Word sense disambiguation using WordNet relations

2002

This paper presents an adaptation of Lesk’s dictionarybased word sense disambiguation algorithm. Rather than using a standard dictionary as the source of glosses for our approach, the lexical database WordNet is employed. This provides a rich hierarchy of semantic relations that our algorithm can exploit. This method is evaluated using the English lexical sample data from the Senseval-2 word sense disambiguation exercise, and attains an overall accuracy of 32%. This represents a significant improvement over the 16% and 23% accuracy attained by variations of the Lesk algorithm used as benchmarks during the SENSEVAL-2 comparative exercise among word sense disambiguation systems.

GWC, 2016

In this paper we present an analysis of different semantic relations extracted from WordNet, Extended WordNet and Sem-Cor, with respect to their role in the task of knowledge-based word sense disambiguation. The experiments use the same algorithm and the same test sets, but different variants of the knowledge graph. The results show that different sets of relations have different impact on the results: positive or negative. The beneficial ones are discussed with respect to the combination of relations and with respect to the test set. The inclusion of inference has only a modest impact on accuracy, while the addition of syntactic relations produces stable improvement over the baselines.

International Journal of Recent Technology and Engineering, 2014

Word sense disambiguation is a technique in the field of natural language processing where the main task is to find the correct sense in which a word occurs in a particular context. It is found to be of vital help to applications such as question answering, machine translation, text summarization, text classification, information retrieval etc. This has resulted in excessive interest in approaches based on machine learning which performs classification of word senses automatically. The main motivation behind word sense disambiguation is to allow the users to make ample use of the available technologies because ambiguities present in any language provide great difficulty in the use of information technology as words in human language that occur in a particular context can be interpreted in more than one way depending on the context. In this paper we put forward a survey of supervised, unsupervised and knowledge based approaches and algorithms available in word sense disambiguation (WSD). Index Terms-Machine readable dictionary, Machine translation, Natural language processing, Wordnet, Word sense disambiguation.

PolyWordNet is a new lexical database which deals with the organization of senses of polysemy words. It mimics the way how human mind organizes the senses of polysemy words and their related words to analyze and determine correct meaning of a polysemy word in a context. A related word of a sense of a polysemy word is a word which provides necessary and sufficient context to disambiguate the meaning of the polysemy word. A context with a polysemy word must contain at least one related word that determines the correct sense of the polysemy word. The PolyWordNet utilizes this fact to organize the senses of a polysemy word with their corresponding related words. PolyWordNet is completely different than that of the dictionary and WordNet. The words which spell similar come together in dictionary. The words with similar meaning come together in WordNet. The same words, in WordNet, are connected to the multiple senses of the same polysemy word. This introduces an ambiguity. This ambiguity is resolved in PolyWordNet by linking one related word only with a single sense of the same polysemy word. The PolyWordNet can be used to disambiguate senses of polysemy words more precisely and more efficiently.

The term "knowledge acquisition bottleneck" has been used in Word Sense Disambiguation Tasks (WSDTs) to illustrate / express the problem of the lack of large tagged corpora. In this paper, an automated WSDT is based on text corpora extracted / collected from Internet web pages. First, the disambiguation for the sense of a word, in a context, is based on the use of its definition and the definitions of its direct hyponyms in the WordNet to form queries for searching the Internet. Then, the "sense-related examples", in other words the collected answers / information, are used to disambiguate the word's sense in the context. A (similarity) metric is used to calculate the similarity between the context and the "sense-related examples" and the word is assigned the sense of the most similar example with the context. Some experiments are briefly described and the evaluation of the proposed method is discussed.

Word sense disambiguation is an essential, yet a very difficult task in natural language processing. While several other NLP tasks, such as POS tagging, can provide more than fairly good results (highly accurate, with almost 100% rate of successfully labeled words), disambiguation is far from achieving such performances. However, we will demonstrate the need of word sense disambiguation in computing the lexical chains on a special kind of text (chats) using a WordNet-based approach. In addition, we will try to identify the bottlenecks (mostly in respect to accuracy) in such an approach and provide possible improvements.

Speech Technology and Human- …, 2011

This paper proposes a knowledge-based WSD (Word Sense Disambiguation) method derived from the Lesk algorithm. The proposed method considers an extension of the definition domain of the Lesk algorithm by creating a lexicon network from tagged lexicon glosses. We present several methods that adjust the lexicon network in order to better describe the natural language. Further, on the pre-processed lexicon network we build competence and definition semantic trees for each sense that will be used to compute costs of semantic similarity between words senses. For this purpose we use a WSD window limited to a phrase, and a similar reasoning for larger contexts. For testing we apply our methods to the recently WordNet tagged glosses.

Word Sense Disambiguation is the process of determining which sense of a word is used in a given context. Word Sense Disambiguation is a classi cation problem. Given an instance of a word and the context in which it occurs , the aim is to determine the sense of that occurrence of the word . In this paper a comparison of three recent word sense disambiguation tech- niques is presented. The Word Sense Disambiguation methods surveyed are as fol- lows. Word Sense Disambiguation with automatically acquired knowledge, Word Sense Disambiguation using enriched semantic relation network and a Word Sense Disambiguation based on Lexical Chaining. These approaches are evaluated with standard corporas and their results are compared. These approaches are extensively used in Natural Language Processing

2005

We have previously introduced a method of word sense disambiguation that computes the intended sense of a target word, using WordNet-based measures of semantic relatedness . SenseRelate::TargetWord is a Perl package that implements this algorithm. The disambiguation process is carried out by selecting that sense of the target word which is most related to the context words. Relatedness between word senses is measured using the WordNet::Similarity Perl modules.

2008

Word sense disambiguation (WSD) methods evolve towards exploring all of the available semantic information that word thesauri provide. In this scope, the use of semantic graphs and new measures of semantic relatedness may offer better WSD solutions. In this paper we propose a new measure of semantic relatedness between any pair of terms for the English language, using WordNet as our knowledge base. Furthermore, we introduce a new WSD method based on the proposed measure.