We present our new paper 'Geographic Citation Gaps in NLP Research'

In this #EMNLP2022 work, we examine the relationship between geographical location and publication impact in the field of NLP.

arxiv.org/abs/2210.14424

Janvijay Singh Diyi Yang Machine Learning at Georgia Tech Stanford NLP Group

#NLProc

What a poster session: Thank you all for stopping by!

If you missed it and want to know the secret on how to choose the best LM for your task without fine-tuning, find us (Max Mike Zhang Barbara Plank) around the conference in the next days 😁👋

#EMNLP2022

TOKEN2049, 13-14 September 2023 | Marina Bay Sands

With 10,000+ attendees, 200+ A-list speakers, and 300+ side events including the F1 Singapore GP, #TOKEN2049 brings together the community that will define what's next in crypto.

Tickets: asia.token2049.com/tickets

Excited about EMNLP 2022 in-person this week!
Here's the summary of my posters (thanks to all my collaborators). Please DM if you have any question or just want to chat.
#EMNLP2022 #NLProc

While I'm not at #EMNLP2022 , we have two works on the intersection of RL + NLP.

RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning
(arxiv.org/abs/2205.12548)

Efficient (Soft) Q-Learning for Text Generation with Limited Good Data
(arxiv.org/abs/2106.07704)

Can we give some award to #ChatGPT at #EMNLP2022 ? 90+% of the research conversations I heard were about #ChatGPT !

Are hard examples hard to explain? Explained at #EMNLP2022 ! 😃

What machine translation errors are evaluation metrics sensitive to and to what extent? Check out DEMETR - dataset to diagnose MT evaluation metrics #EMNLP2022 (P4 Board 1) work with Nishant Raj Katherine Thai Yixiao Song Ankita Gupta Mohit Iyyer (1/5)

📜Paper arxiv.org/abs/2210.13746

Do multilingual language models (MultiLMs) learn different languages using the same subset of parameters? In our #EMNLP2022 #NLProc paper, we show that MultiLMs are composed of language-neutral representations that jointly encode multiple languages.

Machine rationales are generated to explain LM behavior, but to what extent can they be *utilized* to improve LMs’ OOD generalization? 🤔

Our 🏥ER-Test paper ( #EMNLP2022 Findings + #BlackboxNLP ) investigates this question! 🔍

🧵👇 [1/n]

Update: Expect significant escalation in the conflict on June 26/27/28 with the intensity increasing through mid-August 2023. Major offensives from Russia are likely during this time.

How much Chinese linguistic knowledge do large pretrained language models encode? SLING (to appear at #EMNLP2022 ) investigates this question and presents a high-quality dataset with 38K minimal pairs covering 9 Chinese linguistic phenomena. (1/6)

📄Paper: arxiv.org/abs/2210.11689

Slowly coming back to earth (+ timezone) after a fantastic time at #emnlp2022 . It's truly a privilege to get to spend a week nerding out with colleagues and catching up with friends while exploring a new destination. Looking forward to many more!

how my phd started vs how it’s going #EMNLP2022

#EMNLP2023 will be in Singapore #emnlp2022 #nlproc 6-10/12/2023

🧙‍♀️Jan 1st, 2023 I am joining Computing & Information Systems UniMelb as a Cont. Lecturer and will be a part of its fabulous #NLProc Group: cis.unimelb.edu.au/research/artif…!

🪄Interested in joining the group as a PhD student? Please email us or approach Lea Frermann, Daniel Beck, Jey Han Lau, Ed Hovy at #EMNLP2022

Finally, I met Yejin Choi at the conference!Thank you for accepting the photo request. I met her at the Ritz-Carlton with a view of the beautiful mosque last night. I was so honored that I couldn't sleep! As a Korean, I am proud of her! Yejin Choi #EMNLP2022

me(俺), me(僕), or me(私)? What makes translation especially fascinating is the difference between types of nuance captured in one language (but not another). In our #EMNLP2022 paper, we investigate this in MT. USC Thomas Lord Department of Computer Science CUTELABNAME (NLP @ ISI) USC NLP

Mind-blowing paper I met on #EMNLP2022 . I highly recommend this paper. The idea is so cool that I can't help to check out the code directly after having a chat with the cool author Oren Sultan!
#EMNLP2022 livetweet

Best long paper award at #EMNLP2022 on #tangrams !

4/25 Russia appears to be preparing for the perfect offensive. This will be mechanical & precise in execution (after some initial issues). As predicted in March 2023, the offensive will be launched between late June and August 2023. This will be the decisive phase of the SMO.

NEARCON 2023: Step into the open web.

Join us in Lisbon from November 7-10.

Early bird tickets are available until the end of June.

Purchase yours now at nearcon.org

#NEARCON2023

We reverse-engineered the ability of GPTs to incrementally piece together ‘who did what to whom?’ and found they rediscover a classic algorithm! 🧵
w/ Yoon Kim (Yoon Kim) Roger Levy (@roger_p_levy) and Vineet Gangireddy (@VineetGan) #EMNLP2022 (findings) arxiv.org/abs/2211.09748

Coming to you live from Edinburgh, my #emnlp2022 Findings poster and I, during the virtual poster session of #BlackboxNLP at 4PM in Abu Dhabi (noon UTC). Find me at stand 492 in Gathertown to learn more about the Bottleneck Compositionality Metric Ivan Titov and I propose!