An investigation into feature construction to assist word sense disambiguation

Identifying the correct sense of a word in context is crucial for many tasks in natural language processing (machine translation is an example). State-of-the art methods for Word Sense Disambiguation (WSD) build models using hand-crafted features that usually capturing shallow linguistic information. Complex background knowledge, such as semantic relationships, are typically either not used, or used in specialised manner, due to the limitations of the feature-based modelling techniques used. On the other hand, empirical results from the use of Inductive Logic Programming (ILP) systems have repeatedly shown that they can use diverse sources of background knowledge when constructing models. In this paper, we investigate whether this ability of ILP systems could be used to improve the predictive accuracy of models for WSD. Specifically, we examine the use of a general-purpose ILP system as a method to construct a set of features using semantic, syntactic and lexical information. This feature-set is then used by a common modelling technique in the field (a support vector machine) to construct a classifier for predicting the sense of a word. In our investigation we examine one-shot and incremental approaches to feature-set construction applied to monolingual and bilingual WSD tasks. The monolingual tasks use 32 verbs and 85 verbs and nouns (in English) from the SENSEVAL-3 and SemEval-2007 benchmarks; while the bilingual WSD task consists of 7 highly ambiguous verbs in translating from English to Portuguese. The results are encouraging: the ILP-assisted models show substantial improvements over those that simply use shallow features. In addition, incremental feature-set construction appears to identify smaller and better sets of features. Taken together, the results suggest that the use of ILP with diverse sources of background knowledge provide a way for making substantial progress in the field of WSD.

Word sense disambiguation via high order of learning in complex networks

Complex networks have been employed to model many real systems and as a modeling tool in a myriad of applications. In this paper, we use the framework of complex networks to the problem of supervised classification in the word disambiguation task, which consists in deriving a function from the supervised (or labeled) training data of ambiguous words. Traditional supervised data classification takes into account only topological or physical features of the input data. On the other hand, the human (animal) brain performs both low- and high-level orders of learning and it has facility to identify patterns according to the semantic meaning of the input data. In this paper, we apply a hybrid technique which encompasses both types of learning in the field of word sense disambiguation and show that the high-level order of learning can really improve the accuracy rate of the model. This evidence serves to demonstrate that the internal structures formed by the words do present patterns that, generally, cannot be correctly unveiled by only traditional techniques. Finally, we exhibit the behavior of the model for different weights of the low- and high-level classifiers by plotting decision boundaries. This study helps one to better understand the effectiveness of the model. Copyright (C) EPLA, 2012

BabelNet e il problema della Word Sense Disambiguation

La Word Sense Disambiguation è un problema informatico appartenente al campo di studi del Natural Language Processing, che consiste nel determinare il senso di una parola a seconda del contesto in cui essa viene utilizzata. Se un processo del genere può apparire banale per un essere umano, può risultare d'altra parte straordinariamente complicato se si cerca di codificarlo in una serie di istruzioni esguibili da una macchina. Il primo e principale problema necessario da affrontare per farlo è quello della conoscenza: per operare una disambiguazione sui termini di un testo, un computer deve poter attingere da un lessico che sia il più possibile coerente con quello di un essere umano. Sebbene esistano altri modi di agire in questo caso, quello di creare una fonte di conoscenza machine-readable è certamente il metodo che permette di affrontare il problema in maniera più diretta. Nel corso di questa tesi si cercherà, come prima cosa, di spiegare in cosa consiste la Word Sense Disambiguation, tramite una descrizione breve ma il più possibile dettagliata del problema. Nel capitolo 1 esso viene presentato partendo da alcuni cenni storici, per poi passare alla descrizione dei componenti fondamentali da tenere in considerazione durante il lavoro. Verranno illustrati concetti ripresi in seguito, che spaziano dalla normalizzazione del testo in input fino al riassunto dei metodi di classificazione comunemente usati in questo campo. Il capitolo 2 è invece dedicato alla descrizione di BabelNet, una risorsa lessico-semantica multilingua di recente costruzione nata all'Università La Sapienza di Roma. Verranno innanzitutto descritte le due fonti da cui BabelNet attinge la propria conoscenza, WordNet e Wikipedia. In seguito saranno illustrati i passi della sua creazione, dal mapping tra le due risorse base fino alla definizione di tutte le relazioni che legano gli insiemi di termini all'interno del lessico. Infine viene proposta una serie di esperimenti che mira a mettere BabelNet su un banco di prova, prima per verificare la consistenza del suo metodo di costruzione, poi per confrontarla, in termini di prestazioni, con altri sistemi allo stato dell'arte sottoponendola a diversi task estrapolati dai SemEval, eventi internazionali dedicati alla valutazione dei problemi WSD, che definiscono di fatto gli standard di questo campo. Nel capitolo finale vengono sviluppate alcune considerazioni sulla disambiguazione, introdotte da un elenco dei principali campi applicativi del problema. Vengono in questa sede delineati i possibili sviluppi futuri della ricerca, ma anche i problemi noti e le strade recentemente intraprese per cercare di portare le prestazioni della Word Sense Disambiguation oltre i limiti finora definiti.

