Robust Frame-Semantic Models with Lexical Unit Trees and Negative Samples

Jacob Devasier, Yogesh Gurjar, Chengkai Li


Abstract
We present novel advancements in frame-semantic parsing, specifically focusing on target identification and frame identification. Our target identification model employs a novel prefix tree modification to enable robust support for multi-word lexical units, resulting in a coverage of 99.4% of the targets in the FrameNet 1.7 fulltext annotations. It utilizes a RoBERTa-based filter to achieve an F1 score of 0.775, surpassing the previous state-of-the-art solution by +0.012. For frame identification, we introduce a modification to the standard multiple-choice classification paradigm by incorporating additional negative frames for targets with limited candidate frames, resulting in a +0.014 accuracy improvement over the frame-only model of FIDO, the previous state-of-the-art system, and +0.002 over its full system. Our approach significantly enhances performance on rare frames, exhibiting an improvement of +0.044 over FIDO’s accuracy on frames with 5 or fewer samples, and on under-utilized frames, with an improvement of +0.139 on targets with a single candidate frame. Overall, our contributions address critical challenges and advance the state-of-the-art in frame-semantic parsing.
Anthology ID:
2024.acl-long.374
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6930–6941
Language:
URL:
https://aclanthology.org/2024.acl-long.374
DOI:
10.18653/v1/2024.acl-long.374
Bibkey:
Cite (ACL):
Jacob Devasier, Yogesh Gurjar, and Chengkai Li. 2024. Robust Frame-Semantic Models with Lexical Unit Trees and Negative Samples. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6930–6941, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Robust Frame-Semantic Models with Lexical Unit Trees and Negative Samples (Devasier et al., ACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2024.acl-long.374.pdf
Video:
 https://preview.aclanthology.org/add_acl24_videos/2024.acl-long.374.mp4