Towards Generalized Models for Task-oriented Dialogue Modeling on Spoken Conversations
This work addresses the problem of task-oriented dialogue modeling for spoken conversations, which is incremental as it builds on existing methods with specific enhancements for a domain-specific challenge.
The paper tackled the challenge of building robust dialogue models for spoken conversations by mitigating discrepancies between spoken and written data using data augmentation and improved pre-trained models, achieving third place in objective evaluation and second in human evaluation in the DSTC-10 challenge.
Building robust and general dialogue models for spoken conversations is challenging due to the gap in distributions of spoken and written data. This paper presents our approach to build generalized models for the Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations Challenge of DSTC-10. In order to mitigate the discrepancies between spoken and written text, we mainly employ extensive data augmentation strategies on written data, including artificial error injection and round-trip text-speech transformation. To train robust models for spoken conversations, we improve pre-trained language models, and apply ensemble algorithms for each sub-task. Typically, for the detection task, we fine-tune \roberta and ELECTRA, and run an error-fixing ensemble algorithm. For the selection task, we adopt a two-stage framework that consists of entity tracking and knowledge ranking, and propose a multi-task learning method to learn multi-level semantic information by domain classification and entity selection. For the generation task, we adopt a cross-validation data process to improve pre-trained generative language models, followed by a consensus decoding algorithm, which can add arbitrary features like relative \rouge metric, and tune associated feature weights toward \bleu directly. Our approach ranks third on the objective evaluation and second on the final official human evaluation.