Abstract
Open Information Extraction (OpenIE) facilitates the open-domain discovery of textual facts. However, the prevailing solutions evaluate OpenIE models on in-domain test sets aside from the training corpus, which certainly violates the initial task principle of domain-independence. In this paper, we propose to advance OpenIE towards a more realistic scenario: generalizing over unseen target domains with different data distributions from the source training domains, termed Generalized OpenIE. For this purpose, we first introduce GLOBE, a large-scale human-annotated multi-domain OpenIE benchmark, to examine the robustness of recent OpenIE models to domain shifts, and the relative performance degradation of up to 70% implies the challenges of generalized OpenIE. Then, we propose DragonIE, which explores a minimalist expression of textual fact: directed acyclic graph, to improve the OpenIE generalization ability. Extensive experiments demonstrate that DragonIE beats the previous methods in both in-domain and out-of-domain settings by as much as 6.0% in F1 score absolutely, but there is still ample room for improvement.- Anthology ID:
- 2022.findings-emnlp.103
- 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:
- 1439–1453
- Language:
- URL:
- https://aclanthology.org/2022.findings-emnlp.103
- DOI:
- Cite (ACL):
- 2022. Towards Generalized Open Information Extraction. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 1439–1453, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Towards Generalized Open Information Extraction (, Findings 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.findings-emnlp.103.pdf