English

Machine Translation Evaluation Meets Community Question Answering

Computation and Language 2019-12-09 v1 Information Retrieval Machine Learning

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.

Keywords

Cite

@article{arxiv.1912.02998,
  title  = {Machine Translation Evaluation Meets Community Question Answering},
  author = {Francisco Guzmán and Lluís Màrquez and Preslav Nakov},
  journal= {arXiv preprint arXiv:1912.02998},
  year   = {2019}
}

Comments

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

R2 v1 2026-06-23T12:37:46.520Z