Machine Translation Evaluation Meets Community Question Answering

TL;DR

This paper adapts machine translation evaluation techniques to improve answer ranking in community Question Answering by using a neural network architecture that combines MTE features with rich embeddings, achieving state-of-the-art results.

Contribution

It introduces a novel pairwise neural network model that integrates MTE features and semantic embeddings for answer ranking in community QA, demonstrating significant performance gains.

Findings

Achieved state-of-the-art answer ranking performance.

Both MTE features and neural network architecture significantly contribute.

The approach effectively models complex non-linear interactions.

Abstract

We explore the applicability of machine translation evaluation (MTE) methods to a very different problem: answer ranking in community Question Answering. In particular, we adopt a pairwise neural network (NN) architecture, which incorporates MTE features, as well as rich syntactic and semantic embeddings, and which efficiently models complex non-linear interactions. The evaluation results show state-of-the-art performance, with sizeable contribution from both the MTE features and from the pairwise NN architecture.