Esin Durmus @esindurmusnlp Twitter profile | Pikagi

Pikagi

Esin Durmus

@esindurmusnlp

2,925

Followers

387

Following

2

Media

257

Statuses

Research Scientist @anthropicai . Previously Postdoc @stanfordnlp and PhD @cornellcis . Working on LLMs & evaluating their safety and impact on society. she/her.

https://t.co/s3r4MQi3U2

Joined January 2017

Don't wanna be here? Send us removal request.

Pinned Tweet

@esindurmusnlp

Esin Durmus

1 month

Our latest study measures how persuasive language models like Claude are compared to humans. We find a general scaling trend: newer models tend to be more persuasive, with Claude 3 Opus generating arguments that don't differ statistically from human-written ones.

@AnthropicAI

Anthropic

1 month

New Anthropic research: Measuring Model Persuasiveness We developed a way to test how persuasive language models (LMs) are, and analyzed how persuasiveness scales across different versions of Claude. Read our blog post here:

Tweet media one

56

118

712

5

15

95

Last Seen Profiles

@Ahall41116

@hanhaepari

@ShijunDeng

@Barnabas_Daru

@3yitmeldenya

@badhapple

@FiresideChatApp

@serpaJ

@DiocesanoCoroVA

@Ctln0

@ValRobinson12

@AllanDownton

@STEM_LPS

@princessdajaa

@VShred_

@FellaBrigade

@karsthetics

@crafterior_

@sunnenfinster

@TigerHiroMetal

@truflation

@jacrecordstore

@herrkor

@bubmatcha

@Mitochondrium72

@RitaSuszek

@hatz_csgo

@DouglasLwangaUg

@popcornshed

@watvindjezelf

@EggyInu

@quazijohir

@inetaprog

@ArmiarmaA

@BCRebelFootball

@bbinacry

@esindurmusnlp

Esin Durmus

4 years

It’s great that schools are waiving the GRE requirement. But I remember the main cost that prevented me from applying to more schools was the application fees (~100USD per school). Given the exchange rate, it was a big challenge. I spent all my savings for PhD applications.

19

34

541

@esindurmusnlp

Esin Durmus

4 years

Personal news: Excited to share that after completing my PhD towards the end of Spring 2021, I will be joining @stanfordnlp for a Postdoc. I am extremely fortunate to be co-hosted by @jurafsky , @tatsu_hashimoto and @chrmanning . Looking forward to be part of this amazing group!

18

7

428

@esindurmusnlp

Esin Durmus

7 months

Join our team! 🙌 The societal impacts team at @AnthropicAI is hiring. We design new methods to assess language models for societally or policy-relevant traits. If you feel passionate about this direction, apply to join us! (please retweet)

16

64

278

@esindurmusnlp

Esin Durmus

1 year

After two amazing postdoc years at @StanfordNLP , thrilled to join @AnthropicAI 's Societal Impacts team as a Research Scientist! Grateful for everyone who helped me along the way. Feeling lucky to work with this great group on the crucial mission of building safer AI.

9

9

240

@esindurmusnlp

Esin Durmus

11 months

Language models are widely used but whose views do they reflect? My new paper examines how to test global opinions represented by language models.

@AnthropicAI

Anthropic

11 months

We develop a method to test global opinions represented in language models. We find the opinions represented by the models are most similar to those of the participants in USA, Canada, and some European countries. We also show the responses are steerable in separate experiments.

102

173

786

4

36

179

@esindurmusnlp

Esin Durmus

4 years

@kisacakimdir Çok teşekkür ederim sayfanızda bana yer verdiğiniz için :)

6

0

122

@esindurmusnlp

Esin Durmus

4 years

@kisacakimdir Özellikle genç kadınlarımıza söylemek isterim ki başarıları olamayacağınız hiçbir alan yok. Bilgisayar bilimleri, yapay zeka ve teknoloji içerikli her konu da buna dahil. Yeter ki isteyin, korkmayın ve çalışın. Genç kadınlarımızın katılımına bu alanlarda çok ihtiyacımız var.

