A computational model of logical metonymy

Shutova, Ekaterina; Kaplan, Jonathan; Teufel, Simone; Korhonen, Anna

doi:10.1145/2483969.2483973

Cited by 28 publications

(8 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are many forms of metonymy (e.g., ''thing for people'' and ''thing for organization'') [2], and it often hampers the development of NLP applications such as geographical analysis [3], [4] machine translation [5], question answering [6], anaphora analysis [7], [8], and geographic information retrieval [9]. For example, we note that the user asks an intelligent navigation system: ''I am at Tokyo station now, where is the Beijing restaurant?''.…”

Section: Introductionmentioning

confidence: 99%

“…There are several issues in metonymy recognition: (1) At present, the available metonymy datasets are very few, only SemEval 2007 task 8 (SemEval) [10] and ReLocaR [1], and there is no other language version of the data set available because manual tagging of the data is extremely costly. (2) The method based on rules and knowledge base depends on the construction of appropriate handcrafted features, which is also a very hard task, and the performance of the system depends on the quality of construction handcrafted features. 3The method of metonymy recognition based on deep learning lacks the guidance of linguistic theory and has poor interpretability.…”

Section: Introductionmentioning

confidence: 99%

“…As far as we know, these Chinese data sets are the first trials we put forward in the field of metonymy recognition. (2) We propose a metonymy recognition method that introduces the theory of semantic priority interruption into the neural language model, using additional knowledge such as metonymy trigger words, location information, POS as additional features. (3) The experimental results on six data sets show that our model is comparable to the state-of-the-art approach in both the English and Chinese metonymy recognition tasks.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

English and Chinese Neural Metonymy Recognition Based on Semantic Priority Interruption Theory

Huang

Fukumoto

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Metonymy is one of the types of common figurative languages and often used in human conversation without any difficulties. However, metonymy recognition in NLP requires a deep semantic/contextual processing to interpretation because it is highly related to the discourse of the contexts. Moreover, the fact that few available datasets of figurative languages make it more problematic. Motivated by the shortcomings of metonymy recognition, we develop several new data sets, including the Chinese version of the data, and design an end-to-end neural network metonymy recognizer. Our framework is based on the semantic priority interrupt theory and additional knowledge is introduced which makes to learn contexts effectively. Through a series of experiments, we show that our method is comparable to the state-of-the-art metonymy recognition method, especially we verified that metonymy trigger words information contributes to performance improvement in our model. INDEX TERMS Metonymy recognition, neural network, semantic priority interrupt theory.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

English and Chinese Neural Metonymy Recognition Based on Semantic Priority Interruption Theory

Huang

Fukumoto

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…", London refers to the concept of "people" and should not be classified as a location. There are many types of metonymy (Shutova et al, 2013), however, in this paper, we primarily address metonymic location mentions with reference to GP and NER.…”

Section: Introductionmentioning

confidence: 99%

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

“…Parsing is performed using the Spacy module for Python 4. Word sense ambiguity in semantic type coercion is addressed in depth byShutova et al (2013).…”

mentioning

confidence: 99%

Proceedings of the 13th International Conference on Computational Semantics - Short Papers

2019

View full text Add to dashboard Cite

We explore a novel application for interpreting semantic type coercions, motivated by insight into the role that perceptual affordances play in the selection of artefactual nouns that are observed as arguments for verbs that would stereotypically select for objects of a different type. In order to simulate affordances, which we take to be direct perceptions of context-specific opportunities for action, we perform a distributional analysis of dependency relationships between target words and their modifiers and adjuncts. We propose a novel methodology that uses these relationships as the basis for generating on-line transformations projecting semantic subspaces in which the interpretations of coercive compositions are expected to emerge as salient word-vectors. We offer some preliminary examples of how this model operates on phrases involving coercive verb-object interactions. sell create sell sell order take take drink take take produce milk produce produce take give give take give drink produce include produce give take take take give take take drink serve get give take give give finish serve get get buy order eat eat eat include eat order sandwich serve sell create get sell include take offer get give serve offer take take eat give eat give cake eat eat create take take take win produce take include give produce win create create include create create dessert serve produce eat call eat produce eat prepare play play call include take wear wear include wear produce glass produce take read give take take read produce drink take give give take take drink give take produce bottle finish produce take take give give produce drink give find keep take build take drive take take build

show abstract

A computational model of logical metonymy

Cited by 28 publications

References 43 publications

English and Chinese Neural Metonymy Recognition Based on Semantic Priority Interruption Theory

English and Chinese Neural Metonymy Recognition Based on Semantic Priority Interruption Theory

Vancouver Welcomes You! Minimalist Location Metonymy Resolution

Proceedings of the 13th International Conference on Computational Semantics - Short Papers

Contact Info

Product

Resources

About