利用多尺度负抽样学习选择外部知识
Learning to Select External Knowledge with Multi-Scale Negative Sampling
摘要：
DSTC 9的Track-1旨在有效地回答面向任务的对话中的用户请求或问题，这超出了API/DB的范围。通过利用外部知识资源，可以检索相关信息并将其编码到这些API覆盖范围外查询的响应生成中。在这项工作中，我们已经探索了一些先进的技术，以提高利用外部知识，提高响应生成的质量，包括图式引导的知识决策，否定增强的知识选择，知识接地响应生成。为了评估我们所提出的方法的性能，已经进行了全面的实验上公开可用的数据集。我们的方法在DSTC 9 Track-1的人类评估中被评为最佳。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
