Search

The maintenance of wordnets and lexical knwoledge bases typically relies on time-consuming manual effort. In order to minimise this issue, we propose the exploitation of models of distributional semantics, namely word embeddings learned from corpora, in the automatic identification of relation instances missing in a wordnet. Analogy-solving methods are first used for learning a set of relations from analogy tests focused on each relation. Despite their low accuracy, we noted that a portion of the top-given answers are good suggestions of relation instances that could be included in the wordnet. This procedure is applied to the enrichment of OpenWordNet-PT, a public Portuguese wordnet. Relations are learned from data acquired from this resource, and illustrative examples are provided. Results are promising for accelerating the identification of missing relation instances, as we estimate that about 17% of the potential suggestions are good, a proportion that almost doubles if some are automatically invalidated., OASIcs, Vol. 93, 3rd Conference on Language, Data and Knowledge (LDK 2021), pages 21:1-21:13

In this paper we present a method for enlarging wordnets focusing on multi-word terms and utilising data from parallel corpora. Our approach is validated using the Galician and Portuguese wordnets. The multi-word candidates obtained in this experiment were manually validated, obtaining a 73.2% accuracy for the Galician language and a 75.5% for the Portuguese language. Presentamos un método para la ampliación de wordnets en el ámbito de las unidades pluriverbales, usando datos de corpus paralelos y aplicando el método a la expansión de los wordnets del gallego y del portugués. Las unidades pluriverbales que se obtienen en este experimento se validaron manualmente, obteniendo una precisión del 73.2% para el gallego y del 75.5% para el portugués. This research has been carried out thanks to the project DeepReading (RTI2018-096846-B-C21) supported by the Ministry of Science, Innovation and Universities of the Spanish Government and the European Fund for Regional Development (MCIU/AEI/FEDER), and was partially funded by Portuguese National funds (PIDDAC), through the FCT – Fundação para a Ciência e Tecnologia and FCT/MCTES under the scope of the project UIDB/05549/2020.

Овај докторски рад бави се истраживањем најбољег начина да се унапреде језички ресурси и алати за обраду српског језика, са нагласком на обради фигуративног језика, то јест језика који је богат реторичким фигурама. У раду су представљени језички ресурси и алати за обраду српског језика, нарочито Ворднет и Српски ворднет, чија доградња је централни део овог истраживања. Та доградња је спроведена путем модела такозване групне расподеле рада, како смо за потребе израде овог рада превели енглески термин crowdsourcing... The research presented in this doctoral thesis deals with finding the best way to enhance lexical resources and tools for natural language processing of Serbian language, with a focus on processing of figurative language, i.e. language in which plenty of rhetorical figures are used. The thesis presents lexical resources and tools for natural language processing of Serbian language, especially WordNet and Serbian wordnet, whose enhancment and building via the crowdsourcing model are the central part of the presented research results...

Word Sense Disambiguation Based on Large Scale Polish CLARIN Heterogeneous Lexical ResourcesLexical resources can be applied in many different Natural Language Engineering tasks, but the most fundamental task is the recognition of word senses used in text contexts. The problem is difficult, not yet fully solved and different lexical resources provided varied support for it. Polish CLARIN lexical semantic resources are based on the plWordNet — a very large wordnet for Polish — as a central structure which is a basis for linking together several resources of different types. In this paper, several Word Sense Disambiguation (henceforth WSD) methods developed for Polish that utilise plWordNet are discussed. Textual sense descriptions in the traditional lexicon can be compared with text contexts using Lesk’s algorithm in order to find best matching senses. In the case of a wordnet, lexico-semantic relations provide the main description of word senses. Thus, first, we adapted and applied to Polish a WSD method based on the Page Rank. According to it, text words are mapped on their senses in the plWordNet graph and Page Rank algorithm is run to find senses with the highest scores. The method presents results lower but comparable to those reported for English. The error analysis showed that the main problems are: fine grained sense distinctions in plWordNet and limited number of connections between words of different parts of speech. In the second approach plWordNet expanded with the mapping onto the SUMO ontology concepts was used. Two scenarios for WSD were investigated: two step disambiguation and disambiguation based on combined networks of plWordNet and SUMO. In the former scenario, words are first assigned SUMO concepts and next plWordNet senses are disambiguated. In latter, plWordNet and SUMO are combined in one large network used next for the disambiguation of senses. The additional knowledge sources used in WSD improved the performance. The obtained results and potential further lines of developments were discussed.

