.png){kind=icon}
.png){kind=icon}
Return
Learning to Select External Knowledge With Multi-Scale Negative Sampling
.png){kind=icon}
OA
AI
DOI：10.1109/TASLP.2023.3301222.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Keywords:
Task analysis
Oral communication
Training
Transformers
Speech processing
Public transportation
Knowledge engineering
Task-oriented dialogue
knowledge selection
Journal
I
IF:
5.1
Papers:
2.6K
Citations:
1.1W