Learning to Ask Conversational Questions by Optimizing Levenshtein Distance

TL;DR

This paper presents RISE, a reinforcement learning framework that optimizes Levenshtein distance for conversational question simplification, effectively capturing conversational features and outperforming existing methods.

Contribution

Introduction of RISE, a novel reinforcement learning approach that explicitly optimizes Levenshtein distance for better conversational question simplification.

Findings

RISE outperforms state-of-the-art methods on benchmark datasets.

The framework generalizes well to unseen data.

Explicit editing actions improve conversational feature capture.

Abstract

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.