-art FSS evaluation frameworks and the most commonly used techniques and metrics to evaluate facet ranking approaches. It also lays out criteria for dataset appropriateness and its needed structure to be used in evaluating facet ranking methods aside from other FSS aspects. This paper concludes by highlighting gaps in the current research and future research directions related to this area.

Additive Manufacturing (AM) using Powder-Bed Fusion Laser-Beam (PBF-LB) has great potential; however, it has challenges due to its sensitivity to the process parameters [1]. The availability of big data generated in AM facilitates the employment of Machine Learning (ML) tools to understand the process and have a predictive control over the production. An intelligent system like this can thus reduce material wastage and energy cost while increasing a plant’s product quality and throughput. Time-series summary statistics (like mean and variance) can discard valuable discriminatory signatures embedded in raw sensor data. Therefore, special ML time-series classification (TSC) tools that can extract and utilise these signatures from the raw data are much more effective for a task like porosity prediction [1]. However, the data employed in [1] pertains to products with artificially designed pores or gaps. This study focuses on naturally occurring pores, rarer, and evaluates k-Nearest Neighbour (k-NN) with Dynamic Time Warping (DTW) over real-world manufacturing data to classify the porosity of individual raster scans. We believe that natural pores have more diverse signatures than artificial pores, as each pore varies in characteristics (like size and morphology).

Co-authored by a Computer Scientist and a Digital Humanist, this article examines the challenges faced by cultural heritage institutions in the digital age, which have led to the closure of the vast majority of born-digital archival collections. It focuses particularly on cultural organizations such as libraries, museums and archives, used by historians, literary scholars and other Humanities scholars. Most born-digital records held by cultural organizations are inaccessible due to privacy, copyright, commercial and technical issues. Even when born-digital data are publicly available (as in the case of web archives), users often need to physically travel to repositories such as the British Library or the Bibliothèque Nationale de France to consult web pages. Provided with enough sample data from which to learn and train their models, AI, and more specifically machine learning algorithms, offer the opportunity to improve and ease the access to digital archives by learning to perform complex human tasks. These vary from providing intelligent support for searching the archives to automate tedious and time-consuming tasks. In this article, we focus on sensitivity review as a practical solution to unlock digital archives that would allow archival institutions to make non-sensitive information available. This promise to make archives more accessible does not come free of warnings for potential pitfalls and risks: inherent errors, "black box" approaches that make the algorithm inscrutable, and risks related to bias, fake, or partial information. Our central argument is that AI can deliver its promise to make digital archival collections more accessible, but it also creates new challenges - particularly in terms of ethics. In the conclusion, we insist on the importance of fairness, accountability and transparency in the process of making digital archives more accessible.

Background: Brain cancer is a destructive and life-threatening disease that imposes immense negative effects on patients’ lives. Therefore, the detection of brain tumors at an early stage improves the impact of treatments and increases the patients survival rates. However, detecting brain tumors in their initial stages is a demanding task and an unmet need. Methods: The present study presents a comprehensive review of the recent Artificial Intelligence (AI) methods of diagnosing brain tumors using MRI images. These AI techniques can be divided into Supervised, Unsupervised, and Deep Learning (DL) methods. Results: Diagnosing and segmenting brain tumors usually begin with Magnetic Resonance Imaging (MRI) on the brain since MRI is a noninvasive imaging technique. Another existing challenge is that the growth of technology is faster than the rate of increase in the number of medical staff who can employ these technologies. It has resulted in an increased risk of diagnostic misinterpretation. Therefore, developing robust automated brain tumor detection techniques has been studied widely over the past years. Conclusion: The current review provides an analysis of the performance of modern methods in this area. Moreover, various image segmentation methods in addition to the recent efforts of researchers are summarized. Finally, the paper discusses open questions and suggests directions for future research. © 2022 Elsevier Ltd

