1 |
Towards the Next 1000 Languages in Multilingual Machine Translation: Exploring the Synergy Between Supervised and Self-Supervised Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets
|
|
|
|
In: https://hal.inria.fr/hal-03177623 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
3 |
Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Language ID in the Wild: Unexpected Challenges on the Path to a Thousand-Language Web Text Corpus ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Investigating Multilingual NMT Representations at Scale ...
|
|
|
|
Abstract:
Multilingual Neural Machine Translation (NMT) models have yielded large empirical success in transfer learning settings. However, these black-box representations are poorly understood, and their mode of transfer remains elusive. In this work, we attempt to understand massively multilingual NMT representations (with 103 languages) using Singular Value Canonical Correlation Analysis (SVCCA), a representation similarity framework that allows us to compare representations across different languages, layers and models. Our analysis validates several empirical results and long-standing intuitions, and unveils new observations regarding how representations evolve in a multilingual translation model. We draw three major conclusions from our analysis, with implications on cross-lingual transfer learning: (i) Encoder representations of different languages cluster based on linguistic similarity, (ii) Representations of a source language learned by the encoder are dependent on the target language, and vice-versa, and ... : Paper at EMNLP 2019 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences; Machine Learning cs.LG
|
|
URL: https://dx.doi.org/10.48550/arxiv.1909.02197 https://arxiv.org/abs/1909.02197
|
|
BASE
|
|
Hide details
|
|
|
|