Lexical platform – the first step towards user-centred integration of lexical resourcesLexical platform – the first step towards user-centred integration of lexical resources The paper describes the Lexical Platform - a means for lightweight integration of independent lexical resources. Lexical resources (LRs) are represented as web components that implement a minimal set of predefined programming interfaces. These provide functionality for querying and generate a simple, common presentation format. Therefore, a common data format is not needed and the identity of component LRs is preserved. Users can search, browse and navigate via resources on the basis of a limited set of anchor elements such as base form, word form and synset id. Platforma leksykalna – pierwszy krok w kierunku integracji zasobów leksykalnych zorientowanej na użytkownikówArtykuł opisuje Platformę Leksykalną – sposób na lekką integrację niezależnych zasobów leksykalnych. Zasoby leksykalne są na niej reprezentowane jako komponenty webowe, które implementują minimalny zestaw predefiniowanych interfejsów programistycznych. Interfejsy te dostarczają funkcjonalność do przeszukiwania oraz generują prosty, jednolity format prezentacji zasobów. W związku z tym wspólny format danych nie jest konieczny i tożsamość składowych zasobów leksykalnych jest zachowana. Użytkownicy mogą przeszukiwać zasoby na podstawie ograniczonego zbioru odwołań takich jak forma podstawowa, forma wyrazowa i identyfikator synsetu.

This article investigates one kind of cross-part-of-speech relation for English, Czech and Zulu lexical resources in the form of semantic networks (wordnets). Many languages have rules whereby new words are derived regularly and productively from existing words via morphological processes. The morphologically unmarked base words and the derived words, which share a semantic core with the base words, can be interlinked and integrated into wordnets, where they typically form “derivational nests”, or subnets. Efforts are described to capture the morphological and semantic regularities of derivational processes in English, Czech and Zulu to compare the linguistic mechanisms and to exploit them for suitable computational processing and wordnet construction. While some work has been done for English and Czech already, wordnets for Zulu and other Bantu languages are still in their infancy. This article illustrates how Zulu can benefit from existing work.

Thesauri and similarly organised resources attract increasing interest of Natural Language Processing researchers. Thesauri age fast, so there is a constant need to update their vocabulary. Since a manual update cycle takes considerable time, automated methods are required. This work presents a tuneable method of measuring semantic relatedness, trained on Roget’s Thesaurus, which generates lists of terms related to words not yet in the Thesaurus. Using these lists of terms, we experiment with three methods of adding words to the Thesaurus. We add, with high confidence, over 5500 and 9600 new words and word senses to versions of Roget’s Thesaurus from 1911 and 1987 respectively. We evaluate our work both manually, and by applying the updated thesauri in three NLP tasks: selection of the best synonym from a set of candidates, pseudo-word-sense disambiguation, and SAT-style analogy problems. We find that the newly added words are of high quality. The additions significantly improve the performance of Roget’s-based methods in these NLP tasks. It compares favourably to the performance of WordNet-based methods. Our methods are general enough to work with different versions of Roget’s Thesaurus.

Este artículo ofrece una revisión de métodos para la construcción de WordNets siguiendo la estrategia de expansión, es decir, mediante la traducción de las variantes inglesas del Princeton WordNet. En el proceso de construcción se han utilizado recursos libres disponibles en Internet. El artículo presenta también los resultados de la evaluación de las técnicas en la construcción de los WordNets 3.0 para el castellano y catalán. Estas técnicas se pueden utilizar para la construcción de WordNets para otras lenguas. This paper presents a review of methods for building WordNets following the expand model, that is, by translating the English variants of the Princeton WordNet. Only free resources available online have been used. The paper also presents the evaluation of the techniques applied in the construction of Spanish and Catalan WordNets 3.0. These techniques can be also used for other languages. Este trabajo se ha llevado a cabo dentro del proyecto Know2 Language understanding technologies for multilingual domain-oriented information access (MICINN, TINN2009-14715-C04-04).

Este artículo ofrece una revisión de métodos para la construcción de WordNets siguiendo la estrategia de expansión, es decir, mediante la traducción de las variants inglesas del Princeton WordNet. En el proceso de construcción se han utilizado recursos libres disponibles en Internet. El artículo presenta también los resultados de la evaluación de las técnicas en la construcción de los WordNets 3.0 para el castellano y catalán. Estas técnicas se pueden utilizar para la construcción de WordNets para otras lenguas. This paper presents a review of methods for building WordNets following the expand model, that is, by translating the English variants of the Princeton WordNet. Only free resources available online have been used. The paper also presents the evaluation of the techniques applied in the construction of Spanish and Catalan WordNets 3.0. These techniques can be also used for other languages. Aquest article ofereix una revisió de mètodes per a la construcció de WordNets seguint l'estratègia d'expansió, és a dir, mitjançant la traducció de les variants angleses del Princeton WordNet. En el procés de construcció s'han utilitzat recursos lliures disponibles en Internet. L'article presenta també els resultats de l'avaluació de les tècniques en la construcció dels WordNets 3.0 per al castellà i català. Aquestes tècniques es poden utilitzar per la construcció de WordNets per a altres llengües.

