Abstract
Relation extraction (RE) is an important task in natural language processing which aims to annotate the relation between two given entities, which requires a deep understanding of the running text. To import model performance, existing approaches leverage syntactic information to facilitate the relation extraction process, where they mainly focus on dependencies among words while paying limited attention to other types of syntactic structure. Considering that combinatory categorial grammar (CCG) is a lexicalized grammatical formalism that carries the syntactic and semantic knowledge for text understanding, we propose an alternative solution for RE that takes advantage of CCG to detect the relation between entities. In doing so, we perform a multi-task learning process to learn from RE and auto-annotated CCG supertags, where an attention mechanism is performed over all input words to distinguish the important ones for RE with the attention weights guided by the supertag decoding process. We evaluate our model on two widely used English benchmark datasets (i.e., ACE2005EN and SemEval 2010 Task 8 datasets) for RE, where the effectiveness of our approach is demonstrated by the experimental results with our approach achieving state-of-the-art performance on both datasets.- Anthology ID:
- 2022.findings-emnlp.424
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2022
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5780–5786
- Language:
- URL:
- https://aclanthology.org/2022.findings-emnlp.424
- DOI:
- Cite (ACL):
- Yuanhe Tian and Yan Song. 2022. Combinatory Grammar Tells Underlying Relevance among Entities. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 5780–5786, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Combinatory Grammar Tells Underlying Relevance among Entities (Tian & Song, Findings 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.findings-emnlp.424.pdf