Learning to Select External Knowledge With Multi-Scale Negative Sampling
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING(2024)
摘要
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.
更多查看译文
关键词
Task analysis,Oral communication,Training,Transformers,Speech processing,Public transportation,Knowledge engineering,Task-oriented dialogue,knowledge selection
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要