Search Results for author:
Found 142 papers, 29 papers with code
Statistical Power and Translationese in Machine Translation Evaluation
In addition, we provide a re-evaluation of a past machine translation evaluation claiming human-parity of MT.
A Neural Verb Lexicon Model with Source-side Syntactic Context for String-to-Tree Machine Translation
String-to-tree MT systems translate verbs without lexical or syntactic context on the source side and with limited target-side context.
Learning Curricula for Multilingual Neural Machine Translation Training
Low-resource Multilingual Neural Machine Translation (MNMT) is typically tasked with improving the translation performance on one or more language pairs with the aid of high-resource language pairs.
Dual Conditional Cross Entropy Scores and LASER Similarity Scores for the WMT20 Parallel Corpus Filtering Shared Task
This paper describes our submission to the WMT20 Parallel Corpus Filtering and Alignment for Low-Resource Conditions Shared Task.
An exploratory approach to the Parallel Corpus Filtering shared task WMT20
In this document we describe our submission to the parallel corpus filtering task using multilingual word embedding, language models and an ensemble of pre and post filtering rules.
Findings of the WMT 2020 Shared Task on Parallel Corpus Filtering and Alignment
Following two preceding WMT Shared Task on Parallel Corpus Filtering (Koehn et al., 2018, 2019), we posed again the challenge of assigning sentence-level quality scores for very noisy corpora of sentence pairs crawled from the web, with the goal of sub-selecting the highest-quality data to be used to train ma-chine translation systems.
An Alignment-Based Approach to Semi-Supervised Bilingual Lexicon Induction with Small Parallel Corpora
Aimed at generating a seed lexicon for use in downstream natural language tasks and unsupervised methods for bilingual lexicon induction have received much attention in the academic literature recently.
Findings of the WMT 2020 Shared Task on Machine Translation Robustness
We report the findings of the second edition of the shared task on improving robustness in Machine Translation (MT).
Facebook AI’s WMT21 News Translation Task Submission
We describe Facebook’s multilingual model submission to the WMT2021 shared task on news translation.
Machine Translation Quality and Post-Editor Productivity
We assessed how different machine translation (MT) systems affect the post-editing (PE) process and product of professional English–Spanish translators.
Findings of the WMT Shared Task on Machine Translation Using Terminologies
Language domains that require very careful use of terminology are abundant and reflect a significant part of the translation industry.
Neural Interactive Translation Prediction
We present an interactive translation prediction method based on neural machine translation.
Embedding-Enhanced GIZA++: Improving Low-Resource Word Alignment Using Embeddings
A popular natural language processing task decades ago, word alignment has been dominated until recently by GIZA++, a statistical method based on the 30-year-old IBM models.
Findings of the 2021 Conference on Machine Translation (WMT21)
This paper presents the results of the newstranslation task, the multilingual low-resourcetranslation for Indo-European languages, thetriangular translation task, and the automaticpost-editing task organised as part of the Con-ference on Machine Translation (WMT) 2021. In the news task, participants were asked tobuild machine translation systems for any of10 language pairs, to be evaluated on test setsconsisting mainly of news stories.
Findings of the WMT 2023 Shared Task on Discourse-Level Literary Translation: A Fresh Orb in the Cosmos of LLMs
To foster progress in this domain, we hold a new shared task at WMT 2023, the first edition of the Discourse-Level Literary Translation.
Narrowing the Gap between Zero- and Few-shot Machine Translation by Matching Styles
Large language models trained primarily in a monolingual setting have demonstrated their ability to generalize to machine translation using zero- and few-shot examples with in-context learning.
Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models
Text generation models are notoriously vulnerable to errors in the training data.
Condensing Multilingual Knowledge with Lightweight Language-Specific Modules
Incorporating language-specific (LS) modules is a proven method to boost performance in multilingual machine translation.
Multilingual Pixel Representations for Translation and Effective Cross-lingual Transfer
We introduce and demonstrate how to effectively train multilingual machine translation models with pixel representations.
Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal Transport
Bilingual lexicons form a critical component of various natural language processing applications, including unsupervised and semisupervised machine translation and crosslingual information retrieval.
IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces
The ability to extract high-quality translation dictionaries from monolingual word embedding spaces depends critically on the geometric similarity of the spaces -- their degree of "isomorphism."
Multilingual Representation Distillation with Contrastive Learning
Multilingual sentence representations from large models encode semantic information from two or more languages and can be used for different cross-lingual information retrieval and matching tasks.
