Injecting Domain Knowledge in Language Models for Task-oriented Dialogue Systems
Denis Emelin, Daniele Bonadiman, Sawsan Alqahtani, Yi Zhang, Saab Mansour
Abstract
Pre-trained language models (PLM) have advanced the state-of-the-art across NLP applications, but lack domain-specific knowledge that does not naturally occur in pre-training data. Previous studies augmented PLMs with symbolic knowledge for different downstream NLP tasks. However, knowledge bases (KBs) utilized in these studies are usually large-scale and static, in contrast to small, domain-specific, and modifiable knowledge bases that are prominent in real-world task-oriented dialogue (TOD) systems. In this paper, we showcase the advantages of injecting domain-specific knowledge prior to fine-tuning on TOD tasks. To this end, we utilize light-weight adapters that can be easily integrated with PLMs and serve as a repository for facts learned from different KBs. To measure the efficacy of proposed knowledge injection methods, we introduce Knowledge Probing using Response Selection (KPRS) – a probe designed specifically for TOD models. Experiments on KPRS and the response generation task show improvements of knowledge injection with adapters over strong baselines.- Anthology ID:
- 2022.emnlp-main.820
- Volume:
- Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 11962–11974
- Language:
- URL:
- https://aclanthology.org/2022.emnlp-main.820
- DOI:
- Cite (ACL):
- Denis Emelin, Daniele Bonadiman, Sawsan Alqahtani, Yi Zhang, and Saab Mansour. 2022. Injecting Domain Knowledge in Language Models for Task-oriented Dialogue Systems. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11962–11974, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Injecting Domain Knowledge in Language Models for Task-oriented Dialogue Systems (Emelin et al., EMNLP 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.emnlp-main.820.pdf