Background: In this paper a new transparency evaluation framework, Cyrus, is proposed for Open Knowledge Extraction (OKE) systems. Cyrus is based on the state-of-the-art AI and data transparency methods and a well-accepted framework for linked data quality evaluation. Then, the transparency of the outputs of three state-of-the-art OKE systems are automatically evaluated using a combination of three state-of-the-art FAIR (Findable, Accessible, Interoperable, Reusable) tools and the Luzzu linked data quality evaluation framework. OKE systems extract structured knowledge from unstructured or semi-structured text and publish that as linked data. These systems can be used as the fundamental component of advanced knowledge services. However, due to the transition from rule-based to black-box machine learning approaches, most OKE systems are not transparent. This means that their processes and outcomes are not understandable and interpretable for humans. As a result, the transparency problem has been identified as critical by European Union Trustworthy AI guidelines. Automatic transparency evaluation helps with scalability and gives a transparency score that allows comparing different systems' transparencies. It also gives insight into the transparency weaknesses of the system and how to enhance the transparency of the system. Accordingly, being able to evaluate the transparency can be the first step of an effective transparency enhancement process. Results: In Cyrus, data transparency includes 27 dimensions which are grouped in two categories. In this paper, Six of these dimensions, i.e., provenance, interpretability, understandability, licensing, availability, interlinking have been evaluated automatically for three state-of-the-art OKE systems, using the state-of-the-art metrics and tools. The highest mean transparency has been approx. 31\%. Conclusions: This is the first research to study automated transparency evaluation for OKE systems. We show that state-of-the-art FAIR assessment tools and linked data quality evaluation techniques are capable of identifying some transparency weaknesses of OKE systems.\end{abstract}

This paper proposes a new accountability and transparency evaluation framework (AccTEF) for ontology-based systems (OSysts). AccTEF is based on an analysis of the relation between a set of widely accepted data governance principles, i.e. findable, accessible, interoperable, reusable (FAIR) and accountability and transparency concepts. The evaluation of accountability and transparency of input ontologies and vocabularies of OSysts are addressed by analyzing the relation between vocabulary and ontology quality evaluation metrics, FAIR and accountability and transparency concepts. An ontology-based knowledge extraction pipeline is used as a use case in this study. Discovering the relation between FAIR and accountability and transparency helps in identifying and mitigating risks associated with deploying OSysts. This also allows providing design guidelines that help accountability and transparency to be embedded in OSysts. We found that FAIR can be used as a transparency indicator. We also found that the studied vocabulary and ontology quality evaluation metrics do not cover FAIR, accountability and transparency. Accordingly, we suggest these concepts should be considered as vocabulary and ontology quality evaluation aspects. To the best of our knowledge, it is the first time that the relation between FAIR and accountability and transparency concepts has been found and used for evaluation.

An automated contextual suggestion algorithm is likely to recommend contextually appropriate and personalized 'points-of-interest' (POIs) to a user, if it can extract information from the user's preference history (exploitation) and effectively blend it with the user's current contextual information (exploration) to predict a POI's 'appropriateness' in the current context. To balance this trade-off between exploitation and exploration, we propose an unsupervised, generic framework involving a factored relevance model (FRLM), constituting two distinct components, one pertaining to historical contexts, and the other corresponding to the current context. We further generalize the proposed FRLM by incorporating the semantic relationships between terms in POI descriptors using kernel density estimation (KDE) on embedded word vectors. Additionally, we show that trip-qualifiers, (e.g. 'trip-type', 'accompanied-by') are potentially useful information sources that could be used to improve the recommendation effectiveness. Using such information is not straight forward since users' texts/reviews of visited POIs typically do not explicitly contain such annotations. We undertake a weakly supervised approach to predict the associations between the review-texts in a user profile and the likely trip contexts. Our experiments, conducted on the TREC contextual suggestion 2016 dataset, demonstrate that factorization, KDE-based generalizations, and trip-qualifier enriched contexts of the relevance model improve POI recommendation., Comment: To appear at Information Retrieval Journal

In this paper, we introduce LifeSeeker 4.0 - an interactive lifelog retrieval system developed for the fifth annual Lifelog Search Challenge (LSC'22). In LifeSeeker 4.0, we focus on enhancing our previous system to allow users who have little to no knowledge of underlying system functioning and lifelog data to use it with ease by employing a Contrastive Language-Image Pre-training (CLIP) model. Furthermore, we have exploited the music metadata to facilitate searches that may incorporate emotion. Event clustering is also improved in this version to increase user experience by reducing the occurrence of repeated images, and hence decreasing the search time.

