Robust Dialogue Utterance Rewriting as Sequence Tagging
This work is significant for developers of dialogue systems, as it improves the robustness of utterance rewriting models across different domains, an incremental improvement.
This paper addresses the robustness issue in dialogue utterance rewriting, where existing models perform poorly when transferring to new domains. The authors propose a sequence-tagging-based model that significantly reduces the search space and improves domain transfer performance.
The task of dialogue rewriting aims to reconstruct the latest dialogue utterance by copying the missing content from the dialogue context. Until now, the existing models for this task suffer from the robustness issue, i.e., performances drop dramatically when testing on a different domain. We address this robustness issue by proposing a novel sequence-tagging-based model so that the search space is significantly reduced, yet the core of this task is still well covered. As a common issue of most tagging models for text generation, the model's outputs may lack fluency. To alleviate this issue, we inject the loss signal from BLEU or GPT-2 under a REINFORCE framework. Experiments show huge improvements of our model over the current state-of-the-art systems on domain transfer.