In this paper we present a methodology for WordNet construction based on the exploitation of parallel corpora with semantic annotation of the English source text. We are using this methodology for the enlargement of the Spanish and Catalan versions of WordNet 3.0, but the methodology can also be used for other languages. As big parallel corpora with semantic annotation are not usually available, we explore two strategies to overcome this problem: to use monolingual sense tagged corpora and machine translation, on the one hand; and to use parallel corpora and automatic sense tagging on the source text, on the other. With these resources, the problem of acquiring a WordNet from parallel corpora can be seen as a word alignment task. Fortunately, this task is well known, and some aligning algorithms are freely available.

Este artículo ofrece una revisión de métodos para la construcción de WordNets siguiendo la estrategia de expansión, es decir, mediante la traducción de las variantes inglesas del Princeton WordNet. En el proceso de construcción se han utilizado recursos libres disponibles en Internet. El artículo presenta también los resultados de la evaluación de las técnicas en la construcción de los WordNets 3.0 para el castellano y catalán. Estas técnicas se pueden utilizar para la construcción de WordNets para otras lenguas. This paper presents a review of methods for building WordNets following the expand model, that is, by translating the English variants of the Princeton WordNet. Only free resources available online have been used. The paper also presents the evaluation of the techniques applied in the construction of Spanish and Catalan WordNets 3.0. These techniques can be also used for other languages. Este trabajo se ha llevado a cabo dentro del proyecto Know2 Language understanding technologies for multilingual domain-oriented information access (MICINN, TINN2009-14715-C04-04).

In this work we present SENTIWORDNET 3.0, a lexical resource explicitly devised for supporting sentiment classification and opinion mining applications. SENTIWORDNET 3.0 is an improved version of SENTIWORDNET 1.0, a lexical resource publicly available for research purposes, now currently licensed to more than 300 research groups and used in a variety of research projects worldwide. Both SENTIWORDNET 1.0 and 3.0 are the result of automatically annotating all WORDNET synsets according to their degrees of positivity, negativity, and neutrality. SENTIWORDNET 1.0 and 3.0 differ (a) in the versions of WORDNET which they annotate (WORDNET 2.0 and 3.0, respectively), (b) in the algorithm used for automatically annotating WORDNET, which now includes (additionally to the previous semi-supervised learning step) a random-walk step for refining the scores. We here discuss SENTIWORDNET 3.0, especially focussing on the improvements concerning aspect (b) that it embodies with respect to version 1.0. We also report the results of evaluating SENTIWORDNET 3.0 against a fragment of WORDNET 3.0 manually annotated for positivity, negativity, and neutrality; these results indicate accuracy improvements of about 20% with respect to SENTIWORDNET 1.0.

The Universal Networking Language (UNL) is an interlingua designed to be the base of several natural language processing systems aiming to support multilinguality in internet. One of the main components of the language is the dictionary of Universal Words (UWs), which links the vocabularies of the different languages involved in the project. As any NLP system, coverage and accuracy in its lexical resources are crucial for the development of the system. In this paper, the authors describes how a large coverage UWs dictionary was automatically created, based on an existent and well known resource like the English WordNet. Other aspects like implementation details and the evaluation of the final UW set are also depicted.

Opinion mining is a recent discipline at the crossroads of Information Retrieval and of Computational Linguistics which is concerned not with the topic a document is about, but with the opinion it expresses. It has a rich set of applications, ranging from tracking users' opinions about products or about political candidates as expressed in online forums, to customer relationship management. Functional to the extraction of opinions from text is the determination of the relevant entities of the language that are used to express opinions, and their opinion-related properties. For example, determining that the term beautiful casts a positive connotation to its subject. In this thesis we investigate on the automatic recognition of opinion-related properties of terms. This results into building opinion-related lexical resources, which can be used into opinion mining applications. We start from the (relatively) simple problem of determining the orientation of subjective terms. We propose an original semi-supervised term classification model that is based on the quantitative analysis of the glosses of such terms, i.e. the definitions that these terms are given in on-line dictionaries. This method outperforms all known methods when tested on the recognized standard benchmarks for this task. We show how our method is capable to produce good results on more complex tasks, such as discriminating subjective terms (e.g., good) from objective ones (e.g., green), or classifying terms on a fine-grained attitude taxonomy. We then propose a relevant refinement of the task, i.e., distinguishing the opinion-related properties of distinct term senses. We present SentiWordNet, a novel high-quality, high-coverage lexical resource, where each one of the 115,424 senses contained in WordNet has been automatically evaluated on the three dimensions of positivity, negativity, and objectivity. We propose also an original and effective use of random-walk models to rank term senses by their positivity or negativity. The random-walk algorithms we present have a great application potential also outside the opinion mining area, for example in word sense disambiguation tasks. A result of this experience is the generation of an improved version of SentiWordNet. We finally evaluate and compare the various versions of SentiWordNet we present here with other opinion-related lexical resources well-known in literature, experimenting their use in an Opinion Extraction application. We show that the use of SentiWordNet produces a significant improvement with respect to the baseline system, not using any specialized lexical resource, and also with respect to the use of other opinion-related lexical resources

