Search Results for author: Phillip Keung

Found 8 papers, 1 papers with code

Unsupervised Bitext Mining and Translation via Self-trained Contextual Embeddings

no code implementations15 Oct 2020 Phillip Keung, Julian Salazar, Yichao Lu, Noah A. Smith

We then improve an XLM-based unsupervised neural MT system pre-trained on Wikipedia by supplementing it with pseudo-parallel text mined from the same corpus, boosting unsupervised translation performance by up to 3. 5 BLEU on the WMT'14 French-English and WMT'16 German-English tasks and outperforming the previous state-of-the-art.

Machine Translation Sentence Embeddings +1

The Multilingual Amazon Reviews Corpus

no code implementations EMNLP 2020 Phillip Keung, Yichao Lu, György Szarvas, Noah A. Smith

We present the Multilingual Amazon Reviews Corpus (MARC), a large-scale collection of Amazon reviews for multilingual text classification.

Classification General Classification +4

Improving Non-autoregressive Neural Machine Translation with Monolingual Data

no code implementations ACL 2020 Jiawei Zhou, Phillip Keung

Non-autoregressive (NAR) neural machine translation is usually done via knowledge distillation from an autoregressive (AR) model.

Data Augmentation Knowledge Distillation +2

Don't Use English Dev: On the Zero-Shot Cross-Lingual Evaluation of Contextual Embeddings

no code implementations EMNLP 2020 Phillip Keung, Yichao Lu, Julian Salazar, Vikas Bhardwaj

Multilingual contextual embeddings have demonstrated state-of-the-art performance in zero-shot cross-lingual transfer learning, where multilingual BERT is fine-tuned on one source language and evaluated on a different target language.

Model Selection Transfer Learning +1

Attentional Speech Recognition Models Misbehave on Out-of-domain Utterances

1 code implementation12 Feb 2020 Phillip Keung, Wei Niu, Yichao Lu, Julian Salazar, Vikas Bhardwaj

We discuss the problem of echographic transcription in autoregressive sequence-to-sequence attentional architectures for automatic speech recognition, where a model produces very long sequences of repetitive outputs when presented with out-of-domain utterances.

Automatic Speech Recognition

A practical approach to dialogue response generation in closed domains

no code implementations28 Mar 2017 Yichao Lu, Phillip Keung, Shaonan Zhang, Jason Sun, Vikas Bhardwaj

We describe a prototype dialogue response generation model for the customer service domain at Amazon.

Response Generation

Cannot find the paper you are looking for? You can Submit a new open access paper.