Even with the appropriate acquisition of brain images, reliable and accurate brain tumor segmentation is a challenging task. Tumor grading and segmentation employing magnetic resonance imaging (MRI) are necessary for correct diagnosis and treatment planning. There are different MRI sequence images (T1, Flair, T1ce, T2, etc.) for identifying different parts of the tumor. Due to the diversity in the illumination of each brain imaging modality, different information and details can be obtained from each input modality. Therefore, by using various MRI modalities, the diagnosis system is capable of finding more unique details that lead to a better segmentation result, especially in fuzzy borders. In this study, to achieve an automatic and robust brain tumor segmentation framework using four MRI sequence images, an optimized convolutional neural network (CNN) is proposed. All weight and bias values of the CNN model are adjusted using an improved chimp optimization algorithm (IChOA). In the first step, we normalized all four input images to find some potential areas of the existing tumor. Next, we extract 17 features from each object inside the obtained binary image. Next, by employing the IChOA, the best features are selected. Finally, these obtained features are fed to the optimized CNN model to classify each object for brain tumor segmentation. The experimental outcomes conducted on the BRATS 2018 dataset demonstrate superior performance compared to the existing frameworks.

The Global Cancer Statistics 2020 reported breast cancer (BC) as the most common diagnosis of cancer type. Therefore, early detection of such type of cancer would reduce the risk of death from it. Breast imaging techniques are one of the most frequently used techniques to detect the position of cancerous cells or suspicious lesions. Computer-aided diagnosis (CAD) is a particular generation of computer systems that assist experts in detecting medical image abnormalities. In the last decades, CAD has applied deep learning (DL) and machine learning approaches to perform complex medical tasks in the computer vision area and improve the ability to make decisions for doctors and radiologists. The most popular and widely used technique of image processing in CAD systems is segmentation which consists of extracting the region of interest (ROI) through various techniques. This research provides a detailed description of the main categories of segmentation procedures which are classified into three classes: supervised, unsupervised, and DL. The main aim of this work is to provide an overview of each of these techniques and discuss their pros and cons. This will help researchers better understand these techniques and assist them in choosing the appropriate method for a given use case.

Metal additive manufacturing, which uses a layer-by-layer approach to fabricate parts, has many potential advantages over conventional techniques, including the ability to produced complex geometries, fast new design part production, personalised production, have lower cost and produce less material waste. While these advantages make AM an attractive option for industry, determining process parameters which result in specific properties, such as the level of porosity and tensile strength, can be a long and costly endeavour. In this review, the state-of-the-art in the control of part properties in AM is examined, including the effect of microstructure on part properties. The simulation of microstructure formation via numerical simulation and machine learning is examined which can provide process quality control and has the potential to aid in rapid process optimisation via closed loop control. In-situ monitoring of the AM process, is also discussed as a route to enable first time right production in the AM process, along with the hybrid approach of AM fabrication with post-processing steps such as shock peening, heat treatment and rolling. At the end of the paper, an outlook is presented with a view towards potential avenues for further research required in the field of metal AM., International Journal of Material Forming, 15 (3), ISSN:1960-6206, ISSN:1960-6214

In this paper, the relation between the FAIR (Findable, Accessible, Interoperable, Reusable) ontologies and accountability and transparency of ontology-based AI systems is analysed. Also, governance-related gaps in ontology quality evaluation metrics were identified by examining their relation with FAIR principles and FAcct (Fairness, Accountability, Transparency) governance aspects. A simple SKOS vocabulary, titled "Hospital Adverse Incidents Classification Scheme" (HAICS) has been used as a use case for this study. Theoretically, we found that there is a straight relation between FAIR principles and FAccT AI, which means that FAIR ontologies enhance transparency and accountability in ontology-based AI systems. We suggest that "FAIRness" should be assessed as one of the ontology quality evaluation aspects.

In this paper, we present the interactive lifelog retrieval engine developed for the LSC'21 comparative benchmarking challenge. The LifeSeeker 3.0 interactive lifelog retrieval engine is an enhanced version of our previous system participating in LSC'20 - LifeSeeker 2.0. The system is developed by both Dublin City University and the Ho Chi Minh City University of Science. The implementation of LifeSeeker 3.0 focuses on searching and filtering by text query using a weighted Bag-of-Words model with visual concept augmentation and three weighted vocabularies. The visual similarity search is improved using a bag of local convolutional features; while improving the previous version's performance, enhancing query processing time, result displaying, and browsing support.

