# Unsupervised Context Rewriting for Open Domain Conversation

arXiv: https://arxiv.org/abs/1910.08282 · HTML: https://mlsanity.com/paper/1910.08282/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Oct 2019.

## Built on by (most cited first, 14 of 14)

- [From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning](https://mlsanity.com/paper/2308.12032/) (2023)
- [Surface Form Competition: Why the Highest Probability Answer Isn't Always Right](https://mlsanity.com/paper/2104.08315/) (2021)
- [Recent Advances in Neural Text Generation: A Task-Agnostic Survey](https://mlsanity.com/paper/2203.03047/) (2022)
- [Evaluating the Deductive Competence of Large Language Models](https://mlsanity.com/paper/2309.05452/) (2023)
- [Towards Standard Criteria for human evaluation of Chatbots: A Survey](https://mlsanity.com/paper/2105.11197/) (2021)
- [Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models](https://mlsanity.com/paper/2109.05793/) (2021)
- [Incomplete Utterance Rewriting as Sequential Greedy Tagging](https://mlsanity.com/paper/2307.06337/) (2023)
- [Utterance Rewriting with Contrastive Learning in Multi-turn Dialogue](https://mlsanity.com/paper/2203.11587/) (2022)
- [On The Truthfulness of 'Surprisingly Likely' Responses of Large Language Models](https://mlsanity.com/paper/2311.07692/) (2023)
- [Survey of Design Paradigms for Social Robots](https://mlsanity.com/paper/2407.20556/) (2024)
- [Incomplete Utterance Rewriting with Editing Operation Guidance and Utterance Augmentation](https://mlsanity.com/paper/2503.16043/) (2025)
- [A Static and Dynamic Attention Framework for Multi Turn Dialogue Generation](https://mlsanity.com/paper/2410.20766/) (2024)
- [RSMLP: A light Sampled MLP Structure for Incomplete Utterance Rewrite](https://mlsanity.com/paper/2502.12587/) (2025)
- [LINE Conversation History Retrieval for Personal Memory RAG: Evaluating Search Representations and Hybrid Retrieval](https://mlsanity.com/paper/2608.27809/) (2026)

## Abstract (arXiv)

Context modeling has a pivotal role in open domain conversation. Existing works either use heuristic methods or jointly learn context modeling and response generation with an encoder-decoder framework. This paper proposes an explicit context rewriting method, which rewrites the last utterance by considering context history. We leverage pseudo-parallel data and elaborate a context rewriting network, which is built upon the CopyNet with the reinforcement learning method. The rewritten utterance is beneficial to candidate retrieval, explainable context modeling, as well as enabling to employ a single-turn framework to the multi-turn scenario. The empirical results show that our model outperforms baselines in terms of the rewriting quality, the multi-turn response generation, and the end-to-end retrieval-based chatbots.