Details
| Original language | English |
|---|---|
| Title of host publication | Findings of the Association for Computational Linguistics |
| Subtitle of host publication | EMNLP 2023 |
| Place of Publication | Singapore |
| Pages | 4636–4659 |
| Number of pages | 24 |
| ISBN (electronic) | 9798891760615 |
| Publication status | Published - Dec 2023 |
Abstract
Metaphorical language, such as “spending time together”, projects meaning from a source domain (here, money) to a target domain (time). Thereby, it highlights certain aspects of the target domain, such as the effort behind the time investment. Highlighting aspects with metaphors (while hiding others) bridges the two domains and is the core of metaphorical meaning construction. For metaphor interpretation, linguistic theories stress that identifying the highlighted aspects is important for a better understanding of metaphors. However, metaphor research in NLP has not yet dealt with the phenomenon of highlighting. In this paper, we introduce the task of identifying the main aspect highlighted in a metaphorical sentence. Given the inherent interaction of source domains and highlighted aspects, we propose two multitask approaches - a joint learning approach and a continual learning approach - based on a finetuned contrastive learning model to jointly predict highlighted aspects and source domains. We further investigate whether (predicted) information about a source domain leads to better performance in predicting the highlighted aspects, and vice versa. Our experiments on an existing corpus suggest that, with the corresponding information, the performance to predict the other improves in terms of model accuracy in predicting highlighted aspects and source domains notably compared to the single-task baselines.
ASJC Scopus subject areas
- Computer Science(all)
- Information Systems
- Arts and Humanities(all)
- Language and Linguistics
- Computer Science(all)
- Computer Science Applications
- Computer Science(all)
- Computational Theory and Mathematics
- Social Sciences(all)
- Linguistics and Language
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Findings of the Association for Computational Linguistics: EMNLP 2023. Singapore, 2023. p. 4636–4659.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Modeling Highlighting of Metaphors in Multitask Contrastive Learning Paradigms
AU - Sengupta, Meghdut
N1 - Funding Information: This work has been supported by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under project number TRR 318/1 2021 – 438445824. We thank the anonymous reviewers for their helpful feedback.
PY - 2023/12
Y1 - 2023/12
N2 - Metaphorical language, such as “spending time together”, projects meaning from a source domain (here, money) to a target domain (time). Thereby, it highlights certain aspects of the target domain, such as the effort behind the time investment. Highlighting aspects with metaphors (while hiding others) bridges the two domains and is the core of metaphorical meaning construction. For metaphor interpretation, linguistic theories stress that identifying the highlighted aspects is important for a better understanding of metaphors. However, metaphor research in NLP has not yet dealt with the phenomenon of highlighting. In this paper, we introduce the task of identifying the main aspect highlighted in a metaphorical sentence. Given the inherent interaction of source domains and highlighted aspects, we propose two multitask approaches - a joint learning approach and a continual learning approach - based on a finetuned contrastive learning model to jointly predict highlighted aspects and source domains. We further investigate whether (predicted) information about a source domain leads to better performance in predicting the highlighted aspects, and vice versa. Our experiments on an existing corpus suggest that, with the corresponding information, the performance to predict the other improves in terms of model accuracy in predicting highlighted aspects and source domains notably compared to the single-task baselines.
AB - Metaphorical language, such as “spending time together”, projects meaning from a source domain (here, money) to a target domain (time). Thereby, it highlights certain aspects of the target domain, such as the effort behind the time investment. Highlighting aspects with metaphors (while hiding others) bridges the two domains and is the core of metaphorical meaning construction. For metaphor interpretation, linguistic theories stress that identifying the highlighted aspects is important for a better understanding of metaphors. However, metaphor research in NLP has not yet dealt with the phenomenon of highlighting. In this paper, we introduce the task of identifying the main aspect highlighted in a metaphorical sentence. Given the inherent interaction of source domains and highlighted aspects, we propose two multitask approaches - a joint learning approach and a continual learning approach - based on a finetuned contrastive learning model to jointly predict highlighted aspects and source domains. We further investigate whether (predicted) information about a source domain leads to better performance in predicting the highlighted aspects, and vice versa. Our experiments on an existing corpus suggest that, with the corresponding information, the performance to predict the other improves in terms of model accuracy in predicting highlighted aspects and source domains notably compared to the single-task baselines.
UR - http://www.scopus.com/inward/record.url?scp=85183291046&partnerID=8YFLogxK
M3 - Conference contribution
SP - 4636
EP - 4659
BT - Findings of the Association for Computational Linguistics
CY - Singapore
ER -