Building Chatbots from Forum Data: Model Selection Using Question Answering Metrics

TL;DR

This paper introduces a method to build chatbots from forum question-answer data using QA metrics for model selection and extrinsic evaluation, achieving promising results without relying on traditional dialog training data.

Contribution

It presents a novel approach to train chatbots from forum data and introduces a QA-based model selection and evaluation strategy, bypassing the need for dialog-specific training data.

Findings

Achieved a MAP of 63.5% on an extrinsic QA task.

Correctly answered 49.5% of similar forum questions.

Answered 47.3% of conversational questions.

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.