research
∙
05/23/2023
Pixel Representations for Multilingual Translation and Data-efficient Cross-lingual Transfer
We introduce and demonstrate how to effectively train multilingual machi...
share
research
∙
05/23/2023
Condensing Multilingual Knowledge with Lightweight Language-Specific Modules
Incorporating language-specific (LS) modules is a proven method to boost...
research
∙
10/25/2022
Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal Transport
Bilingual lexicons form a critical component of various natural language...
research
∙
10/11/2022
IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces
The ability to extract high-quality translation dictionaries from monoli...
research
∙
10/10/2022
Multilingual Representation Distillation with Contrastive Learning
Multilingual sentence representations from large models can encode seman...
research
∙
08/23/2022
Bitext Mining for Low-Resource Languages via Contrastive Learning
Mining high-quality bitexts for low-resource languages is challenging. T...
research
∙
07/11/2022
No Language Left Behind: Scaling Human-Centered Machine Translation
Driven by the goal of eradicating language barriers on a global scale, m...
research
∙
05/23/2022
The Importance of Being Parameters: An Intra-Distillation Method for Serious Gains
Recent model pruning methods have demonstrated the ability to remove red...
research
∙
05/17/2022
Consistent Human Evaluation of Machine Translation across Language Pairs
Obtaining meaningful quality scores for machine translation systems thro...
research
∙
03/25/2022
Data Selection Curriculum for Neural Machine Translation
Neural Machine Translation (NMT) models are typically trained on heterog...
research
∙
10/15/2021
Alternative Input Signals Ease Transfer in Multilingual Machine Translation
Recent work in multilingual machine translation (MMT) has focused on the...
research
∙
10/12/2021
Doubly-Trained Adversarial Data Augmentation for Neural Machine Translation
Neural Machine Translation (NMT) models are known to suffer from noisy i...
research
∙
09/26/2021
An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from Word Embedding Spaces
Much recent work in bilingual lexicon induction (BLI) views word embeddi...
research
∙
09/17/2021
The JHU-Microsoft Submission for WMT21 Quality Estimation Shared Task
This paper presents the JHU-Microsoft joint submission for WMT 2021 qual...
research
∙
09/12/2021
Levenshtein Training for Word-level Quality Estimation
We propose a novel scheme to use the Levenshtein Transformer to perform ...
research
∙
08/06/2021
Facebook AI WMT21 News Translation Task Submission
We describe Facebook's multilingual model submission to the WMT2021 shar...
research
∙
07/19/2021
Cross-Lingual BERT Contextual Embedding Space Mapping with Isotropic and Isometric Conditions
Typically, a linearly orthogonal transformation mapping is learned by al...
research
∙
06/22/2021
On the Evaluation of Machine Translation for Terminology Consistency
As neural machine translation (NMT) systems become an important part of ...
research
∙
05/31/2021
Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data
The scarcity of parallel data is a major obstacle for training high-qual...
research
∙
04/18/2021
Embedding-Enhanced Giza++: Improving Alignment in Low- and High- Resource Scenarios Using Embedding Space Geometry
A popular natural language processing task decades ago, word alignment h...
research
∙
04/17/2021
XLEnt: Mining a Large Cross-lingual Entity Dataset with Lexical-Semantic-Phonetic Word Alignment
Cross-lingual named-entity lexicon are an important resource to multilin...
research
∙
04/12/2021
Evaluating Saliency Methods for Neural Language Models
Saliency methods are widely used to interpret neural network predictions...
research
∙
03/11/2021
Learning Feature Weights using Reward Modeling for Denoising Parallel Corpora
Large web-crawled corpora represent an excellent resource for improving ...
research
∙
03/11/2021
Learning Policies for Multilingual Training of Neural Machine Translation Systems
Low-resource Multilingual Neural Machine Translation (MNMT) is typically...
research
∙
03/03/2021
Zero-Shot Cross-Lingual Dependency Parsing through Contextual Embedding Transformation
Linear embedding transformation has been shown to be effective for zero-...
research
∙
11/03/2020
SimulMT to SimulST: Adapting Simultaneous Text Translation to End-to-End Simultaneous Speech Translation
Simultaneous text translation and end-to-end speech translation have rec...
research
∙
10/30/2020
Streaming Simultaneous Speech Translation with Augmented Memory Transformer
Transformer-based models have achieved state-of-the-art performance on s...
research
∙
07/03/2020
TICO-19: the Translation Initiative for Covid-19
The COVID-19 pandemic is the worst pandemic to strike the world in over ...
research
∙
04/30/2020
Simulated Multiple Reference Training Improves Low-Resource Machine Translation
Many valid translations exist for a given sentence, and yet machine tran...
research
∙
04/30/2020
Exploiting Sentence Order in Document Alignment
In this work, we exploit the simple idea that a document and its transla...
research
∙
04/12/2020
When Does Unsupervised Machine Translation Work?
Despite the reported success of unsupervised machine translation (MT), t...
research
∙
11/10/2019
A Massive Collection of Cross-Lingual Web-Document Pairs
Cross-lingual document alignment aims to identify pairs of documents in ...
research
∙
06/27/2019
Findings of the First Shared Task on Machine Translation Robustness
We share the findings of the first shared task on improving robustness o...
research
∙
06/25/2019
Saliency-driven Word Alignment Interpretation for Neural Machine Translation
Despite their original goal to jointly learn to align and translate, Neu...
research
∙
06/24/2019
Translationese in Machine Translation Evaluation
The term translationese has been used to describe the presence of unusua...
research
∙
06/20/2019
Low-Resource Corpus Filtering using Multilingual Sentence Embeddings
In this paper, we describe our submission to the WMT19 low-resource para...
research
∙
04/06/2019
Parallelizable Stack Long Short-Term Memory
Stack Long Short-Term Memory (StackLSTM) is useful for various applicati...
research
∙
02/04/2019
Two New Evaluation Datasets for Low-Resource Machine Translation: Nepali-English and Sinhala-English
The vast majority of language pairs in the world are low-resource becaus...
research
∙
09/14/2018
Freezing Subnetworks to Analyze Domain Adaptation in Neural Machine Translation
To better understand the effectiveness of continued training, we analyze...
research
∙
09/06/2018
Character-Aware Decoder for Neural Machine Translation
Standard neural machine translation (NMT) systems operate primarily on w...
research
∙
05/31/2018
On the Impact of Various Types of Noise on Neural Machine Translation
We examine how various types of noise in the parallel training data impa...
research
∙
09/22/2017
Neural Machine Translation
Draft of textbook chapter on neural machine translation. a comprehensive...
research
∙
06/12/2017
Six Challenges for Neural Machine Translation
We explore six challenges for neural machine translation: domain mismatc...
research
∙
02/03/2017