Search

In communication, textual data are a vital attribute. In all languages, ambiguous or polysemous words' meaning changes depending on the context in which they are used. The ability to determine the ambiguous word's correct meaning is a Know‐distill challenging task in natural language processing (NLP). Word sense disambiguation (WSD) is an NLP process to analyze and determine the correct meaning of polysemous words in a text. WSD is a computational linguistics task that automatically identifies the polysemous word's set of senses. Based on the context some word comes into view, WSD recognizes and tags the word to its correct priori known meaning. Semitic languages like Arabic have even more significant challenges than other languages since Arabic lacks diacritics, standardization, and a massive shortage of available resources. Recently, many approaches and techniques have been suggested to solve word ambiguity dilemmas in many different ways and several languages. In this review paper, an extensive survey of research works is presented, seeking to solve Arabic word sense disambiguation with the existing AWSD datasets. This article is categorized under:Algorithmic Development > Text MiningTechnologies > Machine Learning [ABSTRACT FROM AUTHOR]

The article explains the concept of vector semantics under the computational linguistics fields of interest to humanists. Topics mentioned include the use of statistical theory to develop models for meanings of words, a description of concepts used by literary critic William Empson in explaining the use of word's meanings to create poems, and the different types of ambiguity.

We introduce a generative probabilistic model, the noisy channel model, for unsupervised word sense disambiguation. In our model, each context C is modeled as a distinct channel through which the speaker intends to transmit a particular meaning S using a possibly ambiguous word W. To reconstruct the intended meaning the hearer uses the distribution of possible meanings in the given context P(S|C) and possible words that can express each meaning P(W|S). We assume P(W|S) is independent of the context and estimate it using WordNet sense frequencies. The main problem of unsupervised WSD is estimating context-dependent P(S|C) without access to any sense-tagged text. We show one way to solve this problem using a statistical language model based on large amounts of untagged text. Our model uses coarse-grained semantic classes for S internally and we explore the effect of using different levels of granularity on WSD performance. The system outputs fine-grained senses for evaluation, and its performance on noun disambiguation is better than most previously reported unsupervised systems and close to the best supervised systems. [ABSTRACT FROM AUTHOR]

Wisdom is a system for performing word sense disambiguation (WSD) using a limited number of linguistic features and a simple supervised learning algorithm. The most likely sense tag for a word is determined by calculating co-occurrence statistics for words appearing within a small window. This paper gives a brief description of the components in the Wisdom system and the algorithm used to predict the correct sense tag. Some results for Wisdom from the Senseval competition are presented, and directions for future work are also explored. [ABSTRACT FROM AUTHOR]

This work combines a set of available techniques – which could be further extended – to perform noun sense disambiguation. We use several unsupervised techniques (Rigau et al., 1997) that draw knowledge from a variety of sources. In addition, we also apply a supervised technique in order to show that supervised and unsupervised methods can be combined to obtain better results. This paper tries to prove that using an appropriate method to combine those heuristics we can disambiguate words in free running text with reasonable precision. [ABSTRACT FROM AUTHOR]

A Classification Information Model is a pattern classification model. The model decides the proper class of an input instance by integrating individual decisions, each of which is made with each feature in the pattern. Each individual decision is weighted according to the distributional property of the feature deriving the decision. An individual decision and its weight are represented as classification information which is extracted from the training instances. In the word sense disambiguation based on the model, the proper sense of an input instance is determined by the weighted sum of whole individual decisions derived from the features contained in the instance. [ABSTRACT FROM AUTHOR]

SENSEVAL set itself the task of evaluating automatic word sense disambiguation programs (see Kilgarriff and Rosenzweig, this volume, for an overview of the framework and results). In order to do this, it was necessary to provide a `gold standard' dataset of `correct' answers. This paper will describe the lexicographic part of the process involved in creating that dataset. The primary objective was for a group of lexicographers to manually examine keywords in a large number of corpus contexts, and assign to each context a sense-tag for the keyword, taken from the Hector dictionary. Corpus contexts also had to be manually part-of-speech (POS) tagged. Various observations made and insights gained by the lexicographers during this process will be presented, including a critique of the resources and the methodology. [ABSTRACT FROM AUTHOR]

The paper describes SENSE, a word sense disambiguation system that makes use of different types of cues to infer the most likely sense of a word given its context. Architecture and functioning of the system are briefly illustrated. Results are given for the ROMANSEVAL Italian test corpus of verbs. [ABSTRACT FROM AUTHOR]