Query auto-completion helps users to formulate their information needs by providing suggestion lists at every typed key. This task is commonly addressed by exploiting query logs and the approaches proposed in the literature fit well in web scale scenarios, where usually huge amounts of past user queries can be analyzed to provide reliable suggestions. However, when query logs are not available, e.g. in enterprise or desktop search engines, these methods are not applicable at all. To face these challenging scenarios, we present a novel corpus-based approach which exploits the textual content of an indexed document collection in order to dynamically generate query completions. Our method extracts informative text fragments from the corpus and it combines them using a probabilistic graphical model in order to capture the relationships between the extracted concepts. Using this approach, it is possible to automatically complete partial queries with significant suggestions related to the keywords already entered by the user without requiring the analysis of the past queries. We evaluate our system through a user study on two different real-world document collections. The experiments show that our method is able to provide meaningful completions outperforming the state-of-the art approach.

The Video Browser Showdown (VBS) is an annual competition in which each participant prepares an interactive video retrieval system and partakes in a live comparative evaluation at the annual MMM Conference. In this paper, we introduce Eolas, which is a prototype video/image retrieval system incorporating a novel virtual reality (VR) interface. For VBS’21, Eolas represented each keyframe of the collection by an embedded feature in a latent vector space, into which a query would also be projected to facilitate retrieval within a VR environment. A user could then explore the space and perform one of a number of filter operations to traverse the space and locate the correct result.

Faceted Search Systems (FSS) have gained prominence in many existing vertical search systems. They provide facets to assist users in allocating their desired search target quickly. In this paper, we present a framework to generate datasets appropriate for simulation-based evaluation of these systems. We focus on the task of personalized type-based facet ranking. Type-based facets (t-facets) represent the categories of the resources being searched in the FSS. They are usually organized in a large multilevel taxonomy. Personalized t-facet ranking methods aim at identifying and ranking the parts of the taxonomy which reflects query relevance as well as user interests. While evaluation protocols have been developed for facet ranking, the problem of personalising the facet rank based on user profiles has lagged behind due to the lack of appropriate datasets. To fill this gap, this paper introduces a framework to reuse and customise existing real-life data collections. The framework outlines the eligibility criteria and the data structure requirements needed for this task. It also details the process to transform the data into a ground-truth dataset. We apply this framework to two existing data collections in the domain of Point-of-Interest (POI) suggestion. The generated datasets are analysed with respect to the taxonomy richness (variety of types) and user profile diversity and length. In order to experiment with the generated datasets, we combine this framework with a widely adopted simulated user-facet interaction model to evaluate a number of existing personalized t-facet ranking baselines.

In Faceted Search Systems (FSS), users navigate the information space through facets, which are attributes or meta-data that describe the underlying content of the collection. Type-based facets (aka t-facets) help explore the categories associated with the searched objects in structured information space. This work investigates how personalizing t-facet ranking can minimize user effort to reach the intended search target. We propose a lightweight personalisation method based on Vector Space Model (VSM) for ranking the t-facet hierarchy in two steps. The first step scores each individual leaf-node t-facet by computing the similarity between the t-facet BERT embedding and the user profile vector. In this model, the user’s profile is expressed in a category space through vectors that capture the users’ past preferences. In the second step, this score is used to re-order and select the sub-tree to present to the user. The final ranked tree reflects the t-facet relevance both to the query and the user profile. Through the use of embeddings, the proposed method effectively handles unseen facets without adding extra processing to the FSS. The effectiveness of the proposed approach is measured by the user effort required to retrieve the sought item when using the ranked facets. The approach outperformed existing personalization baselines.

Faceted Search Systems (FSS) have become one of the main search interfaces used in vertical search systems, offering users meaningful facets to refine their search query and narrow down the results quickly to find the intended search target. This work focuses on the problem of ranking type-based facets. In a structured information space, type-based facets (t-facets) indicate the category to which each object belongs. When they belong to a large multi-level taxonomy, it is desirable to rank them separately before ranking other facet groups. This helps the searcher in filtering the results according to their type first. This also makes it easier to rank the rest of the facets once the type of the intended search target is selected. Existing research employs the same ranking methods for different facet groups. In this research, we propose a two-step approach to personalize t-facet ranking. The first step assigns a relevance score to each individual leaf-node t-facet. The score is generated using probabilistic models and it reflects t-facet relevance to the query and the user profile. In the second step, this score is used to re-order and select the sub-tree to present to the user. We investigate the usefulness of the proposed method to a Point Of Interest (POI) suggestion task. Our evaluation aims at capturing the user effort required to fulfil her search needs by using the ranked facets. The proposed approach achieved better results than other existing personalized baselines., Comment: Accepted at ICWE 2021

This paper describes the first edition of the “Diachronic Lexical Seman-tics” (DIACR-Ita) task at the EVALITA2020 campaign. The task challenges participants to develop systems that can automatically detect if a given word has changed its meaning over time, given con-textual information from corpora.The task, at its first edition, attracted 9 participant teams and collected a total of 36 sub-mission runs

In this paper, we describe the creation of a diachronic corpus for Italian by exploiting the digital archive of the newspaper “L’Unit`a”. We automatically clean and annotate the corpus with PoStags, lemmas, named entities and syntactic dependencies. Moreover, we compute frequency-based time series for tokens, lemmas and entities. We show some interesting corpus statistics taking into account the temporal dimension and describe some examples of usage of time series.

