Ethan Chau

24 posts

Ethan Chau

Ethan Chau

@echau18

NLP (#NLProc) + Search at MSFT; formerly @uwcse @uwnlp and briefly @ETH; low-resource NLP, adversarial robustness, multilinguality, LMs, contrastive learning

Seattle, WA, USA เข้าร่วม Nisan 2019
426 กำลังติดตาม160 ผู้ติดตาม
ทวีตที่ปักหมุด
Ethan Chau
Ethan Chau@echau18·
Multilingual models have been "specialized" to certain target low-resource languages, but does this work in general? And how do specialization methods interact? Our paper at @mrl_2021 examines these questions and their outlook: arxiv.org/abs/2106.09063 w/ @nlpnoah 🔽1/7
Ethan Chau tweet media
English
2
0
4
0
Ethan Chau
Ethan Chau@echau18·
Excited to be at #NAACL2022! Would love to chat about multilinguality, contrastive learning, low-resource, dense retrieval, robustness, LLMs, and anything in between -- feel free to reach out! #nlproc
English
0
1
14
0
Ethan Chau รีทวีตแล้ว
MRL
MRL@mrl2024_emnlp·
Ethan C. Chau @echau18 is presenting his work on Specializing Multilingual Models: An Empirical Study at MRL 2021 which won the Honorable Mention Award.
MRL tweet media
Ethan Chau@echau18

Honored to receive a Best Paper Honorable Mention at @mrl_2021 #EMNLP2021 -- check out my work w/ @nlpnoah on model specialization today, Nov. 11 (in 30 min)! Poster session: 7-8:30 PST / 11-12:30 Punta Cana Award talk: 12-13 PST / 16-17 Punta Cana Link: underline.io/events/192/ses…

English
0
3
2
0
Ethan Chau
Ethan Chau@echau18·
Honored to receive a Best Paper Honorable Mention at @mrl_2021 #EMNLP2021 -- check out my work w/ @nlpnoah on model specialization today, Nov. 11 (in 30 min)! Poster session: 7-8:30 PST / 11-12:30 Punta Cana Award talk: 12-13 PST / 16-17 Punta Cana Link: underline.io/events/192/ses…
Ethan Chau@echau18

Multilingual models have been "specialized" to certain target low-resource languages, but does this work in general? And how do specialization methods interact? Our paper at @mrl_2021 examines these questions and their outlook: arxiv.org/abs/2106.09063 w/ @nlpnoah 🔽1/7

English
0
2
7
0
Ethan Chau
Ethan Chau@echau18·
While our results are mixed, we see a positive outlook for model specialization and believe it warrants further study, perhaps through different types/configurations of mix-ins, or specialization of different models -- or even designing models to be more specializable. 6/7
English
1
0
0
0
Ethan Chau
Ethan Chau@echau18·
Multilingual models have been "specialized" to certain target low-resource languages, but does this work in general? And how do specialization methods interact? Our paper at @mrl_2021 examines these questions and their outlook: arxiv.org/abs/2106.09063 w/ @nlpnoah 🔽1/7
Ethan Chau tweet media
English
2
0
4
0
Ethan Chau
Ethan Chau@echau18·
Excited to share a new preprint on specializing multilingual LMs for low-resource target languages! We perform extended evaluation with several methods + languages + scripts + tasks and remark on open questions in the area. w/ @nlpnoah arxiv.org/abs/2106.09063
English
2
5
22
0
Ethan Chau รีทวีตแล้ว
SIGTYP
SIGTYP@sig_typ·
💫Parsing with Multilingual BERT, a Small Corpus, and a Small Treebank💫 by Ethan C. Chau @echau18, Lucy H. Lin, Noah A. Smith @nlpnoah twitter.com/echau18/status…
Ethan Chau@echau18

Excited to share my first paper, to appear in Findings @emnlp2020! We show that multilingual models can be effectively adapted to low-resource languages with only a little unlabeled data. w/ Lucy Lin, @nlpnoah Paper: arxiv.org/abs/2009.14124 Code: github.com/ethch18/parsin… 🔽1/8

English
1
2
7
0
Ethan Chau
Ethan Chau@echau18·
If you're interested in adapting multilingual BERT to low-resource languages, check out our talk + Q/A at the #SIGTYP workshop of #emnlp2020, or find us on rocketchat! When: Nov. 19 (Thurs.) 11:20-11:30 PST / 19:20-19:30 UTC Link: virtual.2020.emnlp.org/paper_WS-11.10…
SIGTYP@sig_typ

Will be presented at #SIGTYP Nov, 19th by @echau18 Slideslive: slideslive.com/38940630 Schedule: sigtyp.github.io/ws2020-schedul… #EMNLP2020 #Findings #MultilingualNLP

English
0
2
2
0
Ethan Chau
Ethan Chau@echau18·
There's so much work to be done in understanding how to use multilingual models effectively and bringing NLP advances to low-resource languages. Excited to be part of this stream of work! Please reach out with any thoughts/questions. 8/8
English
0
0
1
0
Ethan Chau
Ethan Chau@echau18·
This is promising for low-resource languages! Lack of data is often cited as a limiting factor for low-resource NLP, but we show that it's possible to achieve strong improvements with very little unlabeled data. 7/8
English
1
0
1
0