Matt Post | DeepAI

DeepAI AI Chat

Featured Co-authors

Benjamin Van Durme
102 publications
Jinyu Li
100 publications
Matteo Negri
52 publications
Kevin Duh
48 publications
Marco Turchi
45 publications
Sanjeev Khudanpur
45 publications
Philipp Koehn
44 publications
Biao Zhang
37 publications
Yashesh Gaur
33 publications
Joel Tetreault
31 publications
Marcin Junczys-Dowmunt
26 publications

∙ 09/16/2023

SLIDE: Reference-free Evaluation for Machine Translation using a Sliding Document Window

Reference-based metrics that operate at the sentence level typically out...

0 Vikas Raunak, et al. ∙

∙ 08/14/2023

SOTASTREAM: A Streaming Approach to Machine Translation Training

Many machine translation toolkits make use of a data preparation step wh...

0 Matt Post, et al. ∙

∙ 05/26/2023

Do GPTs Produce Less Literal Translations?

Large Language Models (LLMs) such as GPT-3 have emerged as general-purpo...

0 Vikas Raunak, et al. ∙

∙ 05/23/2023

Pixel Representations for Multilingual Translation and Data-efficient Cross-lingual Transfer

We introduce and demonstrate how to effectively train multilingual machi...

0 Elizabeth Salesky, et al. ∙

∙ 04/25/2023

Escaping the sentence-level paradigm in machine translation

It is well-known that document context is vital for resolving a range of...

0 Matt Post, et al. ∙

∙ 11/19/2022

Operationalizing Specifications, In Addition to Test Sets for Evaluating Constrained Generative Models

In this work, we present some recommendations on the evaluation of state...

0 Vikas Raunak, et al. ∙

∙ 10/23/2022

Additive Interventions Yield Robust Multi-Domain Machine Translation Models

Additive interventions are a recently-proposed mechanism for controlling...

0 Elijah Rippeth, et al. ∙

∙ 05/20/2022

SALTED: A Framework for SAlient Long-Tail Translation Error Detection

Traditional machine translation (MT) metrics provide an average measure ...

5 Vikas Raunak, et al. ∙

∙ 04/11/2022

Large-Scale Streaming End-to-End Speech Translation with Neural Transducers

Neural transducers have been widely used in automatic speech recognition...

0 Jian Xue, et al. ∙

∙ 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...

0 Shuoyang Ding, et al. ∙

∙ 09/12/2021

Levenshtein Training for Word-level Quality Estimation

We propose a novel scheme to use the Levenshtein Transformer to perform ...

0 Shuoyang Ding, et al. ∙

∙ 04/16/2021

Robust Open-Vocabulary Translation from Visual Text Representations

Machine translation models have discrete vocabularies and commonly use s...

0 Elizabeth Salesky, et al. ∙

∙ 02/02/2021

The Multilingual TEDx Corpus for Speech Recognition and Translation

We present the Multilingual TEDx corpus, built to support speech recogni...

7 Elizabeth Salesky, et al. ∙

∙ 08/11/2020

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 (NM...

0 Brian Thompson, et al. ∙

∙ 04/30/2020

Explicit Representation of the Translation Space: Automatic Paraphrasing for Machine Translation Evaluation

Following previous work on automatic paraphrasing, we assess the feasibi...

0 Rachel Bawden, et al. ∙

∙ 04/30/2020

Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasing

We propose the use of a sequence-to-sequence paraphraser for automatic m...

0 Brian Thompson, et al. ∙

∙ 04/30/2020

Simulated Multiple Reference Training Improves Low-Resource Machine Translation

Many valid translations exist for a given sentence, and yet machine tran...

0 Huda Khayrallah, et al. ∙

∙ 09/01/2019

A Discriminative Neural Model for Cross-Lingual Word Alignment

We introduce a novel discriminative word alignment model, which we integ...

0 Elias Stengel-Eskin, et al. ∙

∙ 04/11/2019

Membership Inference Attacks on Sequence-to-Sequence Models

Data privacy is an important issue for "machine learning as a service" p...

0 Sorami Hisamoto, et al. ∙

∙ 01/11/2019

ParaBank: Monolingual Bitext Generation and Sentential Paraphrasing via Lexically-constrained Neural Machine Translation

We present ParaBank, a large-scale English paraphrase dataset that surpa...

0 J. Edward Hu, et al. ∙

∙ 04/23/2018

A Call for Clarity in Reporting BLEU Scores

The field of machine translation is blessed with new challenges resultin...

0 Matt Post, et al. ∙

∙ 04/18/2018

Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation

The end-to-end nature of neural machine translation (NMT) removes many w...

0 Matt Post, et al. ∙

∙ 12/15/2017

Sockeye: A Toolkit for Neural Machine Translation

We describe Sockeye (version 1.12), an open-source sequence-to-sequence ...

0 Felix Hieber, et al. ∙

∙ 07/02/2017

Grammatical Error Correction with Neural Reinforcement Learning

We propose a neural encoder-decoder model with reinforcement learning (N...

0 Keisuke Sakaguchi, et al. ∙

∙ 06/01/2017

Using of heterogeneous corpora for training of an ASR system

The paper summarizes the development of the LVCSR system built as a part...

0 Jan Trmal, et al. ∙

∙ 08/07/2016

Robsut Wrod Reocginiton via semi-Character Recurrent Neural Network

Language processing mechanism by humans is generally more robust than co...

0 Keisuke Sakaguchi, et al. ∙

∙ 05/09/2016

GLEU Without Tuning

The GLEU metric was proposed for evaluating grammatical error correction...

0 Courtney Napoles, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world