This paper describes the system proposed by the Random team for SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detection. We focus our approach on the detection problem. Given the semantics of words captured by temporal word embeddings in different time periods, we investigate the use of unsupervised methods to detect when the target word has gained or lost senses. To this end, we define a new algorithm based on Gaussian Mixture Models to cluster the target similarities computed over the two periods. We compare the proposed approach with a number of similarity-based thresholds. We found that, although the performance of the detection methods varies across the word embedding algorithms, the combination of Gaussian Mixture with Temporal Referencing resulted in our best system.

In the last few years, the increasing availability of large corpora spanning several time periods has opened new opportunities for the diachronic analysis of language. This type of analysis can bring to the light not only linguistic phenomena related to the shift of word meanings over time, but it can also be used to study the impact that societal and cultural trends have on this language change. This paper introduces a new resource for performing the diachronic analysis of named entities built upon Wikipedia page revisions. This resource enables the analysis over time of changes in the relations between entities (concepts), surface forms (words), and the contexts surrounding entities and surface forms, by analysing the whole history of Wikipedia internal links. We provide some useful use cases that prove the impact of this resource on diachronic studies and delineate some possible future usage. Source code and more details are available here: https://github.com/pippokill/dae

The challenge of providing personalized and contextually appropriate recommendations to a user is faced in a range of use-cases, e.g., recommendations for movies, places to visit, articles to read etc. In this paper, we focus on one such application, namely that of suggesting 'points of interest' (POIs) to a user given her current location, by leveraging relevant information from her past preferences. An automated contextual recommendation algorithm is likely to work well if it can extract information from the preference history of a user (exploitation) and effectively combine it with information from the user's current context (exploration) to predict an item's 'usefulness' in the new context. To balance this trade-off between exploration and exploitation, we propose a generic unsupervised framework involving a factored relevance model (FRLM), comprising two distinct components, one corresponding to the historical information from past contexts, and the other pertaining to the information from the local context. Our experiments are conducted on the TREC contextual suggestion (TREC-CS) 2016 dataset. The results of our experiments demonstrate the effectiveness of our proposed approach in comparison to a number of standard IR and recommender-based baselines.

In this paper, we propose the Cold-start Resistant and Extensible Recommender (CoRE), a novel recommender system that was developed as part of collaborative research with Ryanair, the world's most visited airline website. CoRE is an algorithmic approach to the recommendation of hotel rooms that can function in extreme cold-start situations. It is a hybrid recommender that blends elements of naive collaborative filtering, content-based recommendation and contextual suggestion to address the various shortcomings which exist in the underlying user and product data. We evaluated the performance of CoRE in a number of scenarios in order to assess different aspects of the algorithm: personalization, multi-model and the resistance to the extreme cold-start situations. Experimental results on an authentic, real-world dataset show that CoRE effectively overcomes the different problems associated with the underlying data in these scenarios.

Linking entity mentions in Italian tweets to concepts in a knowledge base is a challenging task, due to the short and noisy nature of these short messages and the lack of specific resources for Italian. This paper proposes an adaptation of a general purpose Named Entity Linking algorithm, which exploits the similarity measure computed over a Distributional Semantic Model, in the context of Italian tweets. In order to evaluate the proposed algorithm, we introduce a new dataset of tweets for entity linking that we have developed specifically for the Italian language.

During the last decade the surge in available data spanning different epochs has inspired a new analysis of cultural, social, and linguistic phenomena from a temporal perspective. This paper describes a method that enables the analysis of the time evolution of the meaning of a word. We propose Temporal Random Indexing (TRI), a method for building WordSpaces that takes into account temporal information. We exploit this methodology in order to build geometrical spaces of word meanings that consider several periods of time. The TRI framework provides all the necessary tools to build WordSpaces over different time periods and perform such temporal linguistic analysis. We propose some examples of usage of our tool by analysing word meanings in two corpora: a collection of Italian books and English scientific papers about computational linguistics. This analysis enables the detection of linguistic events that emerge in specific time intervals and that can be related to social or cultural phenomena.

