# Learning to Ask Conversational Questions by Optimizing Levenshtein Distance

arXiv: https://arxiv.org/abs/2106.15903 · HTML: https://mlsanity.com/paper/2106.15903/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 46 references that are in the map.
- First posted on arXiv 30 Jun 2021.

## Builds on (most cited first, 14 of 14)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [Advances and Challenges in Conversational Recommender Systems: A Survey](https://mlsanity.com/paper/2101.09459/) (2021)
- [Open-Retrieval Conversational Question Answering](https://mlsanity.com/paper/2005.11364/) (2020)
- [Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems](https://mlsanity.com/paper/2002.09102/) (2020)
- [Question Rewriting for Conversational Question Answering](https://mlsanity.com/paper/2004.14652/) (2020)
- [Few-Shot Generative Conversational Query Rewriting](https://mlsanity.com/paper/2006.05009/) (2020)
- [Improving Multi-turn Dialogue Modelling with Utterance ReWriter](https://mlsanity.com/paper/1906.07004/) (2019)
- [Conversational Question Reformulation via Sequence-to-Sequence Architectures and Pretrained Language Models](https://mlsanity.com/paper/2004.01909/) (2020)
- [Generative Adversarial Networks](https://mlsanity.com/paper/1406.2661/) (2014)
- [Wizard of Search Engine: Access to Information Through Conversations with Search Engines](https://mlsanity.com/paper/2105.08301/) (2021)
- [Multi-Stage Conversational Passage Retrieval: An Approach to Fusing Term Importance Estimation and Neural Query Rewriting](https://mlsanity.com/paper/2005.02230/) (2020)

## Abstract (arXiv)

Conversational Question Simplification (CQS) aims to simplify self-contained questions into conversational ones by incorporating some conversational characteristics, e.g., anaphora and ellipsis. Existing maximum likelihood estimation (MLE) based methods often get trapped in easily learned tokens as all tokens are treated equally during training. In this work, we introduce a Reinforcement Iterative Sequence Editing (RISE) framework that optimizes the minimum Levenshtein distance (MLD) through explicit editing actions. RISE is able to pay attention to tokens that are related to conversational characteristics. To train RISE, we devise an Iterative Reinforce Training (IRT) algorithm with a Dynamic Programming based Sampling (DPS) process to improve exploration. Experimental results on two benchmark datasets show that RISE significantly outperforms state-of-the-art methods and generalizes well on unseen data.