Abstract
Open rules refer to the implication from premise atoms to hypothesis atoms, which captures various relationships between instances in the real world. Injecting open rule knowledge into the machine helps to improve the performance of downstream tasks such as dialogue and relation extraction. Existing approaches focus on single-hop open rule generation, ignoring scenarios involving multiple hops, leading to logical inconsistencies between premise and hypothesis atoms, as well as semantic duplication of generated rule atoms. To address these issues, we propose a progressive multi-stage open rule generation method called PRIMO. We introduce ontology information during the rule generation stage to reduce ambiguity and improve rule accuracy. PRIMO constructs a multi-stage structure consisting of generation, extraction, and rank modules to fully leverage the latent knowledge within the language model across multiple dimensions. Furthermore, we employ reinforcement learning from human feedback to further optimize model, enhancing the model’s understanding of commonsense knowledge. Experimental results demonstrate that compared to baseline models, PRIMO significantly enhances rule quality and diversity while reducing the repetition rate of rule atoms.- Anthology ID:
- 2024.lrec-main.1137
- Volume:
- Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
- Month:
- May
- Year:
- 2024
- Address:
- Torino, Italia
- Editors:
- Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
- Venues:
- LREC | COLING
- SIG:
- Publisher:
- ELRA and ICCL
- Note:
- Pages:
- 12988–12998
- Language:
- URL:
- https://aclanthology.org/2024.lrec-main.1137
- DOI:
- Cite (ACL):
- Jianyu Liu, Sheng Bi, and Guilin Qi. 2024. PRIMO: Progressive Induction for Multi-hop Open Rule Generation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 12988–12998, Torino, Italia. ELRA and ICCL.
- Cite (Informal):
- PRIMO: Progressive Induction for Multi-hop Open Rule Generation (Liu et al., LREC-COLING 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2024.lrec-main.1137.pdf