Automated induction of sense in context

Pustejovsky, James; Hanks, Patrick; Rumshisky, Anna

doi:10.3115/1220355.1220488

Cited by 30 publications

(15 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PDEV has been studied from different NLP perspectives, all mainly involved with Word Sense Disambiguation and semantic analysis (Cinková et al, 2012a;Holub et al, 2012;El Maarouf and Baisa, 2013;Kawahara et al, ;Popescu, 2013;Pustejovsky et al, 2004;. For example, (Popescu, 2013) described experiments in modeling finite state automata on a set of 721 verbs taken from PDEV.…”

Section: Corpus Pattern Analysismentioning

confidence: 99%

SemEval-2015 Task 15: A CPA dictionary-entry-building task

Baisa

Bradbury

Cinková

et al. 2015

Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)

View full text Add to dashboard Cite

This paper describes the first SemEval task to explore the use of Natural Language Processing systems for building dictionary entries, in the framework of Corpus Pattern Analysis. CPA is a corpus-driven technique which provides tools and resources to identify and represent unambiguously the main semantic patterns in which words are used. Task 15 draws on the Pattern Dictionary of English Verbs (www.pdev.org.uk), for the targeted lexical entries, and on the British National Corpus for the input text.Dictionary entry building is split into three subtasks which all start from the same concordance sample: 1) CPA parsing, where arguments and their syntactic and semantic categories have to be identified, 2) CPA clustering, in which sentences with similar patterns have to be clustered and 3) CPA automatic lexicography where the structure of patterns have to be constructed automatically. Subtask 1 attracted 3 teams, though none could beat the baseline (rule-based system). Subtask 2 attracted 2 teams, one of which beat the baseline (majority-class classifier). Subtask 3 did not attract any participant.The task has produced a major semantic multidataset resource which includes data for 121 verbs and about 17,000 annotated sentences, and which is freely accessible.

show abstract

Section: Corpus Pattern Analysismentioning

confidence: 99%

SemEval-2015 Task 15: A CPA dictionary-entry-building task

Baisa

Bradbury

Cinková

et al. 2015

Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)

View full text Add to dashboard Cite

show abstract

“…The patterns were stored in a MySQL database. They are partly modelled on the 'Corpus Pattern Analysis' model described in Pustejovsky et al (2004). These are syntagmatic patterns representing a selection context for the predicate they include, which determines the sense of the latter although CPA Patterns as defined by Pustejovsky et al (2004) and are in fact rather more detailed than our patterns.…”

Section: Arg1 Verb1 (Arg2) (Arg3)mentioning

confidence: 99%

“…The current work has a different agenda in that it aims to obtain semantic classes of nouns that feature as verb arguments. This information is combined to form selection contexts for verbs, similar to CPA patterns (Pustejovsky et al, 2004), which are then evaluated on the assignment of semantic types. However, whereas our patterns are obtained in a fully automated way, CPA patterns are acquired semi-automatically after the initial manual construction of core verb subcategorisation frames.…”

Section: Related Workmentioning

confidence: 99%

Automatic fine-grained semantic classification for domain adaptation

Liakata

Pulman

2008

Proceedings of the 2008 Conference on Semantics in Text Processing - STEP '08

View full text Add to dashboard Cite

Assigning arguments of verbs to different semantic classes ('semantic typing'), or alternatively, checking the 'selectional restrictions' of predicates, is a fundamental component of many natural language processing tasks. However, a common experience has been that general purpose semantic classes, such as those encoded in resources like WordNet, or handcrafted subject-specific ontologies, are seldom quite right when it comes to analysing texts from a particular domain. In this paper we describe a method of automatically deriving fine-grained, domain-specific semantic classes of arguments while simultaneously clustering verbs into semantically meaningful groups: the first step in verb sense induction. We show that in a small pilot study on new examples from the same domain we are able to achieve almost perfect recall and reasonably high precision in the semantic typing of verb arguments in these texts.

show abstract

“…Corpus Pattern Analysis (CPA) (Hanks and Pustejovsky, 2005;Pustejovsky et al, 2004) attempts to catalog prototypical norms of usage for individual words, specifying them in terms of context patterns. As a corpus analysis technique, CPA has its origins in the analysis of large corpora for lexicographic purposes, of the kind that was used for compiling the Cobuild dictionary (Sinclair and Hanks, 1987).…”

Section: Defining a Sense Inventorymentioning

confidence: 99%

“…A set of senses was created for each verb using a modification of the CPA technique (Pustejovsky et al, 2004). A set of complements was examined in the Sketch Engine.…”

Section: Data Setmentioning

confidence: 99%

Proceedings of the Workshop on Human Judgements in Computational Linguistics - HumanJudge '08

2008

View full text Add to dashboard Cite

Supervised word sense disambiguation requires training corpora that have been tagged with word senses, and these word senses typically come from a pre-existing sense inventory. Space limitations imposed by dictionary publishers have biased the field towards lists of discrete senses for an individual lexeme. Although some dictionaries use hierarchical entries to emphasize relations between senses, many do not. WordNet, which has been the default choice of NLP researchers for sense tagging because of its broad coverage and easy accibility, does not have hierarchical entries. Could the relations between senses that are captured by a hierarchy be useful to NLP systems? Concerns have also been raised about whether or not WordNet's word senses are unnecessarily fine-grained. WSD systems are obviously more successful in distinguishing coarse-grained senses than fine-grained ones (Navigli, 2006), but important information could be lost if fine-grained distinctions are ignored. Recent psycholinguistic evidence seems to indicate that closely related word senses may be represented in the mental lexicon much like a single sense, whereas distantly related senses may be represented more like discrete entities (Brown, 2008). These results suggest that, for the purposes of WSD, closely related word senses can be clustered together into a more general sense with little meaning loss. This talk will describe this psycholinguistic research and its current implications for automatic word sense disambiguation, as well as plans for future research and its possible impact.

show abstract

Automated induction of sense in context

Cited by 30 publications

References 27 publications

SemEval-2015 Task 15: A CPA dictionary-entry-building task

SemEval-2015 Task 15: A CPA dictionary-entry-building task

Automatic fine-grained semantic classification for domain adaptation

Proceedings of the Workshop on Human Judgements in Computational Linguistics - HumanJudge '08

Contact Info

Product

Resources

About