Unified Semantic Typing with Meaningful Label Inference

James Y. Huang, Bangzheng Li, Jiashu Xu, Muhao Chen


Abstract
Semantic typing aims at classifying tokens or spans of interest in a textual context into semantic categories such as relations, entity types, and event types. The inferred labels of semantic categories meaningfully interpret how machines understand components of text. In this paper, we present UniST, a unified framework for semantic typing that captures label semantics by projecting both inputs and labels into a joint semantic embedding space. To formulate different lexical and relational semantic typing tasks as a unified task, we incorporate task descriptions to be jointly encoded with the input, allowing UniST to be adapted to different tasks without introducing task-specific model components. UniST optimizes a margin ranking loss such that the semantic relatedness of the input and labels is reflected from their embedding similarity. Our experiments demonstrate that UniST achieves strong performance across three semantic typing tasks: entity typing, relation classification and event typing. Meanwhile, UniST effectively transfers semantic knowledge of labels and substantially improves generalizability on inferring rarely seen and unseen types. In addition, multiple semantic typing tasks can be jointly trained within the unified framework, leading to a single compact multi-tasking model that performs comparably to dedicated single-task models, while offering even better transferability.
Anthology ID:
2022.naacl-main.190
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2642–2654
Language:
URL:
https://aclanthology.org/2022.naacl-main.190
DOI:
10.18653/v1/2022.naacl-main.190
Bibkey:
Cite (ACL):
James Y. Huang, Bangzheng Li, Jiashu Xu, and Muhao Chen. 2022. Unified Semantic Typing with Meaningful Label Inference. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2642–2654, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Unified Semantic Typing with Meaningful Label Inference (Huang et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.190.pdf
Video:
 https://aclanthology.org/2022.naacl-main.190.mp4
Code
 luka-group/unist
Data
FewRelMAVENOpen EntitySQuADTACRED