Abstract
Relation schemas are often pre-defined for each relation dataset. Relation types can be related from different datasets and have overlapping semantics. We hypothesize we can combine these datasets according to the semantic relatedness between the relation types to overcome the problem of lack of training data. It is often easy to discover the connection between relation types based on relation names or annotation guides, but hard to measure the exact similarity and take advantage of the connection between the relation types from different datasets. We propose to use prototypical examples to represent each relation type and use these examples to augment related types from a different dataset. We obtain further improvement (ACE05) with this type augmentation over a strong baseline which uses multi-task learning between datasets to obtain better feature representation for relations. We make our implementation publicly available: https://github.com/fufrank5/relatedness- Anthology ID:
- 2021.eacl-main.172
- Volume:
- Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
- Month:
- April
- Year:
- 2021
- Address:
- Online
- Editors:
- Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2011–2016
- Language:
- URL:
- https://aclanthology.org/2021.eacl-main.172
- DOI:
- 10.18653/v1/2021.eacl-main.172
- Cite (ACL):
- Lisheng Fu and Ralph Grishman. 2021. Learning Relatedness between Types with Prototypes for Relation Extraction. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 2011–2016, Online. Association for Computational Linguistics.
- Cite (Informal):
- Learning Relatedness between Types with Prototypes for Relation Extraction (Fu & Grishman, EACL 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/2021.eacl-main.172.pdf
- Code
- fufrank5/relatedness