Word representation models for morphologically rich languages in neural Machine Translation

Ekaterina Vylomova, Trevor Cohn, Xuanli He, Gholamreza Haffari

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

16 Citations (Scopus)


Out-of-vocabulary words present a great challenge for Machine Translation. Recently various character-level compositional models were proposed to address this issue. In current research we incorporate two most popular neural architectures, namely LSTM and CNN, into hard- and soft-attentional models of translation for character-level representation of the source. We propose semantic and morphological intrinsic evaluation of encoder-level representations. Our analysis of the learned representations reveals that character-based LSTM seems to be better at capturing morphological aspects compared to character-based CNN. We also show that a hard-attentional model provides better character-level representations compared to standard 'soft' attention.

Original languageEnglish
Title of host publicationEMNLP 2017 - First Workshop on Subword and Character Level Models in NLP, Proceedings of the Workshop
EditorsManaal Faruqui, Hinrich Schutze, Isabel Trancoso, Yaghoobzadeh Yadollah
Place of PublicationStroudsburg PA USA
PublisherAssociation for Computational Linguistics (ACL)
Number of pages6
ISBN (Electronic)9781945626913
Publication statusPublished - 2017
EventWorkshop on Subword and Character Level Models in NLP 2017 - Copenhagen, Denmark
Duration: 7 Sept 20177 Sept 2017
Conference number: 1st
https://aclanthology.org/volumes/W17-41/ (Proceedings)


WorkshopWorkshop on Subword and Character Level Models in NLP 2017
Abbreviated titleSCLeM 2017
Internet address

Cite this