Abstract
Rationale-based models provide a unique way to provide justifiable results for relation classification models by identifying rationales (key words and phrases that a person can use to justify the relation in the sentence) during the process. However, existing generative networks used to extract rationales come with a trade-off between extracting diversified rationales and achieving good classification results. In this paper, we propose a multilevel heuristic approach to regulate rationale extraction to avoid extracting monotonous rationales without compromising classification performance. In our model, rationale selection is regularized by a semi-supervised process and features from different levels: word, syntax, sentence, and corpus. We evaluate our approach on the SemEval 2010 dataset that includes 19 relation classes and the quality of extracted rationales with our manually-labeled rationales. Experiments show a significant improvement in classification performance and a 20% gain in rationale interpretability compared to state-of-the-art approaches.- Anthology ID:
- C18-1098
- Volume:
- Proceedings of the 27th International Conference on Computational Linguistics
- Month:
- August
- Year:
- 2018
- Address:
- Santa Fe, New Mexico, USA
- Editors:
- Emily M. Bender, Leon Derczynski, Pierre Isabelle
- Venue:
- COLING
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1145–1155
- Language:
- URL:
- https://aclanthology.org/C18-1098
- DOI:
- Cite (ACL):
- Shiou Tian Hsu, Mandar Chaudhary, and Nagiza Samatova. 2018. Multilevel Heuristics for Rationale-Based Entity Relation Classification in Sentences. In Proceedings of the 27th International Conference on Computational Linguistics, pages 1145–1155, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
- Cite (Informal):
- Multilevel Heuristics for Rationale-Based Entity Relation Classification in Sentences (Hsu et al., COLING 2018)
- PDF:
- https://preview.aclanthology.org/naacl24-info/C18-1098.pdf
- Data
- SemEval-2010 Task-8