Soloist: Building Task Bots at Scale with Transfer Learning and Machine Teaching

Baolin Peng, Chunyuan Li, Jinchao Li, Shahin Shayandeh, Lars Liden, Jianfeng Gao


Abstract
We present a new method, Soloist,1 that uses transfer learning and machine teaching to build task bots at scale. We parameterize classical modular task-oriented dialog systems using a Transformer-based auto-regressive language model, which subsumes different dialog modules into a single neural model. We pre-train, on heterogeneous dialog corpora, a task-grounded response generation model, which can generate dialog responses grounded in user goals and real-world knowledge for task completion. The pre-trained model can be efficiently adapted to accomplish new tasks with a handful of task-specific dialogs via machine teaching, where training samples are generated by human teachers interacting with the system. Experiments show that (i)Soloist creates new state-of-the-art on well-studied task-oriented dialog benchmarks, including CamRest676 and MultiWOZ; (ii) in the few-shot fine-tuning settings, Soloist significantly outperforms existing methods; and (iii) the use of machine teaching substantially reduces the labeling cost of fine-tuning. The pre-trained models and codes are available at https://aka.ms/soloist.
Anthology ID:
2021.tacl-1.49
Volume:
Transactions of the Association for Computational Linguistics, Volume 9
Month:
Year:
2021
Address:
Cambridge, MA
Editors:
Brian Roark, Ani Nenkova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
807–824
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2021.tacl-1.49/
DOI:
10.1162/tacl_a_00399
Bibkey:
Cite (ACL):
Baolin Peng, Chunyuan Li, Jinchao Li, Shahin Shayandeh, Lars Liden, and Jianfeng Gao. 2021. Soloist: Building Task Bots at Scale with Transfer Learning and Machine Teaching. Transactions of the Association for Computational Linguistics, 9:807–824.
Cite (Informal):
Soloist: Building Task Bots at Scale with Transfer Learning and Machine Teaching (Peng et al., TACL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2021.tacl-1.49.pdf
Video:
 https://preview.aclanthology.org/build-pipeline-with-new-library/2021.tacl-1.49.mp4