Abstract
In spite of lots of cross-lingual word embedding models for various languages, approaches that support cross-lingual word embedding between languages that have different word order and different origin word are lacking. In this study, we address the problem of cross-lingual word embedding between Korean and English that have different word order and origin and perform experiments to examine its performance behavior. Cross-lingual models have different levels of supervision. For training between languages which have different word order, it is essential to reduce preprocessing time. Therefore, two sentence-level alignment cross-lingual models are chosen for our experiments. Our results show that cross-lingual embedding for Korean and English without word-alignment is possible. We also analyze which bilingual tasks are proper for each trained result by comparing characteristic of each model’s trained result.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Upadhyay S, Faruqui M, Dyer C, Roth D (2016) Cross-lingual models of word embeddings: an empirical comparison. In: Proceedings of ACL
Hermann KM, Blunsom P (2014) Multilingual models for compositional distributed semantics. In: Proceedings of ACL
Hermann KM, Blunsom P (2014) Multilingual distributed representations without word alignment. In: Proceedings of ICLR
Gouws S, Bengio Y, Corrado G (2015) BilBOWA: fast bilingual distributed representations without word alignments. In: Proceedings of ICML
Clark S, Pulman S (2007) Combining symbolic and distributional models of meaning. In: American Association for Artificial Intelligence (AAAI)
Hermann KM, Blunsom P (2013) The role of syntax in vector space models of compositional semantics. In: Proceedings of ACL
Mikolov T, Sutskever I, Chen K, Corrado G, Dean J (2013) Distributed representations of words and phrases and their compositionality. In: Proceedings of NIPS
Acknowledgement
This research was supported by the MISP (Ministry of Science, ICT & Future Planning), Korea, under the National Program for Excellence in SW) supervised by the IITP (Institute for Information & communications Technology Promotion) (R22151610020001002).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Science+Business Media Singapore
About this paper
Cite this paper
Kim, Ms., Cha, Ms., Sohn, KA. (2018). Bilingual Word-Embedding for Korean and English Without Word Alignments. In: Kim, K., Joukov, N. (eds) Mobile and Wireless Technologies 2017. ICMWT 2017. Lecture Notes in Electrical Engineering, vol 425. Springer, Singapore. https://doi.org/10.1007/978-981-10-5281-1_48
Download citation
DOI: https://doi.org/10.1007/978-981-10-5281-1_48
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-5280-4
Online ISBN: 978-981-10-5281-1
eBook Packages: EngineeringEngineering (R0)