We describe a memory-based classification architecture for word sense disambiguation and its application to the SENSEVAL evaluation task. For each ambiguous word, a semantic word expert is automatically trained using a memory-based approach. In each expert, selecting the correct sense of a word in a new context is achieved by finding the closest match to stored examples of this task. Advantages of the approach include (i) fast development time for word experts, (ii) easy and elegant automatic integration of information sources, (iii) use of all available data for training the experts, and (iv) relatively high accuracy with minimal linguistic engineering. [ABSTRACT FROM AUTHOR]

This paper describes the evaluation of a WSD method within SENSEVAL. This method is based on Semantic Classification Trees (SCTs) and short context dependencies between nouns and verbs. The training procedure creates a binary tree for each word to be disambiguated. SCTs are easy to implement and yield some promising results. The integration of linguistic knowledge could lead to substantial improvement. [ABSTRACT FROM AUTHOR]

TLC is a supervised training (S) system that uses a Bayesian statistical model and features of a word's context to identify word sense. We describe the classifier's operation and how it can be configured to use only topical context cues, only local cues, or a combination of both. Our results on Senseval's final run are presented along with a comparison to the performance of the best S system and the average for S systems. We discuss ways to improve TLC by enriching its feature set and by substituting other decision procedures for the Bayesian model. Future development of supervised training classifiers will depend on the availability of tagged training data. TLC can assist in the hand-tagging effort by helping human taggers locate infrequent senses of polysemous words. [ABSTRACT FROM AUTHOR]

The selectional preferences of verbal predicates are an important component of a computational lexicon. They have frequently been cited as being useful for WSD, alongside other sources of knowledge. We evaluate automatically acquired selectional preferences on the level playing field provided by SENSEVAL to examine to what extent they help in WSD. [ABSTRACT FROM AUTHOR]

We describe a simple approach to word sense disambiguation using information filtering and extraction. The method fully exploits and extends the information available in the Hector dictionary. The algorithm proceeds by the application of several filters to prune the candidate set of word senses returning the most frequent if more than one remains. The experimental methodology and its implication are also discussed. [ABSTRACT FROM AUTHOR]

Discusses issues on the existence of word meanings. Reaffirmation of the argument, on the basis of recent work in corpus analysis, that checklist theories in their current form are superficial and misleading; Redundancy of natural language processing; Identification of words with different meanings.

A word sense disambiguation system which is going to be used as part of a NLP system needs to be large scale, able to be optimised towards a specific task and above all accurate. This paper describes the knowledge sources used in a disambiguation system able to achieve all three of these criteria. It is a hybrid system combining sub-symbolic, stochastic and rule-based learning. The paper reports the results achieved in Senseval and analyses them to show the system's strengths and weaknesses relative to other similar systems. [ABSTRACT FROM AUTHOR]

This paper describes the grling-sdm system, which is a supervised probabilistic classifier that participated in the 1998 SENSEVAL competition for word-sense disambiguation. This system uses model search to select decomposable probability models describing the dependencies among the feature variables. These types of models have been found to be advantageous in terms of efficiency and representational power. Performance on the SENSEVAL evaluation data is discussed. [ABSTRACT FROM AUTHOR]

Presents a case-based algorithm for word sense disambiguation. Suggestion that the local context of a word is a set of paths in the dependency tree of the sentence that contains the word; Use of a thesaurus automatically extracted from a large corpus to bridge the gap between the training examples and the testing corpus; Related works on word sense disambiguation algorithms.

The paper examines the task of Word Sense Disambiguation (WSD) critically and compares it with Part of Speech (POS) tagging, arguing that the ability of a writer to create new senses distinguishes the tasks and makes it more problematic to test WSD by the mark-up-and-model paradigm, because new senses cannot be marked up against dictionaries. This serves to set WSD apart and puts limits on its effectiveness as an independent NLP task. Moreover, it is argued that current WSD methods based on very small word samples are also potentially misleading because they may or may not scale up. Since all-word WSD methods are now available and are producing figures comparable to the smaller scale tasks, it is argued that we should concentrate on the former and find ways of bootstrapping test materials for such tests in the future. [ABSTRACT FROM AUTHOR]

Presents the adopted methodology for evaluating sense disambiguation in French language. Procedures used to set up the French exercise; Participating systems and evaluation procedure in the French ROMANSEVAL; Evaluation metrics and results.