# Action based Network for Conversation Question Reformulation

Source: [Action based Network for Conversation Question Reformulation](<https://www.sota2.com/research/paper/68fa6b4c1e209131cea2d61a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:11:34.522Z

Authors: Zheyu Ye, Jiangning Liu, Qian Yu, Jianxun Ju

Published: 2021-11-29T10:58:15.000Z

## Abstract

Conversation question answering requires the ability to interpret a question correctly. Current models, however, are still unsatisfactory due to the difficulty of understanding the co-references and ellipsis in daily conversation. Even though generative approaches achieved remarkable progress, they are still trapped by semantic incompleteness. This paper presents an action-based approach to recover the complete expression of the question. Specifically, we first locate the positions of co-reference or ellipsis in the question while assigning the corresponding action to each candidate span. We then look for matching phrases related to the candidate clues in the conversation context. Finally, according to the predicted action, we decide whether to replace the co-reference or supplement the ellipsis with the matched information. We demonstrate the effectiveness of our method on both English and Chinese utterance rewrite tasks, improving the state-of-the-art EM (exact match) by 3.9\\% and ROUGE-L by 1.0\\% respectively on the Restoration-200K dataset.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2111.14445>)

[PDF](<https://arxiv.org/pdf/2111.14445.pdf>)