In this chapter we propose an innovative information retrieval system able to manage temporal information. The system allows temporal constraints in a classical keyword-based search. Information about temporal events is automatically extracted from text at indexing time and stored in an ad-hoc data structure exploited by the retrieval module for searching relevant documents. Our system can search textual information that refers to specific period of times. We perform an exploratory case study indexing all Italian Wikipedia articles.

The retrieval of pertaining information during the decision-making process requires more than the traditional concept of relevance to be fulfilled. This task asks for opinionated sources of information able to influence the user’s point of view about an entity or target. We propose SABRE, a Sentiment Aspect-Based Retrieval Engine, able to tackle this process through the retrieval of opinions about an entity at two different levels of granularity that we called aspect and sub-aspect. Such fine-grained opinion retrieval enables both an aspect-based sentiment classification of text fragments, and an aspect-based filtering during the navigational exploration of the retrieved documents. A preliminary evaluation on a manually created dataset shows the ability of the proposed method at better identify \(\langle \textit{aspect}, \textit{sub}\)-\(\textit{aspect}\rangle \) with respect to a term frequency baseline.

The growth of the Web is the most influential factor that contributes to the increasing importance of text retrieval and filtering systems. On one hand, the Web is becoming more and more multilingual, and on the other hand users themselves are becoming increasingly polyglot. In this context, platforms for intelligent information access as search engines or recommender systems need to evolve to deal with this increasing amount of multilingual information. This paper proposes a content-based recommender system able to generate cross-lingual recommendations. The idea is to exploit user preferences learned in a given language, to suggest item in another language. The main intuition behind the work is that, differently from keywords which are inherently language dependent, concepts are stable across different languages, allowing to deal with multilingual and cross-lingual scenarios. We propose four knowledge-based strategies to build concept-based representation of items, by relying on the knowledge contained in two knowledge sources, i.e. Wikipedia and BabelNet. We learn user profiles by leveraging the different concept-based representations, in order to define a cross-lingual recommendation process. The empirical evaluation carried out on two state of the art datasets, DBbook and Movielens, shows that concept-based approaches are suitable to provide cross-lingual recommendations, even though there is not a clear advantage of using one of the different proposed representations. However, it emerges that most of the times the approaches based on BabelNet outperform those based on Wikipedia, which clearly shows the advantage of using a native multilingual knowledge source.

This paper describes the effect of introducing embedding-based features in a learning to rank approach to entity relatedness. We define several features that exploit word- and link-embedding approaches by relying on both links and the content that appear in Wikipedia articles. These features are combined with other state-of-the-art relatedness measures by using a learning to rank framework. In the evaluation, we report the performance of each feature individually. Moreover, we investigate the contribution of each feature to the ranking function by analysing the output of a feature selection algorithm. The results of this analysis prove that features based on word and link embeddings are able to increase the performance of the learning to rank algorithm.

Named Entity Linking (NEL) is the task of semantically annotating entity mentions in a portion of text with links to a knowledge base. The automatic annotation, which requires the recognition and disambiguation of the entity mention, usually exploits contextual clues like the context of usage and the coherence with respect to other entities. In Twitter, the limits of 140 characters originates very short and noisy text messages that pose new challenges to the entity linking task. We propose an overview of NEL methods focusing on approaches specifically developed to deal with short messages, like tweets. NEL is a fundamental task for the extraction and annotation of concepts in tweets, which is necessary for making the Twitter’s huge amount of interconnected user-generated contents machine readable and enable the intelligent information access.

This paper introduces a semantic and personalised information retrieval (SEPIR) tool for the public administration of Apulia Region. SEPIR, through semantic search and visualisation tools, enables the analysis of a large amount of unstructured data and the intelligent access to information. At the core of these functionalities is an NLP pipeline responsible for the WordSpace building and the key-phrase extraction. The WordSpace is the key component of the semantic search and personalisation algorithm. Moreover, key-phrases enrich the document representation of the retrieval system and are on the basis of the bubble charts, which provide a quick overview of the main concepts involved in a document collection. We show some of the key features of SEPIR in a use case where the personalisation technique re-ranks the set of relevant documents on the basis of the user's past queries and the visualisation tools provide the users with useful information about the analysed collection.

