Masking Orchestration: Multi-task Pretraining for Multi-role Dialogue Representation Learning

TL;DR

This paper introduces a multi-task pretraining approach for multi-role dialogue representation learning, leveraging unsupervised objectives aligned with dialogue structure to improve performance across various dialogue understanding tasks.

Contribution

It proposes a novel fine-tuned pretraining mechanism that integrates external knowledge and is effective across multiple dialogue tasks and datasets.

Findings

Significant improvements in downstream dialogue tasks.

Effective across different encoder architectures.

Enhances dialogue summarization and extraction performance.

Abstract

Multi-role dialogue understanding comprises a wide range of diverse tasks such as question answering, act classification, dialogue summarization etc. While dialogue corpora are abundantly available, labeled data, for specific learning tasks, can be highly scarce and expensive. In this work, we investigate dialogue context representation learning with various types unsupervised pretraining tasks where the training objectives are given naturally according to the nature of the utterance and the structure of the multi-role conversation. Meanwhile, in order to locate essential information for dialogue summarization/extraction, the pretraining process enables external knowledge integration. The proposed fine-tuned pretraining mechanism is comprehensively evaluated via three different dialogue datasets along with a number of downstream dialogue-mining tasks. Result shows that the proposed pretraining mechanism significantly contributes to all the downstream tasks without discrimination to different encoders.