Learning to Ask Conversational Questions by Optimizing Levenshtein Distance
This work addresses the challenge of generating conversational questions for natural language processing applications, representing an incremental improvement over existing methods.
The paper tackles the problem of Conversational Question Simplification (CQS) by proposing a Reinforcement Iterative Sequence Editing (RISE) framework that optimizes the minimum Levenshtein distance, significantly outperforming state-of-the-art methods on two benchmark datasets.
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.