Learning to Select External Knowledge with Multi-Scale Negative Sampling

by   Huang He, et al.

The Track-1 of DSTC9 aims to effectively answer user requests or questions during task-oriented dialogues, which are out of the scope of APIs/DB. By leveraging external knowledge resources, relevant information can be retrieved and encoded into the response generation for these out-of-API-coverage queries. In this work, we have explored several advanced techniques to enhance the utilization of external knowledge and boost the quality of response generation, including schema guided knowledge decision, negatives enhanced knowledge selection, and knowledge grounded response generation. To evaluate the performance of our proposed method, comprehensive experiments have been carried out on the publicly available dataset. Our approach was ranked as the best in human evaluation of DSTC9 Track-1.


Can I Be of Further Assistance? Using Unstructured Knowledge Access to Improve Task-oriented Conversational Modeling

Most prior work on task-oriented dialogue systems are restricted to limi...

Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access

Most prior work on task-oriented dialogue systems are restricted to a li...

Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue

Knowledge-grounded dialogue is a task of generating an informative respo...

Multimodal Dialog Systems with Dual Knowledge-enhanced Generative Pretrained Language Model

Text response generation for multimodal task-oriented dialog systems, wh...

Neural Assistant: Joint Action Prediction, Response Generation, and Latent Knowledge Reasoning

Task-oriented dialog presents a difficult challenge encompassing multipl...

PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable

Pre-training models have been proved effective for a wide range of natur...