Word Sense Disambiguation Task Research Articles

Construction of Context Models for Word Sense Disambiguation

This paper presents a study on the use of word context features for Word Sense Disambiguation (WSD). State-of-the-art WSD systems achieve high accuracy by using resources such as dictionaries, taggers, lexical analyzers or topic modeling packages. However, these resources are either too heavy or don’t have sufficient coverage for large-scale tasks such as information retrieval. The use of local context for WSD is common, but the rationale behind the formulation of features is often based on trial and error. We therefore investigate the notion of relatedness of context words to the target word (the word to be disambiguated), and propose an unsupervised method for finding the optimal weights for context words based on their distance to the target word. The key idea behind the method is that the optimal weights should maximize the similarity of two context models constructed from different context samples of the same word. Our experimental results show that the strength of the relation between two words follows approximately a power law. The resulting context models are used in Naive Bayes classifiers for word sense disambiguation. Our evaluation on Semeval WSD tasks in both English and Japanese show that our method can achieve state-of-the-art effectiveness even though it does not use external tools like most existing methods. The high efficiency makes it possible to use our method in large scale applications such as information retrieval.

Active Learning With Sampling by Uncertainty and Density for Data Annotations

To solve the knowledge bottleneck problem, active learning has been widely used for its ability to automatically select the most informative unlabeled examples for human annotation. One of the key enabling techniques of active learning is uncertainty sampling, which uses one classifier to identify unlabeled examples with the least confidence. Uncertainty sampling often presents problems when outliers are selected. To solve the outlier problem, this paper presents two techniques, sampling by uncertainty and density (SUD) and density-based re-ranking. Both techniques prefer not only the most informative example in terms of uncertainty criterion, but also the most representative example in terms of density criterion. Experimental results of active learning for word sense disambiguation and text classification tasks using six real-world evaluation data sets demonstrate the effectiveness of the proposed methods.

A Reexamination of MRD-Based Word Sense Disambiguation

This article reconsiders the task of MRD-based word sense disambiguation, in extending the basic Lesk algorithm to investigate the impact on WSD performance of different tokenization schemes and methods of definition extension. In experimentation over the Hinoki Sensebank and the Japanese Senseval-2 dictionary task, we demonstrate that sense-sensitive definition extension over hyponyms, hypernyms, and synonyms, combined with definition extension and word tokenization leads to WSD accuracy above both unsupervised and supervised baselines. In doing so, we demonstrate the utility of ontology induction and establish new opportunities for the development of baseline unsupervised WSD methods.

Semantic Drift in Espresso-style Bootstrapping: Graph-theoretic Analysis and Evaluation in Word Sense Disambiguation

Bootstrapping has a tendency, called semantic drift, to select instances unrelated to the seed instances as the iteration proceeds. We demonstrate the semantic drift of Espresso-style bootstrapping has the same root as the topic drift of Kleinberg's HITS, using a simplified graph-based reformulation of bootstrapping. We confirm that two graph-based algorithms, the von Neumann kernels and the regularized Laplacian, can reduce the effect of semantic drift in the task of word sense disambiguation (WSD) on Senseval-3 English Lexical Sample Task. Proposed algorithms achieve superior performance to Espresso and previous graph-based WSD methods, even though the proposed algorithms have less parameters and are easy to calibrate.

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.

Learning Representative Examples for Data Annotation

Among the techniques to solve the knowledge bottleneck problem of supervised learning models, active learning is a promising method. One of the popular techniques of active learning is uncertainty sampling which, however, often presents problems when outliers are selected. To solve this problem, this paper presents a density-based re-ranking technique, in which a density measure is adopted to determine whether an unlabeled example is an outlier. The motivation of this method is to use not only the most informative example in terms of uncertainty measure, but also the most representative example in terms of density measure. The second effort we made is that a technique of sampling by clustering (SBC) is presented to build a representative initial training data set for active learning. Experimental results of active learning for word sense disambiguation and text classification tasks show that the proposed techniques can improve active learning with uncertainty sampling.

