Dialogue-oriented Pre-training
This work addresses the need for better dialogue modeling in NLP, offering a general-purpose solution that improves performance on specific dialogue tasks, though it is incremental as it builds on existing pre-training methods.
The paper tackles the gap between general pre-trained language models and dialogue tasks by proposing strategies to simulate conversation features on plain text, resulting in a dialogue-oriented pre-trained model that achieves significant and consistent improvements on multi-turn dialogue datasets.
Pre-trained language models (PrLM) has been shown powerful in enhancing a broad range of downstream tasks including various dialogue related ones. However, PrLMs are usually trained on general plain text with common language model (LM) training objectives, which cannot sufficiently capture dialogue exclusive features due to the limitation of such training setting, so that there is an immediate need to fill the gap between a specific dialogue task and the LM task. As it is unlikely to collect huge dialogue data for dialogue-oriented pre-training, in this paper, we propose three strategies to simulate the conversation features on general plain text. Our proposed method differs from existing post-training methods that it may yield a general-purpose PrLM and does not individualize to any detailed task while keeping the capability of learning dialogue related features including speaker awareness, continuity and consistency. The resulted Dialog-PrLM is fine-tuned on three public multi-turn dialogue datasets and helps achieve significant and consistent improvement over the plain PrLMs.