Research Area:  Machine Learning
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.
Author(s) Name:  Nicole Peinelt, Dong Nguyen, Maria Liakata
Conferrence name:  Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Publisher name:  ACL
Volume Information:  Pages: 7047–7055,2020
Paper Link:   https://aclanthology.org/2020.acl-main.630/