activity
20172022
most citedA practical approach to dialogue response generation in closed domains

13 citations · 18 across the 2 of their papers we have counts for

collaborators

9 papers

cs.CL2022

Domain Mismatch Doesn't Always Prevent Cross-Lingual Transfer Learning

Daniel Edmiston, Phillip Keung, Noah A. Smith

Cross-lingual transfer learning without labeled target language data or parallel text has been surprisingly effective in zero-shot cross-lingual classification, question answering,…

cs.CL2020

Unsupervised Bitext Mining and Translation via Self-trained Contextual Embeddings

Phillip Keung, Julian Salazar, Yichao Lu +1

We describe an unsupervised method to create pseudo-parallel corpora for machine translation (MT) from unaligned text. We use multilingual BERT to create source and target sentence…

cs.CL2020

The Multilingual Amazon Reviews Corpus

Phillip Keung, Yichao Lu, György Szarvas +1

We present the Multilingual Amazon Reviews Corpus (MARC), a large-scale collection of Amazon reviews for multilingual text classification. The corpus contains reviews in English, J…

cs.CL2020

Improving Non-autoregressive Neural Machine Translation with Monolingual Data

Jiawei Zhou, Phillip Keung

Non-autoregressive (NAR) neural machine translation is usually done via knowledge distillation from an autoregressive (AR) model. Under this framework, we leverage large monolingua…

cs.CL2020

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

Phillip Keung, Yichao Lu, Julian Salazar +1

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…

eess.AS20205 cited

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

Phillip Keung, Wei Niu, Yichao Lu +2

We discuss the problem of echographic transcription in autoregressive sequence-to-sequence attentional architectures for automatic speech recognition, where a model produces very l…