Myle Ott

Publications
Influence

RoBERTa: A Robustly Optimized BERT Pretraining Approach

Y. Liu, Myle Ott, +7 authors Veselin Stoyanov
Computer Science
ArXiv
26 July 2019

We present a replication study of BERT pretraining (Devlin et al., 2019) that carefully measures the impact of many key hyperparameters and training data size. Expand

2,214
697
PDF

Finding Deceptive Opinion Spam by Any Stretch of the Imagination

Myle Ott, Yejin Choi, Claire Cardie, J. Hancock
Computer Science
ACL
19 June 2011

In this work we study deceptive opinion spam---fictitious opinions that have been deliberately written to sound authentic, in order to deceive the reader. Expand

Unsupervised Cross-lingual Representation Learning at Scale

Alexis Conneau, Kartikay Khandelwal, +7 authors Veselin Stoyanov
Computer Science
ACL
5 November 2019

We present XLM-R a transformer-based multilingual masked language model pre-trained on one hundred languages, which obtains state-of-the-art performance on cross-lingual classification, sequence labeling and question answering. Expand

Phrase-Based & Neural Unsupervised Machine Translation

Guillaume Lample, Myle Ott, Alexis Conneau, Ludovic Denoyer, Marc'Aurelio Ranzato
Computer Science
EMNLP
20 April 2018

We propose two model variants, a neural and a phrase-based model. Expand

fairseq: A Fast, Extensible Toolkit for Sequence Modeling

Myle Ott, Sergey Edunov, +5 authors M. Auli
Computer Science
NAACL-HLT
1 April 2019

We present FAIRSEQ, an open-source sequence modeling toolkit written in PyTorch that is fast, extensible, and useful for both research and production. Expand

Understanding Back-Translation at Scale

Sergey Edunov, Myle Ott, M. Auli, David Grangier
Computer Science
EMNLP
1 August 2018

An effective method to improve neural machine translation with monolingual data is to augment the parallel training corpus with back-translations of target language sentences. Expand

Scaling Neural Machine Translation

Myle Ott, Sergey Edunov, David Grangier, M. Auli
Computer Science
WMT
1 June 2018

This paper shows that reduced precision and large batch training can speedup training by nearly 5x on a single 8-GPU machine with careful tuning and implementation. Expand

Negative Deceptive Opinion Spam

Myle Ott, Claire Cardie, J. Hancock
Computer Science
HLT-NAACL
1 June 2013

The rising influence of user-generated online reviews has led to growing incentive for businesses to solicit and manufacture DECEPTIVE OPINION SPAM—fictitious reviews that have been deliberately written to sound authentic and deceive the reader. Expand

Towards a General Rule for Identifying Deceptive Opinion Spam

J. Li, Myle Ott, Claire Cardie, E. Hovy
Computer Science
ACL
1 June 2014

We explore generalized approaches for identifying online deceptive opinion spam based on a new gold standard dataset, which is comprised of data from three different domains ( Hotel, Restaurant, Doctor), each of which contains three types of reviews, i.e. customer generated truthful reviews, Turker generated deceptive reviews and employee (domain-expert)generated deceptive reviews. Expand

Classical Structured Prediction Losses for Sequence to Sequence Learning

Sergey Edunov, Myle Ott, M. Auli, David Grangier, Marc'Aurelio Ranzato
Computer Science
NAACL-HLT
14 November 2017

We survey a range of classical objective functions that have been widely used to train linear models for structured prediction and apply them to neural sequence to sequence models. Expand

Recommended Authors