Improving subjectivity detection using unsupervised subjectivity word sense disambiguation

En este trabajo se presenta un método para la detección de subjetividad a nivel de oraciones basado en la desambiguación subjetiva del sentido de las palabras. Para ello se extiende un método de desambiguación semántica basado en agrupamiento de sentidos para determinar cuándo las palabras dentro de la oración están siendo utilizadas de forma subjetiva u objetiva. En nuestra propuesta se utilizan recursos semánticos anotados con valores de polaridad y emociones para determinar cuándo un sentido de una palabra puede ser considerado subjetivo u objetivo. Se presenta un estudio experimental sobre la detección de subjetividad en oraciones, en el cual se consideran las colecciones del corpus MPQA y Movie Review Dataset, así como los recursos semánticos SentiWordNet, Micro-WNOp y WordNet-Affect. Los resultados obtenidos muestran que nuestra propuesta contribuye de manera significativa en la detección de subjetividad.

A supervised machine learning method for word sense disambiguation of Portuguese nouns

Dissertação de Mestrado, Ciências da Linguagem, Faculdade de Ciências Humanas e Sociais, Universidade do Algarve, 2010

Noun Sense Disambiguation using Co-Occurrence Relation in Machine Translation

Word Sense Disambiguation, the process of identifying the meaning of a word in a sentence when the word has multiple meanings, is a critical problem of machine translation. It is generally very difficult to select the correct meaning of a word in a sentence, especially when the syntactical difference between the source and target language is big, e.g., English-Korean machine translation. To achieve a high level of accuracy of noun sense selection in machine translation, we introduced a statistical method based on co-occurrence relation of words in sentences and applied it to the English-Korean machine translator RyongNamSan. ACM Computing Classification System (1998): I.2.7.

Using triangulation to identify word senses

Word sense disambiguation is the task of determining which sense of a word is intended from its context. Previous methods have found the lack of training data and the restrictiveness of dictionaries' choices of senses to be major stumbling blocks. A robust novel algorithm is presented that uses multiple dictionaries, the Internet, clustering and triangulation to attempt to discern the most useful senses of a given word and learn how they can be disambiguated. The algorithm is explained, and some promising sample results are given.

Unveiling the relationship between complex networks metrics and word senses

The automatic disambiguation of word senses (i.e., the identification of which of the meanings is used in a given context for a word that has multiple meanings) is essential for such applications as machine translation and information retrieval, and represents a key step for developing the so-called Semantic Web. Humans disambiguate words in a straightforward fashion, but this does not apply to computers. In this paper we address the problem of Word Sense Disambiguation (WSD) by treating texts as complex networks, and show that word senses can be distinguished upon characterizing the local structure around ambiguous words. Our goal was not to obtain the best possible disambiguation system, but we nevertheless found that in half of the cases our approach outperforms traditional shallow methods. We show that the hierarchical connectivity and clustering of words are usually the most relevant features for WSD. The results reported here shed light on the relationship between semantic and structural parameters of complex networks. They also indicate that when combined with traditional techniques the complex network approach may be useful to enhance the discrimination of senses in large texts. Copyright (C) EPLA, 2012

Improving distributed representation of word sense via WordNet Gloss composition and context clustering

In recent years, there has been an increas-ing interest in learning a distributed rep-resentation of word sense. Traditional context clustering based models usually require careful tuning of model parame-ters, and typically perform worse on infre-quent word senses. This paper presents a novel approach which addresses these lim-itations by first initializing the word sense embeddings through learning sentence-level embeddings from WordNet glosses using a convolutional neural networks. The initialized word sense embeddings are used by a context clustering based model to generate the distributed representations of word senses. Our learned represen-tations outperform the publicly available embeddings on 2 out of 4 metrics in the word similarity task, and 6 out of 13 sub tasks in the analogical reasoning task.