Super-sense tagging is the task of annotating each word in a text with a super-sense, i.e. a general concept such as animal, food or person, coming from the general semantic taxonomy defined by the WordNet lexicographer classes. Due to the small set of involved concepts, the task is simpler than Word Sense Disambiguation, which identifies a specific meaning for each word. The small set of concepts allows machine learning algorithms to achieve good performance when coping with the problem of tagging. However, machine learning algorithms suffer from data-sparseness. This problem becomes more evident when lexical features are involved, because test data can contain words with low frequency (or completely absent) in training data. To overcome the sparseness problem, this paper proposes a supervised method for super-sense tagging which incorporates information coming from a distributional space of words built on a large corpus. Results obtained on two standard datasets, SemCor and SensEval-3, show the effectiveness of our approach.

This paper investigates the role of Distributional Semantic Models (DSMs) in Question Answering (QA), and specifically in a QA system called Question Cube. Question Cube is a framework for QA that combines several techniques to retrieve passages containing the exact answers for natural language questions. It exploits Information Retrieval models to seek candidate answers and Natural Language Processing algorithms for the analysis of questions and candidate answers both in English and Italian. The data source for the answer is an unstructured text document collection stored in search indices. In this paper we propose to exploit DSMs in the Question Cube framework. In DSMs words are represented as mathematical points in a geometric space, also known as semantic space. Words are similar if they are close in that space. Our idea is that DSMs approaches can help to compute relatedness between users' questions and candidate answers by exploiting paradigmatic relations between words. Results of an experimental evaluation carried out on CLEF2010 QA dataset, prove the effectiveness of the proposed approach.

This paper proposes two approaches to compositional semantics in distributional semantic spaces. Both approaches conceive the semantics of complex structures, such as phrases or sentences, as being other than the sum of its terms. Syntax is the plus used as a glue to compose words. The former kind of approach encodes information about syntactic dependencies directly into distributional spaces, the latter exploits compositional operators reflecting the syntactic role of words. We present a preliminary evaluation performed on GEMS 2011 "Compositional Semantics" dataset, with the aim of understanding the effects of these approaches when applied to simple word pairs of the kind Noun-Noun, Adjective-Noun and Verb-Noun. Experimental results corroborate our conjecture that exploiting syntax can lead to improved distributional models and compositional operators, and suggest new openings for future uses in real-application scenario.

Information about top-ranked documents plays a key role to improve retrieval performance. One of the most common strategies which exploits this kind of information is relevance feedback. Few works have investigated the role of negative feedback on retrieval performance. This is probably due to the difficulty of dealing with the concept of nonrelevant document. This paper proposes a novel approach to document re-ranking, which relies on the concept of negative feedback represented by non-relevant documents. In our model the concept of non-relevance is defined as a quantum operator in both the classical Vector Space Model and a Semantic Document Space. The latter is induced from the original document space using a distributional approach based on Random Indexing. The evaluation carried out on a standard document collection shows the effectiveness of the proposed approach and opens new perspectives to address the problem of quantifying the concept of non-relevance.

A number of works have shown that the aggregation of several Information Retrieval (IR) systems works better than each system working individually. Nevertheless, early investigation in the context of CLEF Robust-WSD task, in which semantics is involved, showed that aggregation strategies achieve only slight improvements. This paper proposes a re-ranking approach which relies on inter-document similarities. The novelty of our idea is twofold: the output of a semantic based IR system is exploited to re-weigh documents and a new strategy based on Semantic Vectors is used to compute inter-document similarities.

This paper presents the participation of the semantic Nlevels search engine SENSE at the CLEF 2009 Ad Hoc Robust-WSD Task. Our aim is to demonstrate that the combination of the N-levels model and WSD can improve the retrieval performance even when an effective retrieval model is adopted. To reach this aim, we worked on two different strategies. On one hand a model, based on Okapi BM25, was adopted at each level. On the other hand, we integrated a local relevance feedback technique, called Local Context Analysis, in both indexing levels of the system (keyword and word meaning). The hypothesis that Local Context Analysis can be effective even when it works on word meanings coming from a WSD algorithm is supported by experimental results. In monolingual task MAP increased of about 2% exploiting disambiguation, while GMAP increased from 4% to 9% when we used WSD in both mono- and bi- lingual tasks.

