Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/90538
PIRA download icon_1.1View/Download Full Text
Title: Comparing probabilistic, distributional and transformer-based models on logical metonymy interpretation
Authors: Rambelli, G
Chersoni, E 
Lenci, A
Blache, P
Huang, CR 
Issue Date: Dec-2020
Source: Proceedings 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, p. 224-234
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.
Description: 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, Suzhou, China, December 4 - 7, 2020
Rights: ©2020 Association for Computational Linguistics
Posted with permission of the publisher and author.
Appears in Collections:Conference Paper

Files in This Item:
File Description SizeFormat 
2020.aacl-main.26.pdf377.81 kBAdobe PDFView/Open
Open Access Information
Status open access
File Version Version of Record
Show full item record

Page views

24
Citations as of May 22, 2022

Downloads

3
Citations as of May 22, 2022

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.