Word sense disambiguation across two domains: Biomedical literature and clinical notes

The aim of this study is to explore the word sense disambiguation (WSD) problem across two biomedical domains—biomedical literature and clinical notes. A supervised machine learning technique was used for the WSD task. One of the challenges addressed is the creation of a suitable clinical corpus with manual sense annotations. This corpus in conjunction with the WSD set from the National Library of Medicine provided the basis for the evaluation of our method across multiple domains and for the comparison of our results to published ones. Noteworthy is that only 20% of the most relevant ambiguous terms within a domain overlap between the two domains, having more senses associated with them in the clinical space than in the biomedical literature space. Experimentation with 28 different feature sets rendered a system achieving an average F-score of 0.82 on the clinical data and 0.86 on the biomedical literature.

Learning model order from labeled and unlabeled data for partially supervised classification, with application to word sense disambiguation

Previous partially supervised classification methods can partition unlabeled data into positive examples and negative examples for a given class by learning from positive labeled examples and unlabeled examples, but they cannot further group the negative examples into meaningful clusters even if there are many different classes in the negative examples. Here we proposed an automatic method to obtain a natural partitioning of mixed data (labeled data + unlabeled data) by maximizing a stability criterion defined on classification results from an extended label propagation algorithm over all the possible values of model order (or the number of classes) in mixed data. Our experimental results on benchmark corpora for word sense disambiguation task indicate that this model order identification algorithm with the extended label propagation algorithm as the base classifier outperforms SVM, a one-class partially supervised classification algorithm, and the model order identification algorithm with semi-supervised k-means clustering as the base classifier when labeled data is incomplete.

DISTRIBUTIONAL ANALYSIS OF RELATED SYNSETS IN WordNet FOR A WORD SENSE DISAMBIGUATION TASK

This work presents a new method for an unsupervised word sense disambiguation task using WordNet semantic relations. In this method we expand the context of a word being disambiguated with related synsets from the available WordNet relations and study within this set the distribution of the related synset that correspond to each sense of the target word. A single sample Pearson-Chi-Square goodness-of-fit hypothesis test is used to determine whether the null hypothesis of a composite normality PDF is a reasonable assumption for a set of related synsets corresponding to a sense. The calculated p-value from this test is a critical value for deciding the correct sense. The target word is assigned the sense, the related synsets of which are distributed more "abnormally" relative to the other sets of the other senses. Our algorithm is evaluated on English lexical sample data from the Senseval-2 word sense disambiguation competition. Three WordNet relations, antonymy, hyponymy and hypernymy give a distributional set of related synsets for the context that was proved quite a good word sense discriminator, achieving comparable results with the system obtained the better results among the other competing participants.

Combining Knowledge- and Corpus-based Word-Sense-Disambiguation Methods

In this paper we concentrate on the resolution of the lexical ambiguity that arises when a given word has several different meanings. This specific task is commonly referred to as word sense disambiguation (WSD). The task of WSD consists of assigning the correct sense to words using an electronic dictionary as the source of word definitions. We present two WSD methods based on two main methodological approaches in this research area: a knowledge-based method and a corpus-based method. Our hypothesis is that word-sense disambiguation requires several knowledge sources in order to solve the semantic ambiguity of the words. These sources can be of different kinds--- for example, syntagmatic, paradigmatic or statistical information. Our approach combines various sources of knowledge, through combinations of the two WSD methods mentioned above. Mainly, the paper concentrates on how to combine these methods and sources of information in order to achieve good results in the disambiguation. Finally, this paper presents a comprehensive study and experimental work on evaluation of the methods and their combinations.

Lexical knowledge and human disagreement on a WSD task

This paper explores factors correlating with lack of inter-annotator agreement on a word sense disambiguation (WSD) task taken from SENSEVAL-2. Twenty-seven subjects were given a series of tasks requiring word sense judgments. Subjects were asked to judge the applicability of word senses to polysemous words used in context. Metrics of lexical ability were evaluated as predictors of agreement between judges. A strong interaction effect was found for lexical ability, in which differences between levels of lexical knowledge predict disagreement. Individual levels of lexical knowledge, however, were not independently predictive of disagreement. The finding runs counter to previous assumptions regarding expert agreement on WSD annotation tasks, which in turn impacts notions of a meaningful “gold standard” for systems evaluation.

