# Reasoning in Dialog: Improving Response Generation by Context Reading Comprehension

arXiv: https://arxiv.org/abs/2012.07410 · HTML: https://mlsanity.com/paper/2012.07410/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Dec 2020.

## Built on by (most cited first, 6 of 6)

- [Target-aware Abstractive Related Work Generation with Contrastive Learning](https://mlsanity.com/paper/2205.13339/) (2022)
- [EZInterviewer: To Improve Job Interview Performance with Mock Interview Generator](https://mlsanity.com/paper/2301.00972/) (2023)
- [Logical Reasoning for Task Oriented Dialogue Systems](https://mlsanity.com/paper/2202.04161/) (2022)
- [Learning towards Selective Data Augmentation for Dialogue Generation](https://mlsanity.com/paper/2303.09719/) (2023)
- [Emotion Conditioned Creative Dialog Generation](https://mlsanity.com/paper/2212.02907/) (2022)
- [Does the Appearance of Autonomous Conversational Robots Affect User Spoken Behaviors in Real-World Conference Interactions?](https://mlsanity.com/paper/2503.13625/) (2025)

## Abstract (arXiv)

In multi-turn dialog, utterances do not always take the full form of sentences citeCarbonell1983DiscoursePA, which naturally makes understanding the dialog context more difficult. However, it is essential to fully grasp the dialog context to generate a reasonable response. Hence, in this paper, we propose to improve the response generation performance by examining the model's ability to answer a reading comprehension question, where the question is focused on the omitted information in the dialog. Enlightened by the multi-task learning scheme, we propose a joint framework that unifies these two tasks, sharing the same encoder to extract the common and task-invariant features with different decoders to learn task-specific features. To better fusing information from the question and the dialog history in the encoding part, we propose to augment the Transformer architecture with a memory updater, which is designed to selectively store and update the history dialog information so as to support downstream tasks. For the experiment, we employ human annotators to write and examine a large-scale dialog reading comprehension dataset. Extensive experiments are conducted on this dataset, and the results show that the proposed model brings substantial improvements over several strong baselines on both tasks. In this way, we demonstrate that reasoning can indeed help better response generation and vice versa. We release our large-scale dataset for further research.