Výsledky vyhledávání

nmT5 -- Is parallel data still relevant for pre-training massively multilingual language models?

Autor: Aditya Siddhant, Melvin Johnson, Noah Constant, Mihir Kale, Linting Xue, Rami Al-Rfou

Publikováno v: ACL/IJCNLP (2)

Recently, mT5 - a massively multilingual version of T5 - leveraged a unified text-to-text format to attain state-of-the-art results on a wide variety of multilingual NLP tasks. In this paper, we investigate the impact of incorporating parallel data i

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6ecc502f36493adff335cae7874f1a9d
http://arxiv.org/abs/2106.02171

Zobrazit plný text záznamu

mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer

Autor: Noah Constant, Aditya Siddhant, Aditya Barua, Linting Xue, Mihir Kale, Adam Roberts, Rami Al-Rfou, Colin Raffel

Publikováno v: NAACL-HLT

The recent "Text-to-Text Transfer Transformer" (T5) leveraged a unified text-to-text format and scale to attain state-of-the-art results on a wide variety of English-language NLP tasks. In this paper, we introduce mT5, a multilingual variant of T5 th

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6841f14537777a14674607884ca00048
https://doi.org/10.18653/v1/2021.naacl-main.41

Zobrazit plný text záznamu

Evolving Augmented Graph Grammars for Argument Analysis

Autor: Collin F. Lynch, Linting Xue, Min Chi

Publikováno v: GECCO (Companion)

Augmented Graph Grammars are a robust rule representation for rich graph data. In this paper we present our work on the automatic induction of graph grammars for argument diagrams via EC. We show that EC outperforms the existing grammar induction alg

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::71f85cfde14917c42ae6664d2d19b316
https://doi.org/10.1145/2908961.2908994

Zobrazit plný text záznamu

Attention-aware robotic laparoscope for human-robot cooperative surgery

Autor: Fernando J. Kim, Songpo Li, Jiucai Zhang, Xiaoli Zhang, Linting Xue

Publikováno v: ROBIO

Current laparoscopic surgeries suffer from inconvenient, limited visualization due to the small incisions. It normally needs an assistant to hold and readjust a laparoscope to view the surgical set when performing procedures. This assistant can be ei

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::287e13bea9faf2b827e885b02835b95b
https://doi.org/10.1109/robio.2013.6739559

Zobrazit plný text záznamu

Digital human modeling for ergonomic evaluation of patient table height

Autor: Xiaoli Zhang, Songpo Li, Fernando J. Kim, Linting Xue

Publikováno v: ROBIO

Laparoscopic techniques provide significant advantages to patients, such as shorter hospital stays, faster recovery times, and minimal scarring. However, poor ergonomics in laparoscopic surgery and failure to understand the ergonomics of laparoscopic

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::12613008cbc819b7689d0f8b8ef1b4a6
https://doi.org/10.1109/robio.2013.6739675

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání