Abstract
Translation of noun compounds has been a challenging task in machine translation for many years. Noun compounds are used very productively and constitute a large amount of the text vocabulary. We present a work on translation of noun compounds from English to German, focusing on identifying the nominal structures in English which represent compounds. This work is part of developing a speech-to-speech translation system, and the input to the machine translation component comes from automatic speech recognition. This brings in a further difficulty to the translation of noun compounds because the input might introduce recognition errors and it does not have typical features of a written text such as punctuation and capitalization. We present a method of noun compound identification based on syntactic analysis and lexical information and discuss the challenges that we encountered during the compound identification process.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Parra EscartÃn, C., Peitz, S., Ney, H.: German compounds and statistical machine translation. Can they get along? In: Proceedings of the 10th Workshop on Multiword Expressions. ACL (2014)
Nakov, P.: On the interpretation of noun compounds: Syntax, semantics, and entailment. Natural Language Engineering 19(3) (2013)
Rat für deutsche Rechtschreibung: Deutsche Rechtschreibung: Regeln und Wörterverzeichnis: Amtliche Regelung. Gunter Narr Verlag, Tübingen (2006)
Rackow, U., Dagan, I., Schwall, U.: Automatic translation of noun compounds. In: Proceedings of the 14th International Conference on Computational Linguistics (1992)
Lauer, M.: Corpus statistics meet the noun compound: some empirical results. In: Proceedings of the 33rd Annual Meeting of ACL (1995)
Lieber, R., Stekauer, P.: The Oxford Handbook of Compounding. Oxford Handbooks in Linguistics. OUP, Oxford (2009)
Ziering, P., van der Plas, L.: What good are ‘nominalkomposita’ for ‘noun compounds’: multilingual extraction and structure analysis of nominal compositions using linguistic restrictors. In: Proceedings of COLING (2014)
Garner, P.N., Clark, R., Goldman, J.P., Honnet, P.E., Ivanova, M., Lazaridis, A., Liang, H., Pfister, B., Ribeiro, M.S., Wehrli, E., Yamagishi, J.: Translation and prosody in Swiss languages. Nouveaux cahiers de linguistique française 31 (2014). 3rd Swiss Workshop on Prosody, Geneva, September 2014
Bauer, L.: When is a sequence of noun + noun a compound in english? English Language and Linguistics 2 (1998)
Wehrli, E., Nerima, L., Scherrer, Y.: Deep linguistic multilingual translation and bilingual dictionaries. In: Proceedings of the Fourth Workshop on Statistical Machine Translation. ACL (2009)
Wehrli, E.: Fips, a “deep" linguistic multilingual parser. In: Proceedings of the Workshop on Deep Linguistic Processing. ACL (2007)
Booij, G.: The grammar of words. An introduction to linguistic morphology. Oxford University Press (2005)
Bell, P., Swietojanski, P., Driesen, J., Sinclair, M., McInnes, F., Renals, S.: The UEDIN ASR systems for the IWSLT 2014 evaluation. In: IWSLT (2014)
Grazina, N.M.M.: Automatic Speech Translation. Universidade Técnica de Lisboa (UTL), Instituto Superior Técnico., Lisboa, Portugal (2010)
Batista, F., Caseiro, D., Mamede, N.J., Trancoso, I.: Recovering punctuation marks for automatic speech recognition. In: INTERSPEECH. ISCA (2007)
Cho, E., Niehues, J., Waibel, A.: Segmentation and punctuation prediction in speech language translation using a monolingual translation system. In: IWSLT (2012)
Batista, F., Caseiro, D., Mamede, N., Trancoso, I.: Recovering capitalization and punctuation marks for automatic speech recognition: Case study for portuguese broadcast news. Speech Communication 50(10) (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Ivanova, M., Wehrli, E. (2015). Identification of Noun-Noun Compounds in the Context of Speech-to-Speech Translation. In: Král, P., Matoušek, V. (eds) Text, Speech, and Dialogue. TSD 2015. Lecture Notes in Computer Science(), vol 9302. Springer, Cham. https://doi.org/10.1007/978-3-319-24033-6_60
Download citation
DOI: https://doi.org/10.1007/978-3-319-24033-6_60
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-24032-9
Online ISBN: 978-3-319-24033-6
eBook Packages: Computer ScienceComputer Science (R0)