3

5

111

@esindurmusnlp

Esin Durmus

4 years

I am very excited to co-teach NLP (CS 4740) with my great advisor @clairecardie this semester. This class has a special place in my heart since it was the first NLP class I have ever taken and it convinced me to do research in this area. #NLProc #CornellCIS #Cornell

4

4

111

@esindurmusnlp

Esin Durmus

11 months

My first collaboration at @AnthropicAI 🎉 I led the experiments on summarization, topic modeling and political bias. It’s cool to see that long context model opens up great possibilities for long-form summarization.

@_akhaliq

AK

11 months

Opportunities and Risks of LLMs for Scalable Deliberation with Polis paper page: Polis is a platform that leverages machine intelligence to scale up deliberative processes. In this paper, we explore the opportunities and risks associated with applying…

Tweet media one

0

22

78

2

19

99

@esindurmusnlp

Esin Durmus

2 years

That moment when you realize NAACL regular early registration price > 2 times Turkish minimum wage… #NAACL2022 #nlproc

2

10

92

@esindurmusnlp

Esin Durmus

2 years

Excited to share that our paper “Spurious Correlations in Reference-free Evaluation of Text Generation” will appear in #acl2022nlp Main Conf. We find that recently proposed metrics in summarization and dialog generation may be exploiting spurious correlations in the benchmarks.

4

10

84

@esindurmusnlp

Esin Durmus

4 years

Proud moment when the student you advised gets her first main conference paper @emnlp2020 . Congrats @JialuLi96 ! You will do great at @uncnlp !

3

2

83

@esindurmusnlp

Esin Durmus

4 years

Even after I got accepted, I still had to borrow money to pay for the initial costs (i.e. flight tickets, one month deposit for the apartment) since you don’t get the first paycheck until after you start. A lot of these are prohibitive costs for international students.

1

1

80

@esindurmusnlp

Esin Durmus

4 years

@kisacakimdir Çok teşekkür ederim sorularınız ve mesajlarınız için. Koç’ta not ortalaması 4 üzerinden ve bir çok derste A+ opsiyonu yok. Fakat olan derslerde A+ alıp 4 ün üzerine çıkmak mümkün. Biraz kafa karıştırıcı bir durum olduğunun farkındayım ama bu şekilde. :)

1

3

74

@esindurmusnlp

Esin Durmus

4 years

@kisacakimdir Bazı okullarda sınıftaki en başarılı 1-2 öğrenciye A+ veriliyor. O yüzden not ortalaması 4 üzerine çıkabiliyor.

1

0

65

@esindurmusnlp

Esin Durmus

2 months

Excited to share what we’ve built!

@AnthropicAI

Anthropic

2 months

Today, we're announcing Claude 3, our next generation of AI models. The three state-of-the-art models—Claude 3 Opus, Claude 3 Sonnet, and Claude 3 Haiku—set new industry benchmarks across reasoning, math, coding, multilingual understanding, and vision.

Tweet media one

568

2K

10K

1

5

62

@esindurmusnlp

Esin Durmus

3 years

Checkout our new paper: “Faithful or Extractive? On Mitigating the Faithfulness-Abstractiveness Trade-off in Abstractive Summarization”. #NLProc 1/n

3

13

61

@esindurmusnlp

Esin Durmus

10 months

Honored that our paper got the Social Impact Award at #acl2023nlp . With AI's growing influence, it feels particularly meaningful that our work was recognized in this category. @aclmeeting #NLProc

@aclmeeting

ACL 2024

10 months

Social Impact Award 📢S7: Ethics & NLP (Poster) 📌Marked Personas: Using Natural Language Prompts to Measure Stereotypes in LMs 🔎 Portrayals by GPT-3.5/4GPT-4 contain higher rates of racial stereotypes than human-written ones 🔗 🧵(3/4)

1

6

18

5

7

57

@esindurmusnlp

Esin Durmus

1 month

Excited to share our new research on a long-context jailbreaking technique that works across a wide range of large language models (w/ @cem__anil ) .

