Syntactic features and word similarity for supervised metonymy resolution

Nissim, Malvina; Markert, Katja

doi:10.3115/1075096.1075104

Cited by 31 publications

(54 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Along with theoretical work, there have been a number of computational accounts of general [Utiyama et al 2000;Markert and Nissim 2002;Nissim and Markert 2003;Peirsman 2006;Agirre et al 2007] and logical [Lapata and Lascarides 2003] metonymy. All of these approaches are data-driven.…”

Section: Previous Computational Approachesmentioning

confidence: 99%

A computational model of logical metonymy

Shutova

Kaplan

Teufel

et al. 2013

ACM Trans. Speech Lang. Process.

View full text Add to dashboard Cite

The use of figurative language is ubiquitous in natural language texts and it is a serious bottleneck in automatic text understanding. A system capable of interpreting figurative expressions would be an invaluable addition to the real-world natural language processing (NLP) applications that need to access semantics, such as machine translation, opinion mining, question answering and many others. In this article we focus on one type of figurative language, logical metonymy, and present a computational model of its interpretation bringing together statistical techniques and the insights from linguistic theory. Compared to previous approaches this model is both more informative and more accurate. The system produces sense-level interpretations of metonymic phrases and then automatically organizes them into conceptual classes, or roles, discussed in the majority of linguistic literature on the phenomenon.

show abstract

Section: Previous Computational Approachesmentioning

confidence: 99%

A computational model of logical metonymy

Shutova

Kaplan

Teufel

et al. 2013

ACM Trans. Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…Our main standard for performance evaluation is the SemEval 2007 Shared Task 8 (Markert and Nissim, 2007) dataset first introduced in Nissim and Markert (2003b). Two types of entities were evaluated, organisations and locations, randomly retrieved from the British National Corpus (BNC).…”

Section: Semeval 2007 Datasetmentioning

confidence: 99%

“…Some of the earliest work on MR that used an approach similar to our method (machine learning and dependency parsing) was by Nissim and Markert (2003a). The decision list classifier with backoff was evaluated using syntactic head-modifier relations, grammatical roles and a thesaurus to overcome data sparseness and generalisation problems.…”

Section: Related Workmentioning

confidence: 99%

“…The feature set of Nissim and Markert (2003a) was updated to include: grammatical role of the potentially metonymic word (PMW) (such as subj, obj), lemmatised head/modifier of PMW, determiner of PMW, grammatical number of PMW (singular, plural), number of words in PMW and number of grammatical roles of PMW in current context. The winning system by Farkas et al (2007) used these features and a maximum entropy classifier to achieve 85.2% accuracy.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Vancouver Welcomes You! Minimalist Location Metonymy Resolution

Gritta¹,

Pilehvar²,

Limsopatham³

et al. 2017

Proceedings of the 55th Annual Meeting of the Association For Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

Named entities are frequently used in a metonymic manner. They serve as references to related entities such as people and organisations. Accurate identification and interpretation of metonymy can be directly beneficial to various NLP applications, such as Named Entity Recognition and Geographical Parsing. Until now, metonymy resolution (MR) methods mainly relied on parsers, taggers, dictionaries, external word lists and other handcrafted lexical resources. We show how a minimalist neural approach combined with a novel predicate window method can achieve competitive results on the SemEval 2007 task on Metonymy Resolution. Additionally, we contribute with a new Wikipedia-based MR dataset called RelocaR, which is tailored towards locations as well as improving previous deficiencies in annotation guidelines.

show abstract

“…al., 2000;Nissim & Markert, 2003;Mason, 2004). Nissim & Markert (2003) approach metonymy resolution with machine learning methods, "which [exploit] the similarity between examples of conventional metonymy" ( (Nissim & Markert, 2003), p. 56). They see metonymy resolution as a classification problem between the literal use of a word and a number of pre-defined metonymy types.…”

Section: Previous Workmentioning

confidence: 99%

Active learning for the identification of nonliteral language

Birke

Sarkar

2007

Proceedings of the Workshop on Computational Approaches to Figurative Language - FigLanguages '07

View full text Add to dashboard Cite

In this paper we present an active learning approach used to create an annotated corpus of literal and nonliteral usages of verbs. The model uses nearly unsupervised word-sense disambiguation and clustering techniques. We report on experiments in which a human expert is asked to correct system predictions in different stages of learning: (i) after the last iteration when the clustering step has converged, or (ii) during each iteration of the clustering algorithm. The model obtains an f-score of 53.8% on a dataset in which literal/nonliteral usages of 25 verbs were annotated by human experts. In comparison, the same model augmented with active learning obtains 64.91%. We also measure the number of examples required when model confidence is used to select examples for human correction as compared to random selection. The results of this active learning system have been compiled into a freely available annotated corpus of literal/nonliteral usage of verbs in context.

show abstract

Syntactic features and word similarity for supervised metonymy resolution

Cited by 31 publications

References 18 publications

A computational model of logical metonymy

A computational model of logical metonymy

Vancouver Welcomes You! Minimalist Location Metonymy Resolution

Active learning for the identification of nonliteral language

Contact Info

Product

Resources

About