Textual Entailment for Temporal Dependency Graph Parsing

Jiarui Yao, Steven Bethard, Kristin Wright-Bettner, Eli Goldner, David Harris, Guergana Savova


Abstract
We explore temporal dependency graph (TDG) parsing in the clinical domain. We leverage existing annotations on the THYME dataset to semi-automatically construct a TDG corpus. Then we propose a new natural language inference (NLI) approach to TDG parsing, and evaluate it both on general domain TDGs from wikinews and the newly constructed clinical TDG corpus. We achieve competitive performance on general domain TDGs with a much simpler model than prior work. On the clinical TDGs, our method establishes the first result of TDG parsing on clinical data with 0.79/0.88 micro/macro F1.
Anthology ID:
2023.clinicalnlp-1.25
Volume:
Proceedings of the 5th Clinical Natural Language Processing Workshop
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Tristan Naumann, Asma Ben Abacha, Steven Bethard, Kirk Roberts, Anna Rumshisky
Venue:
ClinicalNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
191–199
Language:
URL:
https://aclanthology.org/2023.clinicalnlp-1.25
DOI:
10.18653/v1/2023.clinicalnlp-1.25
Bibkey:
Cite (ACL):
Jiarui Yao, Steven Bethard, Kristin Wright-Bettner, Eli Goldner, David Harris, and Guergana Savova. 2023. Textual Entailment for Temporal Dependency Graph Parsing. In Proceedings of the 5th Clinical Natural Language Processing Workshop, pages 191–199, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Textual Entailment for Temporal Dependency Graph Parsing (Yao et al., ClinicalNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.clinicalnlp-1.25.pdf