Výsledky vyhledávání - "Phillip Keung"

Unsupervised Bitext Mining and Translation via Self-trained Contextual Embeddings

Autor: Julian Salazar, Yichao Lu, Phillip Keung, Noah A. Smith

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 embeddings for nearest-neighbor search and adapt the model via self-t

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::48fa85d532ed05079d727b6de4ab2c9d

Zobrazit plný text záznamu

The Multilingual Amazon Reviews Corpus

Autor: Yichao Lu, Noah A. Smith, Phillip Keung, György Szarvas

Publikováno v: EMNLP (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, Japanese, German, French, Spanish, and Chinese, which were collected be

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6b5916436fe22875896a939cbb34d676
https://doi.org/10.18653/v1/2020.emnlp-main.369

Zobrazit plný text záznamu

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

Autor: Julian Salazar, Vikas Bhardwaj, Phillip Keung, Yichao Lu

Publikováno v: EMNLP (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 language and evaluated on a different target language. However, publis

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::1190d9e9716622ae1ce72ba7bbe184af
https://doi.org/10.18653/v1/2020.emnlp-main.40

Zobrazit plný text záznamu

Improving Non-autoregressive Neural Machine Translation with Monolingual Data

Autor: Phillip Keung, Jiawei Zhou

Publikováno v: ACL

Non-autoregressive (NAR) neural machine translation is usually done via knowledge distillation from an autoregressive (AR) model. Under this framework, we leverage large monolingual corpora to improve the NAR model's performance, with the goal of tra

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::63c09dc68198c09d550aaccb0c508d47

Zobrazit plný text záznamu

Adversarial Learning with Contextual Embeddings for Zero-resource Cross-lingual Classification and NER

Autor: Yichao Lu, Phillip Keung, Vikas Bhardwaj

Publikováno v: EMNLP/IJCNLP (1)

Contextual word embeddings (e.g. GPT, BERT, ELMo, etc.) have demonstrated state-of-the-art performance on various NLP tasks. Recent work with the multilingual version of BERT has shown that the model performs very well in zero-shot and zero-resource

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bab14d4a485a73490a774900604f26ed

Zobrazit plný text záznamu

A neural interlingua for multilingual machine translation

Autor: Faisal Ladhak, Yichao Lu, Jason Sun, Shaonan Zhang, Phillip Keung, Vikas Bhardwaj

Publikováno v: WMT

We incorporate an explicit neural interlingua into a multilingual encoder-decoder neural machine translation (NMT) architecture. We demonstrate that our model learns a language-independent representation by performing direct zero-shot translation (wi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::66951e68127718f10d4cf8726accd2d0
https://doi.org/10.18653/v1/w18-6309

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání