Open-Domain Contextual Link Prediction and its Complementarity with Entailment Graphs
Mohammad Javad Hosseini, Shay B. Cohen, Mark Johnson, Mark Steedman
Abstract
An open-domain knowledge graph (KG) has entities as nodes and natural language relations as edges, and is constructed by extracting (subject, relation, object) triples from text. The task of open-domain link prediction is to infer missing relations in the KG. Previous work has used standard link prediction for the task. Since triples are extracted from text, we can ground them in the larger textual context in which they were originally found. However, standard link prediction methods only rely on the KG structure and ignore the textual context that each triple was extracted from. In this paper, we introduce the new task of open-domain contextual link prediction which has access to both the textual context and the KG structure to perform link prediction. We build a dataset for the task and propose a model for it. Our experiments show that context is crucial in predicting missing relations. We also demonstrate the utility of contextual link prediction in discovering context-independent entailments between relations, in the form of entailment graphs (EG), in which the nodes are the relations. The reverse holds too: context-independent EGs assist in predicting relations in context.- Anthology ID:
- 2021.findings-emnlp.238
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2021
- Month:
- November
- Year:
- 2021
- Address:
- Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- Findings
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2790–2802
- Language:
- URL:
- https://aclanthology.org/2021.findings-emnlp.238
- DOI:
- 10.18653/v1/2021.findings-emnlp.238
- Cite (ACL):
- Mohammad Javad Hosseini, Shay B. Cohen, Mark Johnson, and Mark Steedman. 2021. Open-Domain Contextual Link Prediction and its Complementarity with Entailment Graphs. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2790–2802, Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Open-Domain Contextual Link Prediction and its Complementarity with Entailment Graphs (Hosseini et al., Findings 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/2021.findings-emnlp.238.pdf
- Code
- mjhosseini/open_contextual_link_pred
- Data
- FIGER