@AnthropicAI

Anthropic

1 month

New Anthropic research paper: Many-shot jailbreaking. We study a long-context jailbreaking technique that is effective on most large language models, including those developed by Anthropic and many of our peers. Read our blog post and the paper here:

Tweet media one

83

350

2K

1

5

52

@esindurmusnlp

Esin Durmus

4 years

Excited about this upcoming work proposing a multilingual benchmark dataset for abstractive summarization. We hope this will encourage further research in languages other than English! It is a very unique resource as it has parallel article-summary pairs in 17 languages. #NLProc

@faisalladhak

Faisal Ladhak

4 years

Our EMNLP Findings paper presenting WikiLingua — a new multilingual abstractive summarization dataset — is now on arXiv. It contains 770K article/summary pairs in 17 languages, parallel with English. Paper: Dataset: #NLProc

1

11

84

0

4

40

@esindurmusnlp

Esin Durmus

1 year

@WilliamWangNLP Yes, especially international students may not have the opportunity to publish papers during their undergrads. Not a very inclusive metric.

0

0

36

@esindurmusnlp

Esin Durmus

4 years

"When I'm sometimes asked 'When will there be enough [women on the Supreme Court]?' and I say 'When there are nine,' people are shocked. But there'd been nine men, and nobody's ever raised a question about that." (RBG).

0

0

28

@esindurmusnlp

Esin Durmus

1 year

Checkout our new ACL paper introducing Marked Personas, an unsupervised way to measure stereotypes in AI models for any intersectional identity. With our method, we prove that personas from GPT-4 and GPT-3.5 are more stereotypical than human-written ones! #ACL2023

@chengmyra1

Myra Cheng

1 year

New paper (to appear at ACL 2023)! We present Marked Personas, an unsupervised way to measure stereotypes in LLMs for any intersectional identity. Paper: Joint work with the wonderful @esindurmusnlp @jurafsky @stanfordnlp 🧵1/6

7

25

137

2

5

28

@esindurmusnlp

Esin Durmus

4 years

I am also involved in GEM (Generation, Evaluation and Metrics) workshop. It will focus on an in-depth evaluation of generation models across both human and automatic evaluation. Highly recommend voting for it! #NLProc

@cocoweixu

Wei Xu

4 years

A whopping 97 #nlproc workshops to select from for next year! There are two I am involved in: • GEM (a new WMT-style evaluation for natural language generation) • WNUT (NLP for social media and other noisy user-generated text)

0

4

16

0

6

28

@esindurmusnlp

Esin Durmus

10 months

#ICML2023

Tweet media one

Tweet media two

Tweet media three

Tweet media four

2

0

27

@esindurmusnlp

Esin Durmus

2 years

Happy to share that this work is going to appear at #acl2022nlp Main Conf. 🎉 Check out the updated paper if you are interested in faithfulness in abstractive summarization ⬇️⬇️⬇️ #NLProc

@esindurmusnlp

Esin Durmus

3 years

Checkout our new paper: “Faithful or Extractive? On Mitigating the Faithfulness-Abstractiveness Trade-off in Abstractive Summarization”. #NLProc 1/n

3

13

61

0

3

27

@esindurmusnlp

Esin Durmus

7 months

How can we include public input in AI development? 🤔 In our new work, we collectively crowdsourced a constitution from Americans with @collect_intel on @usepolis . Check out our blog to learn more about our process and the challenges we faced. #LLMs

@AnthropicAI

Anthropic

7 months

What does it mean for AI development to be more democratic? To find out, we partnered with @collect_intel to use @usepolis to curate an AI constitution based on the opinions of ~1000 Americans. Then we trained a model against it using Constitutional AI.

