Machine Translation Evaluation Meets Community Question Answering

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.

community question answering, machine translation evaluation, pairwise ranking, learning to rank

Cited by in corpus (1)

• Match${}^2$: A Matching over Matching Model for Similar Question Identification