Attention Strategies for Multi-Source Sequence-to-Sequence Learning

Jindřich Libovický, Jindřich Helcl

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

Abstract / Description of output

Modeling attention in neural multi-source sequence-to-sequence learning remains a relatively unexplored area, despite its usefulness in tasks that incorporate multiple source languages or modalities. We propose two novel approaches to combine the outputs of attention mechanisms over each source sequence, flat and hierarchical. We compare the proposed methods with existing techniques and present results of systematic evaluation of those methods on the WMT16 Multimodal Translation and Automatic Post-editing tasks. We show that the proposed methods achieve competitive results on both tasks.
Original languageEnglish
Title of host publicationProceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Place of PublicationVancouver, Canada
PublisherAssociation for Computational Linguistics
Number of pages7
ISBN (Electronic)978-1-945626-76-0
Publication statusPublished - 31 Jul 2017
Event55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 - Vancouver, Canada
Duration: 30 Jul 20174 Aug 2017


Conference55th Annual Meeting of the Association for Computational Linguistics, ACL 2017


Dive into the research topics of 'Attention Strategies for Multi-Source Sequence-to-Sequence Learning'. Together they form a unique fingerprint.

Cite this