Cornell University
Learning Deep Representations for Low-Resource Cross-Lingual Natural Language Processing
Abstract
dc:description.abstractLarge-scale annotated datasets are an indispensable ingredient of modern Natural Language Processing (NLP) systems. Unfortunately, most labeled data is only available in a handful of languages; for the vast majority of human languages, few or no annotations exist to empower automated NLP technology. Cross-lingual transfer learning enables the training of NLP models using labeled data from other languages, which has become a viable technique for building NLP systems for a wider spectrum of world languages without the prohibitive need for data annotation. Existing methods for cross-lingual transfer learning, however, require cross-lingual resources (e.g. machine translation systems) to transfer models across languages. These methods are hence futile for many low-resource languages without such resources. This dissertation proposes a deep representation learning approach for low-resource cross-lingual transfer learning, and presents several models that (i) progressively remove the need for cross-lingual supervision, and (ii) go beyond the standard bilingual transfer case into the more realistic multilingual setting. By addressing key challenges in two important sub-problems, namely multilingual lexical representation and model transfer, the proposed models in this dissertation are able to transfer NLP models across multiple languages with no cross-lingual resources.
Degree
thesis:*- Name thesis:degree_name
- Ph.D., Computer Science
- Level thesis:degree_level
- Doctor of Philosophy
- Discipline thesis:degree_discipline
- Computer Science
- Grantor
- Cornell University
- Year dc:date.issued
- 2019
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Chen, Xilun
- Chair dc:contributor.chair
-
- Cardie, Claire T.
- Committee members dc:contributor.committeemember
-
- Kleinberg, Jon M.
- Hopcroft, John E.
Subjects
dc:subject × 8Rights
dc:rights- Statement dc:rights
-
- Attribution 4.0 International
- Licence dc:rights.uri
- Language dc:language.iso
- en_US
Identifiers
dc:identifier.*- Dc Identifier Bibid
- 11050308
- Dc Identifier Other
-
ProQuest Submission ID: 11362
ProQuest Publication ID: 13864426