Search Results for author:
Found 68 papers, 21 papers with code
Automatic Construction of Morphologically Motivated Translation Models for Highly Inflected, Low-Resource Languages
Statistical Machine Translation (SMT) of highly inflected, low-resource languages suffers from the problem of low bitext availability, which is exacerbated by large inflectional paradigms.
ParBLEU: Augmenting Metrics with Automatic Paraphrases for the WMT’20 Metrics Shared Task
We describe parBLEU, parCHRF++, and parESIM, which augment baseline metrics with automatically generated paraphrases produced by PRISM (Thompson and Post, 2020a), a multilingual neural machine translation system.
On the Evaluation of Machine Translation n-best Lists
The first and principal contribution is an evaluation measure that characterizes the translation quality of an entire n-best list by asking whether many of the valid translations are placed near the top of the list.
SLIDE: Reference-free Evaluation for Machine Translation using a Sliding Document Window
This suggests that source context may provide the same information as a human reference.
SOTASTREAM: A Streaming Approach to Machine Translation Training
Many machine translation toolkits make use of a data preparation step wherein raw data is transformed into a tensor format that can be used directly by the trainer.
Do GPTs Produce Less Literal Translations?
On the task of Machine Translation (MT), multiple works have investigated few-shot prompting mechanisms to elicit better translations from LLMs.
Pixel Representations for Multilingual Translation and Data-efficient Cross-lingual Transfer
We introduce and demonstrate how to effectively train multilingual machine translation models with pixel representations.
Escaping the sentence-level paradigm in machine translation
It is well-known that document context is vital for resolving a range of translation ambiguities, and in fact the document setting is the most natural setting for nearly all translation.
Operationalizing Specifications, In Addition to Test Sets for Evaluating Constrained Generative Models
More concretely, while the associated utility and methods of interacting with generative models have expanded, a similar expansion has not been observed in their evaluation practices.
Additive Interventions Yield Robust Multi-Domain Machine Translation Models
Additive interventions are a recently-proposed mechanism for controlling target-side attributes in neural machine translation.
SALTED: A Framework for SAlient Long-Tail Translation Error Detection
Traditional machine translation (MT) metrics provide an average measure of translation quality that is insensitive to the long tail of behavioral problems in MT.
Large-Scale Streaming End-to-End Speech Translation with Neural Transducers
Neural transducers have been widely used in automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
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.
A unified approach to sentence segmentation of punctuated text in many languages
The sentence is a fundamental unit of text processing.
Robust Open-Vocabulary Translation from Visual Text Representations
Machine translation models have discrete vocabularies and commonly use subword segmentation techniques to achieve an 'open vocabulary.'
The Multilingual TEDx Corpus for Speech Recognition and Translation
We present the Multilingual TEDx corpus, built to support speech recognition (ASR) and speech translation (ST) research across many non-English source languages.
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.
Paraphrase Generation as Zero-Shot Multilingual Translation: Disentangling Semantic Similarity from Lexical and Syntactic Diversity
Recent work has shown that a multilingual neural machine translation (NMT) model can be used to judge how well a sentence paraphrases another sentence in the same language (Thompson and Post, 2020); however, attempting to generate paraphrases from such a model using standard beam search produces trivial copies or near copies.
The JHU Submission to the 2020 Duolingo Shared Task on Simultaneous Translation and Paraphrase for Language Education
This paper presents the Johns Hopkins University submission to the 2020 Duolingo Shared Task on Simultaneous Translation and Paraphrase for Language Education (STAPLE).
Benchmarking Neural and Statistical Machine Translation on Low-Resource African Languages
In this study, we benchmark state of the art statistical and neural machine translation systems on two African languages which do not have large amounts of resources: Somali and Swahili.
The Johns Hopkins University Bible Corpus: 1600+ Tongues for Typological Exploration
The corpus consists of over 4000 unique translations of the Christian Bible and counting.
Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasing
We frame the task of machine translation evaluation as one of scoring machine translation output with a sequence-to-sequence paraphraser, conditioned on a human reference.