A gloss composition and context clustering based distributed word sense representation model

In recent years, there has been an increasing interest in learning a distributed representation of word sense. Traditional context clustering based models usually require careful tuning of model parameters, and typically perform worse on infrequent word senses. This paper presents a novel approach which addresses these limitations by first initializing the word sense embeddings through learning sentence-level embeddings from WordNet glosses using a convolutional neural networks. The initialized word sense embeddings are used by a context clustering based model to generate the distributed representations of word senses. Our learned representations outperform the publicly available embeddings on half of the metrics in the word similarity task, 6 out of 13 sub tasks in the analogical reasoning task, and gives the best overall accuracy in the word sense effect classification task, which shows the effectiveness of our proposed distributed distribution learning model.

Désambiguisation de sens par modèles de contextes et son application à la Recherche d’Information

Il est connu que les problèmes d'ambiguïté de la langue ont un effet néfaste sur les résultats des systèmes de Recherche d'Information (RI). Toutefois, les efforts de recherche visant à intégrer des techniques de Désambiguisation de Sens (DS) à la RI n'ont pas porté fruit. La plupart des études sur le sujet obtiennent effectivement des résultats négatifs ou peu convaincants. De plus, des investigations basées sur l'ajout d'ambiguïté artificielle concluent qu'il faudrait une très haute précision de désambiguation pour arriver à un effet positif. Ce mémoire vise à développer de nouvelles approches plus performantes et efficaces, se concentrant sur l'utilisation de statistiques de cooccurrence afin de construire des modèles de contexte. Ces modèles pourront ensuite servir à effectuer une discrimination de sens entre une requête et les documents d'une collection. Dans ce mémoire à deux parties, nous ferons tout d'abord une investigation de la force de la relation entre un mot et les mots présents dans son contexte, proposant une méthode d'apprentissage du poids d'un mot de contexte en fonction de sa distance du mot modélisé dans le document. Cette méthode repose sur l'idée que des modèles de contextes faits à partir d'échantillons aléatoires de mots en contexte devraient être similaires. Des expériences en anglais et en japonais montrent que la force de relation en fonction de la distance suit généralement une loi de puissance négative. Les poids résultant des expériences sont ensuite utilisés dans la construction de systèmes de DS Bayes Naïfs. Des évaluations de ces systèmes sur les données de l'atelier Semeval en anglais pour la tâche Semeval-2007 English Lexical Sample, puis en japonais pour la tâche Semeval-2010 Japanese WSD, montrent que les systèmes ont des résultats comparables à l'état de l'art, bien qu'ils soient bien plus légers, et ne dépendent pas d'outils ou de ressources linguistiques. La deuxième partie de ce mémoire vise à adapter les méthodes développées à des applications de Recherche d'Information. Ces applications ont la difficulté additionnelle de ne pas pouvoir dépendre de données créées manuellement. Nous proposons donc des modèles de contextes à variables latentes basés sur l'Allocation Dirichlet Latente (LDA). Ceux-ci seront combinés à la méthodes de vraisemblance de requête par modèles de langue. En évaluant le système résultant sur trois collections de la conférence TREC (Text REtrieval Conference), nous observons une amélioration proportionnelle moyenne de 12% du MAP et 23% du GMAP. Les gains se font surtout sur les requêtes difficiles, augmentant la stabilité des résultats. Ces expériences seraient la première application positive de techniques de DS sur des tâches de RI standard.

L'atténuation statistique des surdétections d'un correcteur grammatical symbolique

Les logiciels de correction grammaticale commettent parfois des détections illégitimes (fausses alertes), que nous appelons ici surdétections. La présente étude décrit les expériences de mise au point d’un système créé pour identifier et mettre en sourdine les surdétections produites par le correcteur du français conçu par la société Druide informatique. Plusieurs classificateurs ont été entraînés de manière supervisée sur 14 types de détections faites par le correcteur, en employant des traits couvrant di-verses informations linguistiques (dépendances et catégories syntaxiques, exploration du contexte des mots, etc.) extraites de phrases avec et sans surdétections. Huit des 14 classificateurs développés sont maintenant intégrés à la nouvelle version d’un correcteur commercial très populaire. Nos expériences ont aussi montré que les modèles de langue probabilistes, les SVM et la désambiguïsation sémantique améliorent la qualité de ces classificateurs. Ce travail est un exemple réussi de déploiement d’une approche d’apprentissage machine au service d’une application langagière grand public robuste.

