Comparing Probabilistic, Distributional and Transformer-Based Models on Logical Metonymy Interpretation

Giulia Rambelli, Emmanuele Chersoni, Alessandro Lenci, Philippe Blache, Chu-ren Huang

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

Abstract

In linguistics and cognitive science, Logical metonymies are defined as type clashes between an event-selecting verb and an entity-denoting noun (e.g. The editor finished the article), which are typically interpreted by inferring a hidden event (e.g. reading) on the basis of contextual cues. This paper tackles the problem of logical metonymy interpretation, that is, the retrieval of the covert event via computational methods. We compare different types of models, including the probabilistic and the distributional ones previously introduced in the literature on the topic. For the first time, we also tested on this task some of the recent Transformer-based models, such as BERT, RoBERTa, XLNet, and GPT-2. Our results show a complex scenario, in which the best Transformer-based models and some traditional distributional models perform very similarly. However, the low performance on some of the testing datasets suggests that logical metonymy is still a challenging phenomenon for computational modeling.
Original languageEnglish
Title of host publicationProceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing
EditorsKam-Fai Wong, Kevin Knight, Hua Wu
PublisherAssociation for Computational Linguistics (ACL)
Pages224–234
ISBN (Electronic)978-1-952148-91-0
Publication statusPublished - Dec 2020
Event 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing - Online
Duration: 4 Dec 20207 Dec 2020
http://aacl2020.org/

Conference

Conference 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing
Abbreviated titleAACL-ICJNLP
Period4/12/207/12/20
Internet address

Fingerprint

Dive into the research topics of 'Comparing Probabilistic, Distributional and Transformer-Based Models on Logical Metonymy Interpretation'. Together they form a unique fingerprint.

Cite this