Filling Conversation Ellipsis for Better Social Dialog Understanding
This work addresses a specific issue in natural language processing for social dialog understanding, offering incremental improvements in accuracy for downstream tasks.
The paper tackled the problem of ellipsis in social conversations, which hinders language understanding tasks like dialog act prediction and semantic role labeling, by proposing a method that uses automatic sentence completion and combines predictions from original and completed utterances, resulting in improvements of 1.3% and 2.5% in F1 scores for these tasks.
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.