Apprentissage des réseaux de neurones profonds et applications en traitement automatique de la langue naturelle

En apprentissage automatique, domaine qui consiste à utiliser des données pour apprendre une solution aux problèmes que nous voulons confier à la machine, le modèle des Réseaux de Neurones Artificiels (ANN) est un outil précieux. Il a été inventé voilà maintenant près de soixante ans, et pourtant, il est encore de nos jours le sujet d'une recherche active. Récemment, avec l'apprentissage profond, il a en effet permis d'améliorer l'état de l'art dans de nombreux champs d'applications comme la vision par ordinateur, le traitement de la parole et le traitement des langues naturelles. La quantité toujours grandissante de données disponibles et les améliorations du matériel informatique ont permis de faciliter l'apprentissage de modèles à haute capacité comme les ANNs profonds. Cependant, des difficultés inhérentes à l'entraînement de tels modèles, comme les minima locaux, ont encore un impact important. L'apprentissage profond vise donc à trouver des solutions, en régularisant ou en facilitant l'optimisation. Le pré-entraînnement non-supervisé, ou la technique du ``Dropout'', en sont des exemples. Les deux premiers travaux présentés dans cette thèse suivent cette ligne de recherche. Le premier étudie les problèmes de gradients diminuants/explosants dans les architectures profondes. Il montre que des choix simples, comme la fonction d'activation ou l'initialisation des poids du réseaux, ont une grande influence. Nous proposons l'initialisation normalisée pour faciliter l'apprentissage. Le second se focalise sur le choix de la fonction d'activation et présente le rectifieur, ou unité rectificatrice linéaire. Cette étude a été la première à mettre l'accent sur les fonctions d'activations linéaires par morceaux pour les réseaux de neurones profonds en apprentissage supervisé. Aujourd'hui, ce type de fonction d'activation est une composante essentielle des réseaux de neurones profonds. Les deux derniers travaux présentés se concentrent sur les applications des ANNs en traitement des langues naturelles. Le premier aborde le sujet de l'adaptation de domaine pour l'analyse de sentiment, en utilisant des Auto-Encodeurs Débruitants. Celui-ci est encore l'état de l'art de nos jours. Le second traite de l'apprentissage de données multi-relationnelles avec un modèle à base d'énergie, pouvant être utilisé pour la tâche de désambiguation de sens.

Design And Development Of A Named Entity Based Question Answering System For Malayalam Language

This is a Named Entity Based Question Answering System for Malayalam Language. Although a vast amount of information is available today in digital form, no effective information access mechanism exists to provide humans with convenient information access. Information Retrieval and Question Answering systems are the two mechanisms available now for information access. Information systems typically return a long list of documents in response to a user’s query which are to be skimmed by the user to determine whether they contain an answer. But a Question Answering System allows the user to state his/her information need as a natural language question and receives most appropriate answer in a word or a sentence or a paragraph. This system is based on Named Entity Tagging and Question Classification. Document tagging extracts useful information from the documents which will be used in finding the answer to the question. Question Classification extracts useful information from the question to determine the type of the question and the way in which the question is to be answered. Various Machine Learning methods are used to tag the documents. Rule-Based Approach is used for Question Classification. Malayalam belongs to the Dravidian family of languages and is one of the four major languages of this family. It is one of the 22 Scheduled Languages of India with official language status in the state of Kerala. It is spoken by 40 million people. Malayalam is a morphologically rich agglutinative language and relatively of free word order. Also Malayalam has a productive morphology that allows the creation of complex words which are often highly ambiguous. Document tagging tools such as Parts-of-Speech Tagger, Phrase Chunker, Named Entity Tagger, and Compound Word Splitter are developed as a part of this research work. No such tools were available for Malayalam language. Finite State Transducer, High Order Conditional Random Field, Artificial Immunity System Principles, and Support Vector Machines are the techniques used for the design of these document preprocessing tools. This research work describes how the Named Entity is used to represent the documents. Single sentence questions are used to test the system. Overall Precision and Recall obtained are 88.5% and 85.9% respectively. This work can be extended in several directions. The coverage of non-factoid questions can be increased and also it can be extended to include open domain applications. Reference Resolution and Word Sense Disambiguation techniques are suggested as the future enhancements

Language resources and linked data: a practical perspective

Recently, experts and practitioners in language resources have started recognizing the benefits of the linked data (LD) paradigm for the representation and exploitation of linguistic data on the Web. The adoption of the LD principles is leading to an emerging ecosystem of multilingual open resources that conform to the Linguistic Linked Open Data Cloud, in which datasets of linguistic data are interconnected and represented following common vocabularies, which facilitates linguistic information discovery, integration and access. In order to contribute to this initiative, this paper summarizes several key aspects of the representation of linguistic information as linked data from a practical perspective. The main goal of this document is to provide the basic ideas and tools for migrating language resources (lexicons, corpora, etc.) as LD on the Web and to develop some useful NLP tasks with them (e.g., word sense disambiguation). Such material was the basis of a tutorial imparted at the EKAW’14 conference, which is also reported in the paper.