Bitext Mining for Low-Resource Languages via Contrastive Learning
Mining high-quality bitexts for low-resource languages is challenging.
No Language Left Behind: Scaling Human-Centered Machine Translation
Driven by the goal of eradicating language barriers on a global scale, machine translation has solidified itself as a key focus of artificial intelligence research today.
Ranked #1 on
Machine Translation
on IWSLT2015 English-Vietnamese
(SacreBLEU metric)
The Importance of Being Parameters: An Intra-Distillation Method for Serious Gains
We first highlight the large sensitivity (contribution) gap among high-sensitivity and low-sensitivity parameters and show that the model generalization performance can be significantly improved after balancing the contribution of all parameters.
Consistent Human Evaluation of Machine Translation across Language Pairs
Obtaining meaningful quality scores for machine translation systems through human evaluation remains a challenge given the high variability between human evaluators, partly due to subjective expectations for translation quality for different language pairs.
Learn To Remember: Transformer with Recurrent Memory for Document-Level Machine Translation
We conduct experiments on three popular datasets for document-level machine translation and our model has an average improvement of 0. 91 s-BLEU over the sentence-level baseline.
Data Selection Curriculum for Neural Machine Translation
In this work, we introduce a two-stage curriculum training framework for NMT where we fine-tune a base NMT model on subsets of data, selected by both deterministic scoring using pre-trained methods and online scoring that considers prediction scores of the emerging NMT model.
Alternative Input Signals Ease Transfer in Multilingual Machine Translation
Further, we find that incorporating alternative inputs via self-ensemble can be particularly effective when training set is small, leading to +5 BLEU when only 5% of the total training data is accessible.
Doubly-Trained Adversarial Data Augmentation for Neural Machine Translation
Neural Machine Translation (NMT) models are known to suffer from noisy inputs.
Contrastive Clustering to Mine Pseudo Parallel Data for Unsupervised Translation
Modern unsupervised machine translation systems mostly train their models by generating synthetic parallel training data from large unlabeled monolingual corpora of different languages through various means, such as iterative back-translation.
An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from Word Embedding Spaces
Alternatively, word embeddings may be understood as nodes in a weighted graph.
The JHU-Microsoft Submission for WMT21 Quality Estimation Shared Task
This paper presents the JHU-Microsoft joint submission for WMT 2021 quality estimation shared task.
Levenshtein Training for Word-level Quality Estimation
We propose a novel scheme to use the Levenshtein Transformer to perform the task of word-level quality estimation.
Facebook AI WMT21 News Translation Task Submission
We describe Facebook's multilingual model submission to the WMT2021 shared task on news translation.
Cross-Lingual BERT Contextual Embedding Space Mapping with Isotropic and Isometric Conditions
Typically, a linearly orthogonal transformation mapping is learned by aligning static type-level embeddings to build a shared semantic space.
On the Evaluation of Machine Translation for Terminology Consistency
As neural machine translation (NMT) systems become an important part of professional translator pipelines, a growing body of work focuses on combining NMT with terminologies.
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-quality machine translation systems for low-resource languages.
Embedding-Enhanced Giza++: Improving Alignment in Low- and High- Resource Scenarios Using Embedding Space Geometry
In the lowest-resource setting, we outperform GIZA++ by 8. 5, 10. 9, and 12 AER for Ro-En, De-En, and En-Fr, respectively.
XLEnt: Mining a Large Cross-lingual Entity Dataset with Lexical-Semantic-Phonetic Word Alignment
Cross-lingual named-entity lexica are an important resource to multilingual NLP tasks such as machine translation and cross-lingual wikification.
Evaluating Saliency Methods for Neural Language Models
Saliency methods are widely used to interpret neural network predictions, but different variants of saliency methods often disagree even on the interpretations of the same prediction made by the same model.
Learning Feature Weights using Reward Modeling for Denoising Parallel Corpora
These feature weights which are optimized directly for the task of improving translation performance, are used to score and filter sentences in the noisy corpora more effectively.
Learning Policies for Multilingual Training of Neural Machine Translation Systems
Low-resource Multilingual Neural Machine Translation (MNMT) is typically tasked with improving the translation performance on one or more language pairs with the aid of high-resource language pairs.
Zero-Shot Cross-Lingual Dependency Parsing through Contextual Embedding Transformation
Linear embedding transformation has been shown to be effective for zero-shot cross-lingual transfer tasks and achieve surprisingly promising results.
