# SARG: A Novel Semi Autoregressive Generator for Multi-turn Incomplete Utterance Restoration

arXiv: https://arxiv.org/abs/2008.01474 · HTML: https://mlsanity.com/paper/2008.01474/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Aug 2020.

## Built on by (most cited first, 18 of 18)

- [Holo-Dex: Teaching Dexterity with Immersive Mixed Reality](https://mlsanity.com/paper/2210.06463/) (2022)
- [Enhance Incomplete Utterance Restoration by Joint Learning Token Extraction and Text Generation](https://mlsanity.com/paper/2204.03958/) (2022)
- [Mining Clues from Incomplete Utterance: A Query-enhanced Network for Incomplete Utterance Rewriting](https://mlsanity.com/paper/2307.00866/) (2023)
- [ASR Error Correction with Constrained Decoding on Operation Prediction](https://mlsanity.com/paper/2208.04641/) (2022)
- [Hierarchical Context Tagging for Utterance Rewriting](https://mlsanity.com/paper/2206.11218/) (2022)
- [DialogUSR: Complex Dialogue Utterance Splitting and Reformulation for Multiple Intent Detection](https://mlsanity.com/paper/2210.11279/) (2022)
- [Self-Attention for Incomplete Utterance Rewriting](https://mlsanity.com/paper/2202.12160/) (2022)
- [Incomplete Utterance Rewriting as Sequential Greedy Tagging](https://mlsanity.com/paper/2307.06337/) (2023)
- [Multi-Granularity Information Interaction Framework for Incomplete Utterance Rewriting](https://mlsanity.com/paper/2312.11945/) (2023)
- [Utterance Rewriting with Contrastive Learning in Multi-turn Dialogue](https://mlsanity.com/paper/2203.11587/) (2022)
- [Dialogue Agents 101: A Beginner's Guide to Critical Ingredients for Designing Effective Conversational Systems](https://mlsanity.com/paper/2307.07255/) (2023)
- [Incomplete Utterance Rewriting with Editing Operation Guidance and Utterance Augmentation](https://mlsanity.com/paper/2503.16043/) (2025)
- [Zero-shot Cross-lingual Conversational Semantic Role Labeling](https://mlsanity.com/paper/2204.04914/) (2022)
- [Meeting Decision Tracker: Making Meeting Minutes with De-Contextualized Utterances](https://mlsanity.com/paper/2210.11374/) (2022)
- [Friend-training: Learning from Models of Different but Related Tasks](https://mlsanity.com/paper/2301.13683/) (2023)
- [In-Context Learning with Reinforcement Learning for Incomplete Utterance Rewriting](https://mlsanity.com/paper/2408.13028/) (2024)
- [RSMLP: A light Sampled MLP Structure for Incomplete Utterance Rewrite](https://mlsanity.com/paper/2502.12587/) (2025)
- [Two-stage Incomplete Utterance Rewriting on Editing Operation](https://mlsanity.com/paper/2503.16063/) (2025)

## Abstract (arXiv)

Dialogue systems in open domain have achieved great success due to the easily obtained single-turn corpus and the development of deep learning, but the multi-turn scenario is still a challenge because of the frequent coreference and information omission. In this paper, we investigate the incomplete utterance restoration which has brought general improvement over multi-turn dialogue systems in recent studies. Meanwhile, jointly inspired by the autoregression for text generation and the sequence labeling for text editing, we propose a novel semi autoregressive generator (SARG) with the high efficiency and flexibility. Moreover, experiments on two benchmarks show that our proposed model significantly outperforms the state-of-the-art models in terms of quality and inference speed.