A Study in Improving BLEU Reference Coverage with Diverse Automatic Paraphrasing
We investigate a long-perceived shortcoming in the typical use of BLEU: its reliance on a single reference.
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.
Large-Scale, Diverse, Paraphrastic Bitexts via Sampling and Clustering
Producing diverse paraphrases of a sentence is a challenging task.
A Discriminative Neural Model for Cross-Lingual Word Alignment
We introduce a novel discriminative word alignment model, which we integrate into a Transformer-based machine translation model.
JHU 2019 Robustness Task System Description
We describe the JHU submissions to the French{--}English, Japanese{--}English, and English{--}Japanese Robustness Task at WMT 2019.
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.
Improved Lexically Constrained Decoding for Translation and Monolingual Rewriting
Lexically-constrained sequence decoding allows for explicit positive or negative phrase-based constraints to be placed on target output strings in generation tasks such as machine translation or monolingual text rewriting.
Membership Inference Attacks on Sequence-to-Sequence Models: Is My Data In Your Machine Translation System?
Data privacy is an important issue for "machine learning as a service" providers.
ParaBank: Monolingual Bitext Generation and Sentential Paraphrasing via Lexically-constrained Neural Machine Translation
We present ParaBank, a large-scale English paraphrase dataset that surpasses prior work in both quantity and quality.
A Call for Clarity in Reporting BLEU Scores
The field of machine translation faces an under-recognized problem because of inconsistency in the reporting of scores from its dominant metric.
Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation
The end-to-end nature of neural machine translation (NMT) removes many ways of manually guiding the translation process that were available in older paradigms.
Sockeye: A Toolkit for Neural Machine Translation
Written in Python and built on MXNet, the toolkit offers scalable training and inference for the three most prominent encoder-decoder architectures: attentional recurrent neural networks, self-attentional transformers, and fully convolutional networks.
Neural Lattice Search for Domain Adaptation in Machine Translation
Domain adaptation is a major challenge for neural machine translation (NMT).
Grammatical Error Correction with Neural Reinforcement Learning
We propose a neural encoder-decoder model with reinforcement learning (NRL) for grammatical error correction (GEC).
Error-repair Dependency Parsing for Ungrammatical Texts
We propose a new dependency parsing scheme which jointly parses a sentence and repairs grammatical errors by extending the non-directional transition-based formalism of Goldberg and Elhadad (2010) with three additional actions: SUBSTITUTE, DELETE, INSERT.
Using of heterogeneous corpora for training of an ASR system
The paper summarizes the development of the LVCSR system built as a part of the Pashto speech-translation system at the SCALE (Summer Camp for Applied Language Exploration) 2015 workshop on "Speech-to-text-translation for low-resource languages".
A Rich Morphological Tagger for English: Exploring the Cross-Linguistic Tradeoff Between Morphology and Syntax
A traditional claim in linguistics is that all human languages are equally expressive{---}able to convey the same wide range of meanings.
Robsut Wrod Reocginiton via semi-Character Recurrent Neural Network
Inspired by the findings from the Cmabrigde Uinervtisy effect, we propose a word recognition model based on a semi-character level recurrent neural network (scRNN).
GLEU Without Tuning
The GLEU metric was proposed for evaluating grammatical error corrections using n-gram overlap with a set of reference sentences, as opposed to precision/recall of specific annotated errors (Napoles et al., 2015).
Reassessing the Goals of Grammatical Error Correction: Fluency Instead of Grammaticality
The field of grammatical error correction (GEC) has grown substantially in recent years, with research directed at both evaluation metrics and improved system performance against those metrics.
A Wikipedia-based Corpus for Contextualized Machine Translation
We describe a corpus for target-contextualized machine translation (MT), where the task is to improve the translation of source documents using language models built over presumably related documents in the target language.
The Language Demographics of Amazon Mechanical Turk
We present a large scale study of the languages spoken by bilingual workers on Mechanical Turk (MTurk).
Learning to translate with products of novices: a suite of open-ended challenge problems for teaching MT
Machine translation (MT) draws from several different disciplines, making it a complex subject to teach.