Findings of the 2020 Conference on Machine Translation (WMT20)
In the news task, participants were asked to build machine translation systems for any of 11 language pairs, to be evaluated on test sets consisting mainly of news stories.
SimulMT to SimulST: Adapting Simultaneous Text Translation to End-to-End Simultaneous Speech Translation
Simultaneous text translation and end-to-end speech translation have recently made great progress but little work has combined these tasks together.
Streaming Simultaneous Speech Translation with Augmented Memory Transformer
Transformer-based models have achieved state-of-the-art performance on speech translation tasks.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
TICO-19: the Translation Initiative for Covid-19
Further, the team is converting the test and development data into translation memories (TMXs) that can be used by localizers from and to any of the languages.
ParaCrawl: Web-Scale Acquisition of Parallel Corpora
We report on methods to create the largest publicly available parallel corpora by crawling the web, using open source software.
Simulated Multiple Reference Training Improves Low-Resource Machine Translation
Many valid translations exist for a given sentence, yet machine translation (MT) is trained with a single reference translation, exacerbating data sparsity in low-resource settings.
Exploiting Sentence Order in Document Alignment
We present a simple document alignment method that incorporates sentence order information in both candidate generation and candidate re-scoring.
When Does Unsupervised Machine Translation Work?
We additionally find that unsupervised MT performance declines when source and target languages use different scripts, and observe very poor performance on authentic low-resource language pairs.
CCAligned: A Massive Collection of Cross-Lingual Web-Document Pairs
We mine sixty-eight snapshots of the Common Crawl corpus and identify web document pairs that are translations of each other.
Spelling-Aware Construction of Macaronic Texts for Teaching Foreign-Language Vocabulary
We present a machine foreign-language teacher that modifies text in a student{'}s native language (L1) by replacing some word tokens with glosses in a foreign language (L2), in such a way that the student can acquire L2 vocabulary simply by reading the resulting macaronic text.
HABLex: Human Annotated Bilingual Lexicons for Experiments in Machine Translation
Bilingual lexicons are valuable resources used by professional human translators.
Vecalign: Improved Sentence Alignment in Linear Time and Space
It substantially outperforms the popular Hunalign toolkit at recovering Bible verse alignments in medium- to low-resource language pairs, and it improves downstream MT quality by 1. 7 and 1. 6 BLEU in Sinhala-English and Nepali-English, respectively, compared to the Hunalign-based Paracrawl pipeline.
The FLORES Evaluation Datasets for Low-Resource Machine Translation: Nepali--English and Sinhala--English
For machine translation, a vast majority of language pairs in the world are considered low-resource because they have little parallel data available.
Findings of the 2019 Conference on Machine Translation (WMT19)
This paper presents the results of the premier shared task organized alongside the Conference on Machine Translation (WMT) 2019.
Findings of the WMT 2019 Shared Task on Parallel Corpus Filtering for Low-Resource Conditions
Following the WMT 2018 Shared Task on Parallel Corpus Filtering, we posed the challenge of assigning sentence-level quality scores for very noisy corpora of sentence pairs crawled from the web, with the goal of sub-selecting 2{\%} and 10{\%} of the highest-quality data to be used to train machine translation systems.
Simple Construction of Mixed-Language Texts for Vocabulary Learning
We accomplish this by modifying a cloze language model to incrementally learn new vocabulary items, and use this language model as a proxy for the word guessing and learning ability of real students.
Johns Hopkins University Submission for WMT News Translation Task
We describe the work of Johns Hopkins University for the shared task of news translation organized by the Fourth Conference on Machine Translation (2019).
De-Mixing Sentiment from Code-Mixed Text
The Collective Encoder captures the overall sentiment of the sentence, while the Specific Encoder utilizes an attention mechanism in order to focus on individual sentiment-bearing sub-words.
Findings of the First Shared Task on Machine Translation Robustness
We share the findings of the first shared task on improving robustness of Machine Translation (MT).
Saliency-driven Word Alignment Interpretation for Neural Machine Translation
Despite their original goal to jointly learn to align and translate, Neural Machine Translation (NMT) models, especially Transformer, are often perceived as not learning interpretable word alignments.
Translationese in Machine Translation Evaluation
Finally, we provide a comprehensive check-list for future machine translation evaluation.
Low-Resource Corpus Filtering using Multilingual Sentence Embeddings
In this paper, we describe our submission to the WMT19 low-resource parallel corpus filtering shared task.
