Phillip Keung
Phillip Keung has 2 papers in our library, in 2018–2020, most of them on Multilingual & cross-lingual NLP, Machine translation; often with Yichao Lu, Faisal Ladhak, György Szarvas.
current affiliationAllen Institute for Artificial Intelligence, Seattle, United States
OpenAlex · h-index 7 · 19 works · 447 citations OpenAlex, 2026-10-14
2 works in our library · 159 citations in our library · ⭐ Paper Star rank #3136
Affiliations
- Allen Institute for Artificial Intelligence · Seattle, United States — current · 2026 on 1 paper
- University of Washington · Seattle, United States — 2022–2024 on 4 papers
- Amazon (United States) · Seattle, United States — 2018–2020 on 7 papers
Topics
Works by year
2020s
2010s
Papers
- The Multilingual Amazon Reviews Corpus (2020 · 255 citations)
Multilingual text classification lacks large, openly available benchmarks. Existing options such as RCV1/RCV2, MLDoc, XNLI, Yelp and earlier Amazon review releases are small, hard to obtain, missing non-English training data, unreliable about language labels, or lacking fixed splits. The authors address this gap with… - A neural interlingua for multilingual machine translation (2018 · 178 citations)
Multilingual NMT usually takes one of two routes. One trains a separate model for every language pair, so the number of models grows quadratically. The other shares a single encoder-decoder and a joint vocabulary, which forces many languages into one fixed-size output layer. Lu et al. (Amazon) propose a middle path.…
Co-authors here
Cited by
This page in Markdown → https://md.research.elamur.ai/free/en/authors/phillip-keung/