Joint multitask learning for community question answering using task-specific embeddings

Shafiq Joty, Lluís Màrquez, Preslav Nakov

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

3 Citations (Scopus)

Abstract

We address jointly two important tasks for Question Answering in community forums: given a new question, (i) find related existing questions, and (ii) find relevant answers to this new question. We further use an auxiliary task to complement the previous two, i.e., (iii) find good answers with respect to the thread question in a question-comment thread. We use deep neural networks (DNNs) to learn meaningful task-specific embeddings, which we then incorporate into a conditional random field (CRF) model for the multitask setting, performing joint learning over a complex graph structure. While DNNs alone achieve competitive results when trained to produce the embeddings, the CRF, which makes use of the embeddings and the dependencies between the tasks, improves the results significantly and consistently across a variety of evaluation metrics, thus showing the complementarity of DNNs and structured learning.

Original languageEnglish
Title of host publicationProceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
EditorsEllen Riloff, David Chiang, Julia Hockenmaier, Jun'ichi Tsujii
PublisherAssociation for Computational Linguistics
Pages4196-4207
Number of pages12
ISBN (Electronic)9781948087841
Publication statusPublished - 1 Jan 2020
Event2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018 - Brussels, Belgium
Duration: 31 Oct 20184 Nov 2018

Publication series

NameProceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018

Conference

Conference2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
CountryBelgium
CityBrussels
Period31/10/184/11/18

    Fingerprint

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Information Systems

Cite this

Joty, S., Màrquez, L., & Nakov, P. (2020). Joint multitask learning for community question answering using task-specific embeddings. In E. Riloff, D. Chiang, J. Hockenmaier, & J. Tsujii (Eds.), Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018 (pp. 4196-4207). (Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018). Association for Computational Linguistics.