Overcoming Catastrophic Forgetting During Domain Adaptation of Neural Machine Translation
Continued training is an effective method for domain adaptation in neural machine translation.
Parallelizable Stack Long Short-Term Memory
Stack Long Short-Term Memory (StackLSTM) is useful for various applications such as parsing and string-to-tree neural machine translation, but it is also known to be notoriously difficult to parallelize for GPU training due to the fact that the computations are dependent on discrete operations.
The FLoRes Evaluation Datasets for Low-Resource Machine Translation: Nepali-English and Sinhala-English
For machine translation, a vast majority of language pairs in the world are considered low-resource because they have little parallel data available.
Context and Copying in Neural Machine Translation
In this work, we show that they learn to copy words based on both the context in which the words appear as well as features of the words themselves.
Findings of the 2018 Conference on Machine Translation (WMT18)
This paper presents the results of the premier shared task organized alongside the Conference on Machine Translation (WMT) 2018.
The JHU Parallel Corpus Filtering Systems for WMT 2018
This work describes our submission to the WMT18 Parallel Corpus Filtering shared task.
The JHU Machine Translation Systems for WMT 2018
We report on the efforts of the Johns Hopkins University to develop neural machine translation systems for the shared task for news translation organized around the Conference for Machine Translation (WMT) 2018.
Findings of the WMT 2018 Shared Task on Parallel Corpus Filtering
We posed the shared task of assigning sentence-level quality scores for a very noisy corpus of sentence pairs crawled from the web, with the goal of sub-selecting 1{\%} and 10{\%} of high-quality data to be used to train machine translation systems.
Freezing Subnetworks to Analyze Domain Adaptation in Neural Machine Translation
To better understand the effectiveness of continued training, we analyze the major components of a neural machine translation system (the encoder, decoder, and each embedding space) and consider each component's contribution to, and capacity for, domain adaptation.
Character-Aware Decoder for Translation into Morphologically Rich Languages
Neural machine translation (NMT) systems operate primarily on words (or sub-words), ignoring lower-level patterns of morphology.
Document-Level Adaptation for Neural Machine Translation
It is common practice to adapt machine translation systems to novel domains, but even a well-adapted system may be able to perform better on a particular document if it were to learn from a translator{'}s corrections within the document itself.
Iterative Back-Translation for Neural Machine Translation
We present iterative back-translation, a method for generating increasingly better synthetic parallel data from monolingual data to train neural machine translation systems.
Regularized Training Objective for Continued Training for Domain Adaptation in Neural Machine Translation
Supervised domain adaptation{---}where a large generic corpus and a smaller in-domain corpus are both available for training{---}is a challenge for neural machine translation (NMT).
On the Impact of Various Types of Noise on Neural Machine Translation
We examine how various types of noise in the parallel training data impact the quality of neural machine translation systems.
Neural Lattice Search for Domain Adaptation in Machine Translation
Domain adaptation is a major challenge for neural machine translation (NMT).
CADET: Computer Assisted Discovery Extraction and Translation
It combines a multitude of analytics together with a flexible environment for customizing the workflow for different users.
Neural Machine Translation
Draft of textbook chapter on neural machine translation.
Ranked #1 on
Machine Translation
on 20NEWS
(using extra training data)
Zipporah: a Fast and Scalable Data Cleaning System for Noisy Web-Crawled Parallel Corpora
We introduce Zipporah, a fast and scalable data cleaning system.
Knowledge Tracing in Sequential Learning of Inflected Vocabulary
We present a feature-rich knowledge tracing method that captures a student{'}s acquisition and retention of knowledge during a foreign language phrase learning task.
Six Challenges for Neural Machine Translation
We explore six challenges for neural machine translation: domain mismatch, amount of training data, rare words, long sentences, word alignment, and beam search.
Predicting Target Language CCG Supertags Improves Neural Machine Translation
Our results on WMT data show that explicitly modeling target-syntax improves machine translation quality for German->English, a high-resource pair, and for Romanian->English, a low-resource pair and also several syntactic phenomena including prepositional phrase attachment.
Europarl: A Parallel Corpus for Statistical Machine Translation
We collected a corpus of parallel text in 11 languages from the proceedings of the European Parliament, which are published on the web.
Statistical Phrase-Based Translation
We propose a new phrase-based translation model and decoding algorithm that enables us to evaluate and compare several, previously proposed phrase-based translation models.