This paper proposes an Information Retrieval (IR) system that integrates sense discrimination to overcome the problem of word ambiguity. Word ambiguity is a key problem for systems that have access to textual information. Semantic Vectors are able to divide the usages of a word into different meanings, by discriminating among word meanings on the ground of information available in unannotated corpora. This paper has a twofold goal: the former is to evaluate the effectiveness of an IR system based on Semantic Vectors, the latter is to describe how they have been integrated in a semantic IR framework to build semantic spaces of words and documents. To achieve the first goal, we performed an in vivo evaluation in an IR scenario and we compared the method based on sense discrimination to a method based on Word Sense Disambiguation (WSD). Contrarily to sense discrimination, which aims to discriminate among different meanings not necessarily known a priori, WSD is the task of selecting a sense for a word from a set of predefined possibilities. To accomplish the second goal, we integrated Semantic Vectors in a semantic search engine called SENSE (SEmantic N-levels Search Engine).

Traditional Information Retrieval (IR) systems are based on bag-of-words representation. This approach retrieves relevant documents by lexical matching between query and document terms. Due to synonymy and polysemy, lexical methods produce imprecise or incomplete results. In this paper we present SENSE (SEmantic N-levels Search Engine), an IR system that tries to overcome the limitations of the ranked keyword approach, by introducing semantic levels which integrate (and not simply replace) the lexical level represented by keywords. Semantic levels provide information about word meanings, as described in a reference dictionary, and named entities. This paper focuses on the named entity level. Our aim is to prove that named entities are useful to improve retrieval performance. We exploit a model able to capture entity relationships, although they are not explicit in documents text. Experiments on CLEF dataset prove the effectiveness of our hypothesis.

Polysemous words have more than one possible meaning, thus word ambiguity is a key issue for the systems which access textual information. Computational linguistics proposes two main methods to cope with word ambiguity: sense disambiguation and sense discrimination. (Word) Sense Disambiguation is the task of selecting a sense for a word from a set of predefined possibilities, while (Word) Sense Discrimination is the task of dividing the usages of a word into different meanings, discriminating among word meanings based on information found in unannotated corpora. This paper proposes a strategy to compare disambiguation and discrimination systems by adopting an "in vivo" evaluation in an Information Retrieval scenario. The goal of the evaluation is to establish how disambiguation and discrimination bias the retrieval performance.

This paper presents the results of the experiments conducted at the University of Bari for the Ad Hoc Robust-WSD track of the Cross-Language Evaluation Forum (CLEF) 2008. The evaluation was performed using SENSE (SEmantic N-levels Search Engine), a semantic search engine that tries to overcome the limitations of the ranked keyword approach by introducing semantic levels, which integrate (and not simply replace) the lexical level represented by keywords. We show how SENSE is able to manage documents indexed at two separate levels, keyword and word meaning, in an attempt of improving the retrieval performance. Two types of experiments have been performed by exploiting both only one indexing level and all indexing levels at the same time. The experiments performed combining keywords and word meanings, extracted from the WordNet lexical database, show the promise of the idea and point out the value of our institution. In particular the results confirm our hypothesis: The combination of two indexing levels outperforms a single level. Indeed, an improvement of 35% in precision has been obtained by adopting the N-levels model with respect to the results obtained by exploiting the indexing level based only on keywords.

In this paper, we propose several methods for the diachronic analysis of the Italian language. We build several models by exploiting Temporal Random Indexing and the Google Ngram dataset for the Italian language. Each proposed method is evaluated on the ability to automatically identify meaning shift over time. To this end, we introduce a new dataset built by looking at the etymological information reported in some dictionaries. In questo lavoro proponiamo alcuni metodi per l’analisi diacronica della lingua italiana. Abbiamo costruito differenti modelli utilizzando la tecnica del Temporal Random Indexing e Google Ngram per l’italiano. Ciascun metodo proposto è stato valutato rispetto alla capacità di identificare automaticamente i cambi di significato nel tempo. A tale scopo introduciamo uno nuovo dataset costruito mediante le informazioni etimologiche presenti in alcuni dizionari.

This paper describes the UNIBA team participation in the Cross-Level Semantic Similarity task at SemEval 2014. We propose to combine the output of different semantic similarity measures which exploit Word Sense Disambiguation and Distributional Semantic Models, among other lexical features. The integration of similarity measures is performed by means of two supervised methods based on Gaussian Process and Support Vector Machine. Our systems obtained very encouraging results, with the best one ranked 6 th out of 38 submitted systems.