Timeline-based Sentence Decomposition with In Context Learning for Temporal Fact Extraction
Jianhao Chen, Haoyuan Ouyang, Junyang Ren, Wentao Ding, Wei Hu, Yuzhong Qu
Abstract
Facts extraction is pivotal for constructing knowledge graphs. Recently, the increasing demand for temporal facts in downstream tasks has led to the emergence of the task of temporal fact extraction. In this paper, we specifically address the extraction of temporal facts from natural language text. Previous studies fail to handle the challenge of establishing time-to-fact correspondences in complex sentences. To overcome this hurdle, we propose a timeline-based sentence decomposition strategy using large language models (LLMs) with in-context learning, ensuring a fine-grained understanding of the timeline associated with various facts. In addition, we evaluate the performance of LLMs for direct temporal fact extraction and get unsatisfactory results. To this end, we introduce TSDRE, a method that incorporates the decomposition capabilities of LLMs into the traditional fine-tuning of smaller pre-trained language models (PLMs). To support the evaluation, we construct ComplexTRED, a complex temporal fact extraction dataset. Our experiments show that TSDRE achieves state-of-the-art results on both HyperRED-Temporal and ComplexTRED datasets.- Anthology ID:
- 2024.acl-long.187
- Volume:
- Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3415–3432
- Language:
- URL:
- https://aclanthology.org/2024.acl-long.187
- DOI:
- Cite (ACL):
- Jianhao Chen, Haoyuan Ouyang, Junyang Ren, Wentao Ding, Wei Hu, and Yuzhong Qu. 2024. Timeline-based Sentence Decomposition with In Context Learning for Temporal Fact Extraction. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3415–3432, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- Timeline-based Sentence Decomposition with In Context Learning for Temporal Fact Extraction (Chen et al., ACL 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.acl-long.187.pdf