论文标题
使用多主管变压器进行对话的响应检索方法
A Response Retrieval Approach for Dialogue Using a Multi-Attentive Transformer
论文作者
论文摘要
本文介绍了我们在对话系统技术挑战赛（DSTC9）的第九版中的工作。我们的解决方案解决了曲目编号的第四：模拟交互式多模式对话。该任务包括提供一种能够模拟用他/她的请求支持用户的购物助理的算法。我们解决了响应检索的任务，这是从响应候选者中检索最合适的代理响应的任务。我们的方法利用基于变压器的神经体系结构具有多功能结构，该结构对代理对用户的请求以及用户所指的产品的响应进行了响应。在SIMMC时尚数据集上进行的最终实验表明，我们的方法在组织者定义的所有检索指标上取得了第二好的分数。源代码可在https://github.com/d2klab/dstc9-simmc上找到。
This paper presents our work for the ninth edition of the Dialogue System Technology Challenge (DSTC9). Our solution addresses the track number four: Simulated Interactive MultiModal Conversations. The task consists in providing an algorithm able to simulate a shopping assistant that supports the user with his/her requests. We address the task of response retrieval, that is the task of retrieving the most appropriate agent response from a pool of response candidates. Our approach makes use of a neural architecture based on transformer with a multi-attentive structure that conditions the response of the agent on the request made by the user and on the product the user is referring to. Final experiments on the SIMMC Fashion Dataset show that our approach achieves the second best scores on all the retrieval metrics defined by the organizers. The source code is available at https://github.com/D2KLab/dstc9-SIMMC.
