Cross-Lingual Word Sense Disambiguation for Low-Resource Hybrid Machine Translation

dc.contributor.authorRudnick, Alexander James
dc.date.accessioned2019-01-22T17:50:32Z
dc.date.available2019-01-22T17:50:32Z
dc.date.issued2019-01
dc.descriptionThesis (Ph.D.) - Indiana University, School of Informatics, Computing, and Engineering, 2019en
dc.description.abstractThis thesis argues that cross-lingual word sense disambiguation (CL-WSD) can be used to improve lexical selection for machine translation when translating from a resource- rich language into an under-resourced one, especially when relatively little bitext is avail- able. In CL-WSD, we perform word sense disambiguation, considering the senses of a word to be its possible translations into some target language, rather than using a sense inventory developed manually by lexicographers. Using explicitly trained classifiers that make use of source-language context and of resources for the source language can help machine translation systems make better decisions when selecting target-language words. This is especially the case when the alternative is hand-written lexical selection rules developed by researchers with linguistic knowledge of the source and target languages, but also true when lexical selection would be performed by a statistical machine translation system, when there is a relatively small amount of available target-language text for training language models. In this work, I present the Chipa system for CL-WSD and apply it to the task of translating from Spanish to Guarani and Quechua, two indigenous languages of South America. I demonstrate several extensions to the basic Chipa system, including tech- niques that allow us to benefit from the wealth of available unannotated Spanish text and existing text analysis tools for Spanish, as well as approaches for learning from bitext resources that pair Spanish with languages unrelated to our intended target lan- guages. Finally, I provide proof-of-concept integrations of Chipa with existing machine translation systems, of two completely different architectures.en
dc.identifier.urihttps://hdl.handle.net/2022/22672
dc.language.isoenen
dc.publisher[Bloomington, Ind.] : Indiana Universityen
dc.rightsCreative Commons Attribution 4.0 Internationalen
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en
dc.subjectmachine translationen
dc.subjectartificial intelligenceen
dc.subjectcomputational linguisticsen
dc.titleCross-Lingual Word Sense Disambiguation for Low-Resource Hybrid Machine Translationen
dc.typeDoctoral Dissertationen
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
dissertation.pdf
Size:
988.2 KB
Format:
Adobe Portable Document Format
Description:
If you need an accessible version of this item, please email your request to iusw@iu.edu so that they may create one and provide it to you.