SUDOKU: Treating Word Sense Disambiguation & Entitiy Linking as a Deterministic Problem - via an Unsupervised & Iterative Approach

Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pages 365–369, Denver, Colorado, June 4-5, 2015. c⃝2015 Association for Computational Linguistics SUDOKU: Treating Word Sense Disambiguation & Entity Linking as a Deterministic Problem – via an Unsupervised & Iterative Approach Steve L. Manion University of Canterbury, Christchurch, New Zealand steve.manion @pg.canterbury.ac.nz Abstract SUDOKU’s submissions to SemEval Task 13 treats Word Sense Disambiguation and Entity Linking as a deterministic problem that ex- ploits two key attributes of open-class words as constraints – their degree of polysemy and their part of speech. This is an extension and further validation of the results achieved by Manion and Sainudiin (2014). SUDOKU’s three submissions are incremental in the use of the two aforementioned constraints. Run1 has no constraints and disambiguates all lem- mas in one pass. Run2 disambiguates lemmas at increasing degrees of polysemy, leaving the most polysemous until last. Run3 is identical to Run2, with the additional constraint of dis- ambiguating all named entities and nouns first before other types of open-class words (verbs, adjectives, and adverbs). Over all-domains, for English Run2 and Run3 were placed sec- ond and third. For Spanish Run2, Run3, and Run1 were placed first, second, and third re- spectively. For Italian Run1 was placed first with Run2 and Run3 placed second equal. 1 Introduction & Related Work Almost a decade ago, Agirre and Edmonds (2007) suggested the promising potential for WSD that could exploit the interdependencies between senses in an interactive manner. In other words, this would be a WSD system which allows the disambiguation of word a to directly influence the consecutive dis- ambiguation of word b. This is analogous to treating WSD as a deterministic problem, much like the Su- doku puzzle in which the final solution is reached by adhering to a set of pre-determined constraints. Con- ventional approaches to WSD often overlook the po- tential to exploit sense interdependencies, and sim- ply disambiguate all senses in one pass based on a context window (e.g. a sentence or document). For this task the author proposes an iterative approach which makes several passes based on a set of con- straints. For a more formal distinction between the conventional and iterative approach to WSD, please refer to this paper (Manion and Sainudiin, 2014). Yr %NE %N %V %R %A F ∆F ’04 - 37.7 34.0 12.6 15.6 27.1 +16.8 ’10 - 73.8 26.2 - - 26.8 +11.1 ’13 17.1 82.9 - - - 58.3 +6.1 ’15 6.0 44.9 28.9 6.5 13.7 55.8 +5.8 Table 1: Parts of Speech disambiguated (as percent- ages) for each SemEval Task (denoted by its year). In-Degree Centrality as implemented in (Manion and Sainudiin, 2014) observes F-Score improvement (F + ∆F) by applying the iterative approach. The author found in the investigations of his thesis (Manion, 2014) that the iterative approach performed best on the SemEval 2013 Multilingual WSD Task (Navigli et al., 2013), as opposed to ear- lier tasks such as SensEval 2004 English All Words WSD Task (Snyder and Palmer, …

Content truncated to 500 words