MTE-NN at SemEval-2016 task 3: Can machine translation evaluation help community question answering?

Fráncisco Guzman, Lluis Marques, Preslav Nakov

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

We present a system for answer ranking (SemEval-2016 Task 3, subtask A) that is a direct adaptation of a pairwise neural network model for machine translation evaluation (MTE). In particular, the network incorporates MTE features, as well as rich syntactic and semantic embeddings, and it efficiently models complex non-linear interactions between them. With the addition of lightweight task-specific features, we obtained very encouraging experimental results, with sizeable contributions from both the MTE features and from the pairwise network architecture. We also achieved good results on subtask C.

Original languageEnglish
Title of host publicationSemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings
PublisherAssociation for Computational Linguistics (ACL)
Pages887-895
Number of pages9
ISBN (Electronic)9781941643952
Publication statusPublished - 1 Jan 2016
Event10th International Workshop on Semantic Evaluation, SemEval 2016 - San Diego, United States
Duration: 16 Jun 201617 Jun 2016

Other

Other10th International Workshop on Semantic Evaluation, SemEval 2016
CountryUnited States
CitySan Diego
Period16/6/1617/6/16

    Fingerprint

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computational Theory and Mathematics
  • Computer Science Applications

Cite this

Guzman, F., Marques, L., & Nakov, P. (2016). MTE-NN at SemEval-2016 task 3: Can machine translation evaluation help community question answering? In SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings (pp. 887-895). Association for Computational Linguistics (ACL).