How to avoid unwanted pregnancies: Domain adaptation using neural network models

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

8 Citations (Scopus)

Abstract

We present novel models for domain adaptation based on the neural network joint model (NNJM). Our models maximize the cross enttopy by regularizing the loss function with respect to in-domain model. Domain adaptation is carried out by assigning higher weight to out-domain sequences that are similar to the in-domain data. In our alternative model we take a more restrictive approach by additionally penalizing sequences similar to the outdomain data. Our models achieve better perplexities than the baseline NNIM models and give improvements of up to 0.5 and 0.6 BLEU points in Arabic-to-English and English-to-German language pairs, on a standard task of translating TED talks.

Original languageEnglish
Title of host publicationConference Proceedings - EMNLP 2015
Subtitle of host publicationConference on Empirical Methods in Natural Language Processing
PublisherAssociation for Computational Linguistics (ACL)
Pages1259-1270
Number of pages12
ISBN (Electronic)9781941643327
Publication statusPublished - 1 Jan 2015
EventConference on Empirical Methods in Natural Language Processing, EMNLP 2015 - Lisbon, Portugal
Duration: 17 Sep 201521 Sep 2015

Publication series

NameConference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing

Other

OtherConference on Empirical Methods in Natural Language Processing, EMNLP 2015
CountryPortugal
CityLisbon
Period17/9/1521/9/15

    Fingerprint

ASJC Scopus subject areas

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

Cite this

Joty, S., Sajjad, H., Durrani, N., Al-Mannai, K., Abdelali, A., & Vogel, S. (2015). How to avoid unwanted pregnancies: Domain adaptation using neural network models. In Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing (pp. 1259-1270). (Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing). Association for Computational Linguistics (ACL).