Learning End-to-End Goal-Oriented Dialog with Multiple Answers

Abstract

In a dialog, there can be multiple valid next utterances at any point. The present end-to-end neural methods for dialog do not take this into account. They learn with the assumption that at any time there is only one correct next utterance. In this work, we focus on this problem in the goal-oriented dialog setting where there are different paths to reach a goal. We propose a new method, that uses a combination of supervised learning and reinforcement learning approaches to address this issue. We also propose a new and more effective testbed, permuted-bAbI dialog tasks, by introducing multiple valid next utterances to the original-bAbI dialog tasks, which allows evaluation of goal-oriented dialog systems in a more realistic setting. We show that there is a significant drop in performance of existing end-to-end neural methods from 81.5% per-dialog accuracy on original-bAbI dialog tasks to 30.3% on permuted-bAbI dialog tasks. We also show that our proposed method improves the performance and achieves 47.3% per-dialog accuracy on permuted-bAbI dialog tasks.

arXiv commentEMNLP 2018. permuted-bAbI dialog tasks are available at - https://github.com/IBM/permuted-bAbI-dialog-tasks

References in corpus (6)

• A Neural Conversational Model
• A Survey of Available Corpora for Building Data-Driven Dialogue Systems
• A Network-based End-to-End Trainable Task-oriented Dialogue System
• Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems
• Query-Reduction Networks for Question Answering
• Learning from Real Users: Rating Dialogue Success with Neural Networks for Reinforcement Learning in Spoken Dialogue Systems