- Library Home /
- Search Collections /
- Open Collections /
- Browse Collections /
- UBC Theses and Dissertations /
- Investigating the impact of normalizing flows on latent...
Open Collections
UBC Theses and Dissertations
UBC Theses and Dissertations
Investigating the impact of normalizing flows on latent variable machine translation Przystupa, Michael
Abstract
Natural language processing (NLP) has pervasive applications in everyday life, and has recently witnessed rapid progress. Incorporating latent variables in NLP systems can allow for explicit representations of certain types of information. In neural machine translation systems, for example, latent variables have the potential of enhancing semantic representations. This could help improve general translation quality. Previous work has focused on using variational inference with diagonal covariance Gaussian distributions, which we hypothesize cannot sufficiently encode latent factors of language which could exhibit multi-modal distributive behavior. Normalizing flows are an approach that enables more flexible posterior distribution estimates by introducing a change of variables with invertible functions. They have previously been successfully used in computer vision to enable more flexible posterior distributions of image data. In this work, we investigate the impact of normalizing flows in autoregressive neural machine translation systems. We do so in the context of two currently successful approaches, attention mechanisms, and language models. Our results suggest that normalizing flows can improve translation quality in some scenarios, and require certain modelling assumptions to achieve such improvements.
Item Metadata
Title |
Investigating the impact of normalizing flows on latent variable machine translation
|
Creator | |
Publisher |
University of British Columbia
|
Date Issued |
2020
|
Description |
Natural language processing (NLP) has pervasive applications in everyday life, and has recently witnessed rapid progress. Incorporating latent variables in NLP systems can allow for explicit representations of certain types of information. In neural machine translation systems, for example, latent variables have the potential of enhancing semantic representations. This could help improve general translation quality. Previous work has focused on using variational inference with diagonal covariance Gaussian distributions, which we hypothesize cannot sufficiently encode latent factors of language which could exhibit multi-modal distributive behavior. Normalizing flows are an approach that enables more flexible posterior distribution estimates by introducing a change of variables with invertible functions. They have previously been successfully used in computer vision to enable more flexible posterior distributions of image data. In this work, we investigate the impact of normalizing flows in autoregressive neural machine translation systems. We do so in the context of two currently successful approaches, attention mechanisms, and language models. Our results suggest that normalizing flows can improve translation quality in some scenarios, and require certain modelling assumptions to achieve such improvements.
|
Genre | |
Type | |
Language |
eng
|
Date Available |
2020-02-26
|
Provider |
Vancouver : University of British Columbia Library
|
Rights |
Attribution-NonCommercial-NoDerivatives 4.0 International
|
DOI |
10.14288/1.0388739
|
URI | |
Degree | |
Program | |
Affiliation | |
Degree Grantor |
University of British Columbia
|
Graduation Date |
2020-05
|
Campus | |
Scholarly Level |
Graduate
|
Rights URI | |
Aggregated Source Repository |
DSpace
|
Item Media
Item Citations and Data
Rights
Attribution-NonCommercial-NoDerivatives 4.0 International