# Robust Dialogue Utterance Rewriting as Sequence Tagging

arXiv: https://arxiv.org/abs/2012.14535 · HTML: https://mlsanity.com/paper/2012.14535/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Dec 2020.

## Built on by (most cited first, 5 of 5)

- [Hierarchical Context Tagging for Utterance Rewriting](https://mlsanity.com/paper/2206.11218/) (2022)
- [Self-Aware Feedback-Based Self-Learning in Large-Scale Conversational AI](https://mlsanity.com/paper/2205.00029/) (2022)
- [Self-Attention for Incomplete Utterance Rewriting](https://mlsanity.com/paper/2202.12160/) (2022)
- [Utterance Rewriting with Contrastive Learning in Multi-turn Dialogue](https://mlsanity.com/paper/2203.11587/) (2022)
- [Action based Network for Conversation Question Reformulation](https://mlsanity.com/paper/2111.14445/) (2021)

## Abstract (arXiv)

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.