Automatic Association of Web Directories with Word Senses

We describe an algorithm that combines lexical information (from WordNet 1.7) with Web directories (from the Open Directory Project) to associate word senses with such directories. Such associations can be used as rich characterizations to acquire sense-tagged corpora automatically, cluster topically related senses, and detect sense specializations. The algorithm is evaluated for the 29 nouns (147 senses) used in the Senseval 2 competition, obtaining 148 (word sense, Web directory) associations covering 88% of the domain-specific word senses in the test data with 86% accuracy. The richness of Web directories as sense characterizations is evaluated in a supervised word sense disambiguation task using the Senseval 2 test suite. The results indicate that, when the directory/word sense association is correct, the samples automatically acquired from the Web directories are nearly as valid for training as the original Senseval 2 training instances. The results support our hypothesis that Web directories are a rich source of lexical information: cleaner, more reliable, and more structured than the full Web as a corpus.

Combining Classifiers for word sense disambiguation

Classifier combination is an effective and broadly useful method of improving system performance. This article investigates in depth a large number of both well-established and novel classifier combination approaches for the word sense disambiguation task, studied over a diverse classifier pool which includes feature-enhanced Naïve Bayes, Cosine, Decision List, Transformation-based Learning and MMVC classifiers. Each classifier has access to the same rich feature space, comprised of distance weighted bag-of-lemmas, local ngram context and specific syntactic relations, such as Verb-Object and Noun-Modifier. This study examines several key issues in system combination for the word sense disambiguation task, ranging from algorithmic structure to parameter estimation. Experiments using the standard SENSEVAL2 lexical-sample data sets in four languages (English, Spanish, Swedish and Basque) demonstrate that the combination system obtains a significantly lower error rate when compared with other systems participating in the SENSEVAL2 exercise, yielding state-of-the-art performance on these data sets.

Integrating Linguistic Resources in TC through WSD

Information access methods must be improved to overcome theinformation overload that most professionals face nowadays. Textclassification tasks, like Text Categorization, help the usersto access to the great amount of text they find in the Internetand their organizations.TC is the classification of documents into a predefined set ofcategories. Most approaches to automatic TC are based on theutilization of a training collection, which is a set of manuallyclassified documents. Other linguistic resources that areemerging, like lexical databases, can also be used forclassification tasks. This article describes an approach to TCbased on the integration of a training collection (Reuters-21578)and a lexical database (WordNet 1.6) as knowledge sources.Lexical databases accumulate information on the lexical items ofone or several languages. This information must be filtered inorder to make an effective use of it in our model of TC. Thisfiltering process is a Word Sense Disambiguation task. WSDis the identification of the sense of words in context. This taskis an intermediate process in many natural language processingtasks like machine translation or multilingual informationretrieval. We present the utilization of WSD as an aid for TC. Ourapproach to WSD is also based on the integration of two linguisticresources: a training collection (SemCor and Reuters-21578) and alexical database (WordNet 1.6).We have developed a series of experiments that show that: TC andWSD based on the integration of linguistic resources are veryeffective; and, WSD is necessary to effectively integratelinguistic resources in TC.

Is Word Sense Disambiguation Just One More NLP Task

The paper examines the task of Word Sense Disambiguation (WSD) criticallyand compares it with Part of Speech (POS) tagging, arguing that the abilityof a writer to create new senses distinguishes the tasks and makes it moreproblematic to test WSD by the mark-up-and-model paradigm, because newsenses cannot be marked up against dictionaries. This serves to set WSDapart and puts limits on its effectiveness as an independent NLP task.Moreover, it is argued that current WSD methods based on very small wordsamples are also potentially misleading because they may or may not scaleup. Since all-word WSD methods are now available and are producing figurescomparable to the smaller scale tasks, it is argued that we shouldconcentrate on the former and find ways of bootstrapping test materialsfor such tests in the future.