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

TL;DR

SOLOIST introduces a scalable approach for building task-oriented dialogue systems using transfer learning and machine teaching, achieving state-of-the-art results with minimal task-specific data.

Contribution

The paper presents a Transformer-based pre-trained model that unifies dialog modules and enables efficient adaptation to new tasks with few examples.

Findings

Achieves state-of-the-art on CamRest676 and MultiWOZ benchmarks.

Significantly outperforms existing methods in few-shot settings.

Reduces labeling costs through machine teaching.

Abstract

We present a new method SOLOIST 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.