Generating Lexical Representations of Frames using Lexical Substitution

Saba Anwar, Artem Shelmanov, Alexander Panchenko, Chris Biemann


Abstract
Semantic frames are formal linguistic structures describing situations/actions/events, e.g. Commercial transfer of goods. Each frame provides a set of roles corresponding to the situation participants, e.g. Buyer and Goods, and lexical units (LUs) – words and phrases that can evoke this particular frame in texts, e.g. Sell. The scarcity of annotated resources hinders wider adoption of frame semantics across languages and domains. We investigate a simple yet effective method, lexical substitution with word representation models, to automatically expand a small set of frame-annotated sentences with new words for their respective roles and LUs. We evaluate the expansion quality using FrameNet. Contextualized models demonstrate overall superior performance compared to the non-contextualized ones on roles. However, the latter show comparable performance on the task of LU expansion.
Anthology ID:
2020.pam-1.13
Volume:
Proceedings of the Probability and Meaning Conference (PaM 2020)
Month:
June
Year:
2020
Address:
Gothenburg
Editors:
Christine Howes, Stergios Chatzikyriakidis, Adam Ek, Vidya Somashekarappa
Venue:
PaM
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
95–103
Language:
URL:
https://aclanthology.org/2020.pam-1.13
DOI:
Bibkey:
Cite (ACL):
Saba Anwar, Artem Shelmanov, Alexander Panchenko, and Chris Biemann. 2020. Generating Lexical Representations of Frames using Lexical Substitution. In Proceedings of the Probability and Meaning Conference (PaM 2020), pages 95–103, Gothenburg. Association for Computational Linguistics.
Cite (Informal):
Generating Lexical Representations of Frames using Lexical Substitution (Anwar et al., PaM 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.pam-1.13.pdf
Data
FrameNet