Injecting Domain Knowledge in Language Models for Task-oriented Dialogue Systems
Denis Emelin, Daniele Bonadiman, Sawsan Alqahtani, Yi Zhang, Saab Mansour · 2022
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 1 on KPRS and the response generation task show improvements of knowledge injection with adapters over strong baselines. * Work performed while at AWS AI Labs 1 https://github.com/amazon-research/ domain-knowledge-injection