Tense Sense Disambiguation: A New Syntactic Polysemy Task

44579

Authors

nan

Abstract

Polysemy is a major characteristic of natu- ral languages. Like words, syntactic forms can have several meanings. Understanding the correct meaning of a syntactic form is of great importance to many NLP applications. In this paper we address an important type of syn- tactic polysemy – the multiple possible senses of tense syntactic forms. We make our dis- cussion concrete by introducing the task of Tense Sense Disambiguation (TSD): given a concrete tense syntactic form present in a sen- tence, select its appropriate sense among a set of possible senses. Using English gram- mar textbooks, we compiled a syntactic sense dictionary comprising common tense syntac- tic forms and semantic senses for each. We an- notated thousands of BNC sentences using the defined senses. We describe a supervised TSD algorithm trained on these annotations, which outperforms a strong baseline for the task. 1

Keywords

nan

Full Content

Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pages 325–334, MIT, Massachusetts, USA, 9-11 October 2010. c⃝2010 Association for Computational Linguistics Tense Sense Disambiguation: a New Syntactic Polysemy Task Roi Reichart ICNC Hebrew University of Jerusalem roiri@cs.huji.ac.il Ari Rappoport Institute of Computer Science Hebrew University of Jerusalem arir@cs.huji.ac.il Abstract Polysemy is a major characteristic of natu- ral languages. Like words, syntactic forms can have several meanings. Understanding the correct meaning of a syntactic form is of great importance to many NLP applications. In this paper we address an important type of syn- tactic polysemy – the multiple possible senses of tense syntactic forms. We make our dis- cussion concrete by introducing the task of Tense Sense Disambiguation (TSD): given a concrete tense syntactic form present in a sen- tence, select its appropriate sense among a set of possible senses. Using English gram- mar textbooks, we compiled a syntactic sense dictionary comprising common tense syntac- tic forms and semantic senses for each. We an- notated thousands of BNC sentences using the defined senses. We describe a supervised TSD algorithm trained on these annotations, which outperforms a strong baseline for the task. 1 Introduction The function of syntax is to combine words to ex- press meanings, using syntactic devices such as word order, auxiliary words, and morphology (Gold- berg, 1995). Virtually all natural language devices used for expressing meanings (e.g., words) exhibit polysemy. Like words, concrete syntactic forms (the sentence words generated by specific syntactic de- vices) can have several meanings. Consider the fol- lowing sentences: (a) They are playing chess in the park. (b) They are playing chess next Tuesday. Both contain the concrete syntactic form ‘are play- ing’, generated by the abstract syntactic form usu- ally known as ‘present progressive’ (am/is/are + V- ing). In (a), the meaning is ‘something happening now’, while in (b) it is ‘a plan to do something in the future’. Note that the polysemy is of the syntactic form as a unit, not of individual words. In particu- lar, the verb ‘play’ is used in the same sense in both cases. In this paper we address a prominent type of syn- tactic form polysemy: the multiple possible senses that tense syntactic forms can have. Disambiguat- ing the polysemy of tense forms is of theoretical and practical importance (Section 2). To make our discussion concrete, we introduce the task of Tense Sense Disambiguation (TSD): given a concrete tense syntactic form in a sentence, select its correct sense among a given set of possible senses (Section 3). The disambiguation of polysemy is a fundamental problem in NLP. For example, Word Sense Disam- biguation (WSD) continues to attract a large number of researchers (Agirre and Edmonds, 2006). TSD has the same structure as WSD, with different dis- ambiguated entities. For experimenting with the TSD task, we com- piled an English syntactic sense dictionary based on a thorough study of three major English gram- mar projects (Section 4). We selected 3000 sen- tences from the …

Content truncated to 500 words

Labeled Text

Polysemy is a major characteristic of natural languages. Like words, syntactic forms can have several meanings. Understanding the correct meaning of a syntactic form is of great importance to many NLP applications. In this paper we address an important type of syntactic polysemy – the multiple possible senses of tense syntactic forms. We make our discussion concrete by introducing the task of Tense Sense Disambiguation (TSD): given a concrete tense syntactic form present in a sentence, select its appropriate sense among a set of possible senses. Using English grammar textbooks, we compiled a syntactic sense dictionary comprising common tense syntactic forms and semantic senses for each. We annotated thousands of BNC sentences using the defined senses. We describe a supervised TSD algorithm trained on these annotations, which outperforms a strong baseline for the task. 1

Publication Details

Paper ID:
44579
Year:
2010
Publication:
TIPSTER
Publication Type:
conf
DOI:
nan