Abstract
Querying the knowledge base (KB) has long been a challenge in the end-to-end task-oriented dialogue system. Previous sequence-to-sequence (Seq2Seq) dialogue generation work treats the KB query as an attention over the entire KB, without the guarantee that the generated entities are consistent with each other. In this paper, we propose a novel framework which queries the KB in two steps to improve the consistency of generated entities. In the first step, inspired by the observation that a response can usually be supported by a single KB row, we introduce a KB retrieval component which explicitly returns the most relevant KB row given a dialogue history. The retrieval result is further used to filter the irrelevant entities in a Seq2Seq response generation model to improve the consistency among the output entities. In the second step, we further perform the attention mechanism to address the most correlated KB column. Two methods are proposed to make the training feasible without labeled retrieval data, which include distant supervision and Gumbel-Softmax technique. Experiments on two publicly available task oriented dialog datasets show the effectiveness of our model by outperforming the baseline systems and producing entity-consistent responses.
Highlights
Task-oriented dialogue system, which helps users to achieve specific goals with natural language, is attracting more and more research attention
A consistent response is relatively easy to achieve for the conventional pipeline systems because they query the knowledge base (KB) by issuing API calls (Bordes and Weston, 2017; Wen et al, 2017b,a), and the returned entities, which typically come from a single KB row, are consistently related to the object that serves the user’s request
Analysis empirically verifies our assumption that more than 80% responses in the dataset can be supported by a single KB row and better retrieval results lead to better task-oriented dialogue generation performance
Summary
Task-oriented dialogue system, which helps users to achieve specific goals with natural language, is attracting more and more research attention. The correct address for Valero is 200 Alester Ave. A consistent response is relatively easy to achieve for the conventional pipeline systems because they query the KB by issuing API calls (Bordes and Weston, 2017; Wen et al, 2017b,a), and the returned entities, which typically come from a single KB row, are consistently related to the object (like the “gas station”) that serves the user’s request. A consistent response is relatively easy to achieve for the conventional pipeline systems because they query the KB by issuing API calls (Bordes and Weston, 2017; Wen et al, 2017b,a), and the returned entities, which typically come from a single KB row, are consistently related to the object (like the “gas station”) that serves the user’s request This indicates that a response can usually be supported by a single KB row. Analysis empirically verifies our assumption that more than 80% responses in the dataset can be supported by a single KB row and better retrieval results lead to better task-oriented dialogue generation performance
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
