Neural Matching Models for Question Retrieval and Next Question Prediction in Conversation

TL;DR

This paper explores neural matching models for question retrieval and predicting the next question in conversations, demonstrating their effectiveness on datasets like Quora and Ubuntu chat logs.

Contribution

It formalizes the task of next question prediction in conversations and evaluates neural matching models for both question retrieval and prediction tasks.

Findings

Neural matching models perform well in question retrieval.

Neural models are effective for next question prediction.

Evaluation on Quora and Ubuntu datasets confirms their potential.

Abstract

The recent boom of AI has seen the emergence of many human-computer conversation systems such as Google Assistant, Microsoft Cortana, Amazon Echo and Apple Siri. We introduce and formalize the task of predicting questions in conversations, where the goal is to predict the new question that the user will ask, given the past conversational context. This task can be modeled as a "sequence matching" problem, where two sequences are given and the aim is to learn a model that maps any pair of sequences to a matching probability. Neural matching models, which adopt deep neural networks to learn sequence representations and matching scores, have attracted immense research interests of information retrieval and natural language processing communities. In this paper, we first study neural matching models for the question retrieval task that has been widely explored in the literature, whereas the effectiveness of neural models for this task is relatively unstudied. We further evaluate the neural matching models in the next question prediction task in conversations. We have used the publicly available Quora data and Ubuntu chat logs in our experiments. Our evaluations investigate the potential of neural matching models with representation learning for question retrieval and next question prediction in conversations. Experimental results show that neural matching models perform well for both tasks.