1 |
Pushing the right buttons: adversarial evaluation of quality estimation
|
|
|
|
In: Proceedings of the Sixth Conference on Machine Translation ; 625 ; 638 (2022)
|
|
BASE
|
|
Show details
|
|
2 |
Learning Feature Weights using Reward Modeling for Denoising Parallel Corpora ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Learning Feature Weights using Reward Modeling for Denoising Parallel Corpora ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Cross-Lingual BERT Contextual Embedding Space Mapping with Isotropic and Isometric Conditions ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Learning Policies for Multilingual Training of Neural Machine Translation Systems ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Zero-Shot Cross-Lingual Dependency Parsing through Contextual Embedding Transformation ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Embedding-Enhanced Giza++: Improving Alignment in Low- and High- Resource Scenarios Using Embedding Space Geometry ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Alternative Input Signals Ease Transfer in Multilingual Machine Translation ...
|
|
|
|
Abstract:
Recent work in multilingual machine translation (MMT) has focused on the potential of positive transfer between languages, particularly cases where higher-resourced languages can benefit lower-resourced ones. While training an MMT model, the supervision signals learned from one language pair can be transferred to the other via the tokens shared by multiple source languages. However, the transfer is inhibited when the token overlap among source languages is small, which manifests naturally when languages use different writing systems. In this paper, we tackle inhibited transfer by augmenting the training data with alternative signals that unify different writing systems, such as phonetic, romanized, and transliterated input. We test these signals on Indic and Turkic languages, two language families where the writing systems differ but languages still share common features. Our results indicate that a straightforward multi-source self-ensemble -- training a model on a mixture of various signals and ensembling ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2110.07804 https://arxiv.org/abs/2110.07804
|
|
BASE
|
|
Hide details
|
|
11 |
An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from Word Embedding Spaces ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
XLEnt: Mining a Large Cross-lingual Entity Dataset with Lexical-Semantic-Phonetic Word Alignment ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from Word Embedding Spaces ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Findings of the 2018 conference on machine translation (WMT18)
|
|
|
|
In: Bojar, Ondřej orcid:0000-0002-0606-0050 , Federmann, Christian, Fishel, Mark, Graham, Yvette, Haddow, Barry, Huck, Matthias, Koehn, Philipp and Monz, Christof (2018) Findings of the 2018 conference on machine translation (WMT18). In: Third Conference on Machine Translation, Volume 2: Shared Task Papers, 31 Oct - 1 Nov 2018, Brussels, Belgium. (2018)
|
|
BASE
|
|
Show details
|
|
20 |
On the Impact of Various Types of Noise on Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|