An End-to-End Framework for Cold Question Routing in Community Question Answering Services

TL;DR

This paper introduces an end-to-end framework that combines graph and textual information to improve the routing of new questions to suitable answerers in community question answering platforms.

Contribution

It presents a novel joint learning framework that effectively leverages heterogeneous graph and textual data for cold question routing.

Findings

The framework outperforms existing methods in routing accuracy.

Incorporating textual information from question tags improves performance.

The approach is effective for both existing and newly registered users.

Abstract

Routing newly posted questions (a.k.a cold questions) to potential answerers with the suitable expertise in Community Question Answering sites (CQAs) is an important and challenging task. The existing methods either focus only on embedding the graph structural information and are less effective for newly posted questions, or adopt manually engineered feature vectors that are not as representative as the graph embedding methods. Therefore, we propose to address the challenge of leveraging heterogeneous graph and textual information for cold question routing by designing an end-to-end framework that jointly learns CQA node embeddings and finds best answerers for cold questions. We conducted extensive experiments to confirm the usefulness of incorporating the textual information from question tags and demonstrate that an end-2-end framework can achieve promising performances on routing newly posted questions asked by both existing users and newly registered users.