Abstract
We introduce a new open information extraction (OIE) benchmark for pre-trained language models (LM). Recent studies have demonstrated that pre-trained LMs, such as BERT and GPT, may store linguistic and relational knowledge. In particular, LMs are able to answer “fill-in-the-blank” questions when given a pre-defined relation category. Instead of focusing on pre-defined relations, we create an OIE benchmark aiming to fully examine the open relational information present in the pre-trained LMs. We accomplish this by turning pre-trained LMs into zero-shot OIE systems. Surprisingly, pre-trained LMs are able to obtain competitive performance on both standard OIE datasets (CaRB and Re-OIE2016) and two new large-scale factual OIE datasets (TAC KBP-OIE and Wikidata-OIE) that we establish via distant supervision. For instance, the zero-shot pre-trained LMs outperform the F1 score of the state-of-the-art supervised OIE methods on our factual OIE datasets without needing to use any training sets.- Anthology ID:
- 2022.emnlp-main.576
- Volume:
- Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Editors:
- Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 8417–8437
- Language:
- URL:
- https://aclanthology.org/2022.emnlp-main.576
- DOI:
- 10.18653/v1/2022.emnlp-main.576
- Cite (ACL):
- Chenguang Wang, Xiao Liu, and Dawn Song. 2022. IELM: An Open Information Extraction Benchmark for Pre-Trained Language Models. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 8417–8437, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- IELM: An Open Information Extraction Benchmark for Pre-Trained Language Models (Wang et al., EMNLP 2022)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2022.emnlp-main.576.pdf