Filling Conversation Ellipsis for Better Social Dialog Understanding

TL;DR

This paper introduces a method to resolve ellipsis in social conversations by automatic sentence completion, enhancing downstream language understanding tasks like dialog act prediction and semantic role labeling.

Contribution

It proposes an end-to-end pointer network for ellipsis completion and a combined prediction approach to improve understanding accuracy in social dialogue analysis.

Findings

Dialog act prediction improved by 1.3% F1 score.

Semantic role labeling improved by 2.5% F1 score.

Provides an open-domain dataset with manual ellipsis completion annotations.

Abstract

The phenomenon of ellipsis is prevalent in social conversations. Ellipsis increases the difficulty of a series of downstream language understanding tasks, such as dialog act prediction and semantic role labeling. We propose to resolve ellipsis through automatic sentence completion to improve language understanding. However, automatic ellipsis completion can result in output which does not accurately reflect user intent. To address this issue, we propose a method which considers both the original utterance that has ellipsis and the automatically completed utterance in dialog act and semantic role labeling tasks. Specifically, we first complete user utterances to resolve ellipsis using an end-to-end pointer network model. We then train a prediction model using both utterances containing ellipsis and our automatically completed utterances. Finally, we combine the prediction results from these two utterances using a selection model that is guided by expert knowledge. Our approach improves dialog act prediction and semantic role labeling by 1.3% and 2.5% in F1 score respectively in social conversations. We also present an open-domain human-machine conversation dataset with manually completed user utterances and annotated semantic role labeling after manual completion.