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

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

27 Feb 2020arXiv:2003.04994archive 2025-07-28

Tianyi Wang, Yating Zhang, Xiaozhong Liu, Changlong Sun, Qiong Zhang

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

wangtianyiftd/dialogue officialmentioned in paper report
wangtianyiftd/dialogue_pretrain officialmentioned in paper report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Dialogue UnderstandingQuestion AnsweringRepresentation Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections