Word-sense disambiguation

In computational linguistics, word-sense disambiguation (WSD) is an open problem concerned with identifying which sense of a word is used in a sentence. The solution to this problem impacts other computer-related writing, such as discourse, improving relevance of search engines, anaphora resolution, coherence, inference. In computational linguistics, word-sense disambiguation (WSD) is an open problem concerned with identifying which sense of a word is used in a sentence. The solution to this problem impacts other computer-related writing, such as discourse, improving relevance of search engines, anaphora resolution, coherence, inference. The human brain is quite proficient at word-sense disambiguation. That natural language is formed in a way that requires so much of it is a reflection of that neurologic reality. In other words, human language developed in a way that reflects (and also has helped to shape) the innate ability provided by the brain's neural networks. In computer science and the information technology that it enables, it has been a long-term challenge to develop the ability in computers to do natural language processing and machine learning. A rich variety of techniques have been researched, from dictionary-based methods that use the knowledge encoded in lexical resources, to supervised machine learning methods in which a classifier is trained for each distinct word on a corpus of manually sense-annotated examples, to completely unsupervised methods that cluster occurrences of words, thereby inducing word senses. Among these, supervised learning approaches have been the most successful algorithms to date. Accuracy of current algorithms is difficult to state without a host of caveats. In English, accuracy at the coarse-grained (homograph) level is routinely above 90%, with some methods on particular homographs achieving over 96%. On finer-grained sense distinctions, top accuracies from 59.1% to 69.0% have been reported in evaluation exercises (SemEval-2007, Senseval-2), where the baseline accuracy of the simplest possible algorithm of always choosing the most frequent sense was 51.4% and 57%, respectively. Disambiguation requires two strict inputs: a dictionary to specify the senses which are to be disambiguated and a corpus of language data to be disambiguated (in some methods, a training corpus of language examples is also required). WSD task has two variants: 'lexical sample' and 'all words' task. The former comprises disambiguating the occurrences of a small sample of target words which were previously selected, while in the latter all the words in a piece of running text need to be disambiguated. The latter is deemed a more realistic form of evaluation, but the corpus is more expensive to produce because human annotators have to read the definitions for each word in the sequence every time they need to make a tagging judgement, rather than once for a block of instances for the same target word. To give a hint how all this works, consider three examples of the distinct senses that exist for the (written) word 'bass':