Abstract
Semantic similarity detection is a fundamental task in natural language understanding. Adding topic information has been useful for previous feature-engineered semantic similarity models as well as neural models for other tasks. There is currently no standard way of combining topics with pretrained contextual representations such as BERT. We propose a novel topic-informed BERT-based architecture for pairwise semantic similarity detection and show that our model improves performance over strong neural baselines across a variety of English language datasets. We find that the addition of topics to BERT helps particularly with resolving domain-specific cases.- Anthology ID:
- 2020.acl-main.630
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7047–7055
- Language:
- URL:
- https://aclanthology.org/2020.acl-main.630
- DOI:
- 10.18653/v1/2020.acl-main.630
- Cite (ACL):
- Nicole Peinelt, Dong Nguyen, and Maria Liakata. 2020. tBERT: Topic Models and BERT Joining Forces for Semantic Similarity Detection. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7047–7055, Online. Association for Computational Linguistics.
- Cite (Informal):
- tBERT: Topic Models and BERT Joining Forces for Semantic Similarity Detection (Peinelt et al., ACL 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2020.acl-main.630.pdf
- Code
- wuningxi/tBERT
- Data
- 100DOH