{"page":"4636–4659","type":"conference","year":"2023","project":[{"name":"TRR 318 - C4: TRR 318 - Subproject C4 - Metaphern als Werkzeug des Erklärens","_id":"127"}],"date_updated":"2024-07-26T13:19:53Z","doi":"10.18653/v1/2023.findings-emnlp.308","editor":[{"last_name":"Bouamor","full_name":"Bouamor, Houda","first_name":"Houda"},{"first_name":"Juan","last_name":"Pino","full_name":"Pino, Juan"},{"last_name":"Bali","full_name":"Bali, Kalika","first_name":"Kalika"}],"language":[{"iso":"eng"}],"date_created":"2024-07-26T13:09:20Z","user_id":"3900","_id":"55406","title":"Modeling Highlighting of Metaphors in Multitask Contrastive Learning Paradigms","author":[{"first_name":"Meghdut","id":"99459","full_name":"Sengupta, Meghdut","last_name":"Sengupta"},{"id":"73059","full_name":"Alshomary, Milad","last_name":"Alshomary","first_name":"Milad"},{"first_name":"Ingrid","orcid":"0000-0003-2364-9489","full_name":"Scharlau, Ingrid","id":"451","last_name":"Scharlau"},{"first_name":"Henning","last_name":"Wachsmuth","id":"3900","full_name":"Wachsmuth, Henning"}],"status":"public","citation":{"ama":"Sengupta M, Alshomary M, Scharlau I, Wachsmuth H. Modeling Highlighting of Metaphors in Multitask Contrastive Learning Paradigms. In: Bouamor H, Pino J, Bali K, eds. <i>Findings of the Association for Computational Linguistics: EMNLP 2023</i>. Association for Computational Linguistics; 2023:4636–4659. doi:<a href=\"https://doi.org/10.18653/v1/2023.findings-emnlp.308\">10.18653/v1/2023.findings-emnlp.308</a>","bibtex":"@inproceedings{Sengupta_Alshomary_Scharlau_Wachsmuth_2023, place={Singapore}, title={Modeling Highlighting of Metaphors in Multitask Contrastive Learning Paradigms}, DOI={<a href=\"https://doi.org/10.18653/v1/2023.findings-emnlp.308\">10.18653/v1/2023.findings-emnlp.308</a>}, booktitle={Findings of the Association for Computational Linguistics: EMNLP 2023}, publisher={Association for Computational Linguistics}, author={Sengupta, Meghdut and Alshomary, Milad and Scharlau, Ingrid and Wachsmuth, Henning}, editor={Bouamor, Houda and Pino, Juan and Bali, Kalika}, year={2023}, pages={4636–4659} }","short":"M. Sengupta, M. Alshomary, I. Scharlau, H. Wachsmuth, in: H. Bouamor, J. Pino, K. Bali (Eds.), Findings of the Association for Computational Linguistics: EMNLP 2023, Association for Computational Linguistics, Singapore, 2023, pp. 4636–4659.","ieee":"M. Sengupta, M. Alshomary, I. Scharlau, and H. Wachsmuth, “Modeling Highlighting of Metaphors in Multitask Contrastive Learning Paradigms,” in <i>Findings of the Association for Computational Linguistics: EMNLP 2023</i>, 2023, pp. 4636–4659, doi: <a href=\"https://doi.org/10.18653/v1/2023.findings-emnlp.308\">10.18653/v1/2023.findings-emnlp.308</a>.","apa":"Sengupta, M., Alshomary, M., Scharlau, I., &#38; Wachsmuth, H. (2023). Modeling Highlighting of Metaphors in Multitask Contrastive Learning Paradigms. In H. Bouamor, J. Pino, &#38; K. Bali (Eds.), <i>Findings of the Association for Computational Linguistics: EMNLP 2023</i> (pp. 4636–4659). Association for Computational Linguistics. <a href=\"https://doi.org/10.18653/v1/2023.findings-emnlp.308\">https://doi.org/10.18653/v1/2023.findings-emnlp.308</a>","chicago":"Sengupta, Meghdut, Milad Alshomary, Ingrid Scharlau, and Henning Wachsmuth. “Modeling Highlighting of Metaphors in Multitask Contrastive Learning Paradigms.” In <i>Findings of the Association for Computational Linguistics: EMNLP 2023</i>, edited by Houda Bouamor, Juan Pino, and Kalika Bali, 4636–4659. Singapore: Association for Computational Linguistics, 2023. <a href=\"https://doi.org/10.18653/v1/2023.findings-emnlp.308\">https://doi.org/10.18653/v1/2023.findings-emnlp.308</a>.","mla":"Sengupta, Meghdut, et al. “Modeling Highlighting of Metaphors in Multitask Contrastive Learning Paradigms.” <i>Findings of the Association for Computational Linguistics: EMNLP 2023</i>, edited by Houda Bouamor et al., Association for Computational Linguistics, 2023, pp. 4636–4659, doi:<a href=\"https://doi.org/10.18653/v1/2023.findings-emnlp.308\">10.18653/v1/2023.findings-emnlp.308</a>."},"publisher":"Association for Computational Linguistics","department":[{"_id":"600"},{"_id":"660"}],"place":"Singapore","publication":"Findings of the Association for Computational Linguistics: EMNLP 2023","abstract":[{"text":"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.","lang":"eng"}]}