Many works in sentiment analysis have focused on the problem of subjectivity detection, at various levels: from terms (or term senses), as in the automatic annotation of lexical resources, to fragments of text, as in opinion extraction, to entire documents, as in sentiment classification. At all these levels, the two dimensions that have been investigated more actively are polarity ("positive/negative") and force ("strong/mild/weak" expression of positivity or negativity). In the SentiWordNet project we made a first attempt at automatically adding information concerning these two dimensions to WordNet. In another, more recent research we have explored a further dimension of subjective language, i.e, attitude type, which distinguishes, for example, between moral appreciation ("honest") and aesthetic appreciation ("beautiful"). We think that endowing WordNet with annotations pertaining to these three dimensions (polarity + force + attitude type) would make WordNet an even more invaluable resource for sentiment analysis. Adding this information to WordNet would not be an easy task, for at least two reasons. One is the sheer size of the resource; this might call, at least initially, for a semi-automatic approach, on the line of the SentiWordnet or of the "WordNet Evocation" projects. The other is the choice of the taxonomy of sentiment types, which needs to compromise between conceptual subtlety and real-world applicability. For our recent work on attitude type we have adopted a taxonomy of attitude types originally defined in Martin and White's Appraisal Theory; however, other potentially interesting alternatives have been developed, e.g. in the EU-funded Simple project. However, we conjecture that even this three-dimensional specification of the sentiment-related properties of synsets might not be sufficient for application purposes, at least for some parts of speech. For example, it is conceivable that a verb's polarity should not be characterized as positive or negative tout court, but that a distinction should be made as to which semantic role of the verb such polarity is bestowed upon. For instance, the verbs "torture" and "discard" both have a negative slant; however, while "torture" casts a negative character on the subject of the action (and on the action itself), "discard" typically casts a negative character on the direct object of the action. Such distinctions should be accounted for in a lexicon, especially in order to make it useful for opinion extraction applications.

In this paper we describe WS4LR, the workstation for lexical resources, a software tool developed within the Human Language Technology Group at the Faculty of Mathematics, University of Belgrade. The tool is aimed at manipulating heterogeneous lexical resources, and the need for such a tool came from the large volume of resources the Group has developed in the course of many years and within different projects. The tool handles morphological dictionaries, wordnets, aligned texts and transducers equally and has already proved very useful for various tasks. Although it has so far been used mainly for Serbian, WS4LR is not language dependent and can be successfully used for resources in other languages provided that they follow the described formats and methodologies. The tool operates on the .NET platform and runs on a personal computer under Windows 2000/XP/2003 operating system with at least 256MB of internal memory. М30 М33

In this paper we present Wordnet-LMF, a dialect of ISO Lexical Markup Framework that instantiates LMF for representing wordnets. Wordnet-LMF was developed in the framework of the EU KYOTO project for the specific purpose of endowing a set of wordnets with a standardized interoperability format allowing the interchange of lexico-semantic information encoded in each of them. The aim of this format is twofold a) to give a preliminary assessment of LMF, by large-scale application to real lexical resources; b) to endow WordNet with a format representation that will allow easier integration among resources sharing the same structure (i.e other wordnets) and, more importantly, across resources with different theoretical and implementation approaches.

The paper presents an idea of Lexical Platform proposed as a means for a lightweight integration of various lexical resources into one complex (from the perspective of non-technical users). All LRs will be represented as software web components implementing a minimal set of predefined programming interfaces providing functionality for querying and generating simple common presentation format. A common data format for the resources will not be required. Users will be able to search, browse and navigate via resources on the basis of anchor elements of a limited set of types. Lexical resources linked to the platform via components will preserve their identity. Accepted version

Despite its original intended use, which was very different, WORDNET is used more and more today as an ontology, where the hyponym relation between word senses is interpreted as a subsumption relation between concepts. In this article, we discuss the general problems related to the semantic interpretation of WORDNET taxonomy in light of rigorous ontological principles inspired by the philosophical tradition. Then we introduce the DOLCE upper-level ontology, which is inspired by such principles but with a clear orientation toward language and cognition. We report the results of an experimental effort to align WORDNET's upper level with DOLCE. We suggest that such alignment could lead to an "ontologically sweetened" WORDNET, meant to be conceptually more rigorous, cognitively transparent, and efficiently exploitable in several applications.