Description: This paper presents a Word Sense Disambiguation method based on the idea of semantic density between words. The disambiguation is done in the context of WordNet. The Internet is used as a raw corpora to provide statistical information for word associations. A metric is introduced and used to measure the semantic density and to rank all possible combinations of the senses of two words. This method provides a precision of 58% in indicating the correct sense for both words at the same time. The precision increases as we consider more choices: 70% for top two ranked and 73% for top three ranked.

Description: This paper discusses a method for word sense disambiguation of unrestricted text. Selecting the most appropriate sense for an ambiguous word in a sentence is a central problem in Natural Language Processing. In this paper, the authors present a method that attempts to disambiguate all the nouns, verbs, adverbs and adjectives in a text, using the senses provided in WordNet. The senses are ranked using two sources of information: (1) the Internet for gathering statistics for word-word co-occurrences and (2) WordNet for measuring the semantic density for a pair of words. The authors report an average accuracy of 80% for the first ranked sense, and 91% for the first two ranked senses. Extensions of this method for larger windows of more than two words are considered.

Description: This paper discusses a semi-complete disambiguation algorithm for open text. Word Sense Disambiguation (WSD) is one of the most difficult areas of Natural Language Processing (NLP); the semantic comprehension of a text, and the possibility to expand a text with semantically related information, drastically depends on the availability of a highly accurate WSD algorithm. Solutions considered so far by researchers for the WSD problem, are making use of machine readable dictionaries (Leacock, Chodorow and Miller 1998), or the information gathered from raw or semantically disambiguated corpora (Yarowsky 1995). These methods are designed either to work with a few pre-selected words, in which case a high accuracy is obtained, or they are general methods which disambiguate, with lower precision, all the words in a text. With the present work, the authors are trying to achieve a compromise between these two different directions. There are fields in NLP, like Information Retrieval and others, which could benefit from a method which performs a semi-complete disambiguation (i.e. it disambiguates only a certain percentage of the words in a text), but which is highly accurate.

Description: In this paperarticle, the authors describe a boolean Information Retrieval system that adds words semantics to the classic word based indexing. Two of the main tasks of our system, namely the indexing and retrieval components, are using a combined word-based and sense-based approach. The key to our system is a methodology for building semantic representations of open text, at word and collocation level. This new technique, called semantic indexing, shows improved effectiveness over the classic word based indexing techniques.

Description: This paper discusses FALCON. Abstract: This paper presents the features of FALCON, an answer engine that integrates different forms of syntactic, semantic and pragmatic knowledge for the goal of achieving better performance. The answer engine handles question reformulations, finds the expected answer type from a large hierarchy that incorporates the WordNet semantic net and extracts answers after performing unifications on the semantic forms of the question and its candidate answers. To rule out erroneous answers, it provides justification option, implemented as an abductive proof. In TREC-9, FALCON generated a score of 58% for short answers and 76% for long answers.