Building Chatbots from Forum Data: Model Selection Using Question Answering Metrics
arXiv:1710.00689
Abstract
We propose to use question answering (QA) data from Web forums to train chatbots from scratch, i.e., without dialog training data. First, we extract pairs of question and answer sentences from the typically much longer texts of questions and answers in a forum. We then use these shorter texts to train seq2seq models in a more efficient way. We further improve the parameter optimization using a new model selection strategy based on QA measures. Finally, we propose to use extrinsic evaluation with respect to a QA task as an automatic evaluation method for chatbots. The evaluation shows that the model achieves a MAP of 63.5% on the extrinsic task. Moreover, it can answer correctly 49.5% of the questions when they are similar to questions asked in the forum, and 47.3% of the questions when they are more conversational in style.
RANLP-2017
References in corpus (4)
- A Neural Conversational Model
- Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge
- How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
- A Survey of Available Corpora for Building Data-Driven Dialogue Systems