Injecting Domain Knowledge in Language Models for Task-Oriented Dialogue Systems

12/15/2022
by   Denis Emelin, et al.
0

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.

READ FULL TEXT
research
05/28/2023

Plug-and-Play Knowledge Injection for Pre-trained Language Models

Injecting external knowledge can improve the performance of pre-trained ...
research
09/06/2023

Knowledge Solver: Teaching LLMs to Search for Domain Knowledge from Knowledge Graphs

Large language models (LLMs), such as ChatGPT and GPT-4, are versatile a...
research
04/14/2021

K-PLUG: Knowledge-injected Pre-trained Language Model for Natural Language Understanding and Generation in E-Commerce

Existing pre-trained language models (PLMs) have demonstrated the effect...
research
10/15/2021

DS-TOD: Efficient Domain Specialization for Task Oriented Dialog

Recent work has shown that self-supervised dialog-specific pretraining o...
research
09/19/2023

MelodyGLM: Multi-task Pre-training for Symbolic Melody Generation

Pre-trained language models have achieved impressive results in various ...
research
05/08/2023

Augmented Large Language Models with Parametric Knowledge Guiding

Large Language Models (LLMs) have significantly advanced natural languag...
research
09/08/2023

Knowledge-tuning Large Language Models with Structured Medical Knowledge Bases for Reliable Response Generation in Chinese

Large Language Models (LLMs) have demonstrated remarkable success in div...

Please sign up or login with your details

Forgot password? Click here to reset