Picture for Phillip Keung

Phillip Keung

NarrowBERT: Accelerating Masked Language Model Pretraining and Inference

Jan 11, 2023
Haoxin Li, Phillip Keung, Daniel Cheng, Jungo Kasai, Noah A. Smith

Figure 1 for NarrowBERT: Accelerating Masked Language Model Pretraining and Inference

Figure 2 for NarrowBERT: Accelerating Masked Language Model Pretraining and Inference

Figure 3 for NarrowBERT: Accelerating Masked Language Model Pretraining and Inference

Figure 4 for NarrowBERT: Accelerating Masked Language Model Pretraining and Inference

* Under review (ACL Rolling Review)

Access Paper or Ask Questions

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

Nov 30, 2022
Daniel Edmiston, Phillip Keung, Noah A. Smith

Figure 1 for Domain Mismatch Doesn't Always Prevent Cross-Lingual Transfer Learning

Figure 2 for Domain Mismatch Doesn't Always Prevent Cross-Lingual Transfer Learning

Figure 3 for Domain Mismatch Doesn't Always Prevent Cross-Lingual Transfer Learning

Figure 4 for Domain Mismatch Doesn't Always Prevent Cross-Lingual Transfer Learning

* Proceedings of the Thirteenth Language Resources and Evaluation Conference (LREC 2022), Pages 892-899
* 8 pages, 1 figure. Published/presented at LREC (2022)

Access Paper or Ask Questions

Unsupervised Bitext Mining and Translation via Self-trained Contextual Embeddings

Oct 15, 2020
Phillip Keung, Julian Salazar, Yichao Lu, Noah A. Smith

Figure 1 for Unsupervised Bitext Mining and Translation via Self-trained Contextual Embeddings

Figure 2 for Unsupervised Bitext Mining and Translation via Self-trained Contextual Embeddings

Figure 3 for Unsupervised Bitext Mining and Translation via Self-trained Contextual Embeddings

Figure 4 for Unsupervised Bitext Mining and Translation via Self-trained Contextual Embeddings

* To appear in the Transactions of the Association for Computational Linguistics

Access Paper or Ask Questions

The Multilingual Amazon Reviews Corpus

Oct 06, 2020
Phillip Keung, Yichao Lu, György Szarvas, Noah A. Smith

Figure 1 for The Multilingual Amazon Reviews Corpus

Figure 2 for The Multilingual Amazon Reviews Corpus

Figure 3 for The Multilingual Amazon Reviews Corpus

Figure 4 for The Multilingual Amazon Reviews Corpus

* To appear in EMNLP 2020

Access Paper or Ask Questions

Improving Non-autoregressive Neural Machine Translation with Monolingual Data

May 02, 2020
Jiawei Zhou, Phillip Keung

Figure 1 for Improving Non-autoregressive Neural Machine Translation with Monolingual Data

Figure 2 for Improving Non-autoregressive Neural Machine Translation with Monolingual Data

Figure 3 for Improving Non-autoregressive Neural Machine Translation with Monolingual Data

Figure 4 for Improving Non-autoregressive Neural Machine Translation with Monolingual Data

* To appear in ACL 2020

Access Paper or Ask Questions

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

Feb 12, 2020
Phillip Keung, Wei Niu, Yichao Lu, Julian Salazar, Vikas Bhardwaj

Figure 1 for Attentional Speech Recognition Models Misbehave on Out-of-domain Utterances

Figure 2 for Attentional Speech Recognition Models Misbehave on Out-of-domain Utterances

Figure 3 for Attentional Speech Recognition Models Misbehave on Out-of-domain Utterances

Figure 4 for Attentional Speech Recognition Models Misbehave on Out-of-domain Utterances

* Artifacts like our filtered Audio BNC dataset can be found at https://github.com/aws-samples/seq2seq-asr-misbehaves

Access Paper or Ask Questions

A neural interlingua for multilingual machine translation

Oct 16, 2018
Yichao Lu, Phillip Keung, Faisal Ladhak, Vikas Bhardwaj, Shaonan Zhang, Jason Sun

Figure 1 for A neural interlingua for multilingual machine translation

Figure 2 for A neural interlingua for multilingual machine translation

Figure 3 for A neural interlingua for multilingual machine translation

Figure 4 for A neural interlingua for multilingual machine translation

* Accepted in WMT 18

Access Paper or Ask Questions