Tweet media one

21

71

395

1

5

25

@esindurmusnlp

Esin Durmus

2 months

Excited to leverage your technical skills to shape policy around LLMs? 📜 Want to help build language models that benefit society through sociotechnical alignment and evaluations? 📊 Societal impacts team at #AnthropicAI is also hiring:

@jackclarkSF

Jack Clark

2 months

Want to work at the frontier of AI policy with the most technical policy team in the business? You do? Excellent. Please consider applying - Special Projects Lead - Policy Analyst, Product - Outreach Lead

4

26

110

0

6

24

@esindurmusnlp

Esin Durmus

2 years

I will be attending in person, let’s grab a coffee ☕️

@WiNLPWorkshop

WiNLP

2 years

Tomorrow (10th) at #NAACL2022 we will host a virtual mentorship session from 12-1 PM PDT. Introducing our super-mentors: @faeze_brh (Postdoc @ AI2), @esindurmusnlp (Postdoc @ Stanford), @VioletNPeng (Asst. Prof. @ UCLA), & @Tetreault_NLP (Sr. Director @ Dataminr).

2

6

25

0

0

22

@esindurmusnlp

Esin Durmus

4 years

Yet another disastrous and biased English-Turkish translation. I am sorry that it is really difficult to follow my Turkish tweets :D

@danish037

Danish Pruthi

4 years

A bad translation fail! Particularly important to get such translations right given how poorly women are represented in tech. I don't know Turkish, but this shouldn't be hard (Maybe @esindurmusnlp , @volkancirik can correct me if I am wrong about the Turkish part).

Tweet media one

1

0

9

2

0

21

@esindurmusnlp

Esin Durmus

4 years

There are lots of great mentoring sessions at #acl2020nlp but feel free to DM on RocketChat (username: esin) if you think I can be helpful with any questions regarding PhD applications, surviving grad school, finding internships or any NLP related stuff.

0

1

21

@esindurmusnlp

Esin Durmus

4 years

So, what are doing with your “EMNLP Findings” acceptances? #emnlp2020 #NLProc #emnlp

Resubmit to another conf

110

Publish in findings

227

1

8

19

@esindurmusnlp

Esin Durmus

4 years

We will be taking questions for our work FEQA today 1-2pm EST and 5-6 pm EST. I have done part of this work while interning at @AmazonScience with great collaborators @hhexiy and Mona Diab. Join us if you want to chat about evaluating faithfulness in summarization. #acl2020nlp

0

4

19

@esindurmusnlp

Esin Durmus

10 months

Looking forward to attending #ICML2023 in Hawaii this year. If you want to meet up to discuss evaluating LLMs and their societal impact, let me know!

0

0

19

@esindurmusnlp

Esin Durmus

4 years

I was very fortunate to have had an amazing advisor in @clairecardie . She supported me through everything. Also, I had amazing mentors along the way in Mona Diab and @hhexiy . Without their support this would not have been possible.

0

1

18

@esindurmusnlp

Esin Durmus

3 years

Happy to have contributed to this extensive project of @StanfordHAI led by @RishiBommasani and @percyliang . In the inequity and fairness section, we discuss intrinsic vs. extrinsic harms of foundational models, sources of these harms, and potential interventions #foundationmodels

@percyliang

Percy Liang

3 years

I want to thank each of my 113 co-authors for their incredible work - I learned so much from all of you, @StanfordHAI for providing the rich interdisciplinary environment that made this possible, and everyone who took the time to read this and give valuable feedback!

3

30

265

2

2

17

@esindurmusnlp

Esin Durmus

4 years

@emnlp2020 I am afraid this decision may affect the diversity of the topics in the main conference since it incentivizes people to work on “trendy” topics. Also, terms such as “narrow subfield”, “trendy”, “high impact” only add more subjectivity to the review process...

2

2

17

@esindurmusnlp

Esin Durmus

4 years

@emnlp2020 Students who are interested in more specific topics may now feel pressure to switch to more trendy topics because in the end when it comes to job search people will give more weight to main conference papers.

0

2

15

@esindurmusnlp

Esin Durmus

2 years

Check out our latest preprint where we show that text-to-image models such as Stable diffusion and DALLE amplify dangerous and complex demographic stereotypes. ⬇️ #AI #nlproc

@federicobianchy

Federico Bianchi

@federicobianchy

2 years

Text-to-image generation models (like Stable Diffusion and DALLE) are being used to generate millions of images a day. We show that these models perpetuate and amplify dangerous stereotypes related to race, gender, crime, poverty, and more () A thread🧵

43

460

1K

0

2

10

@esindurmusnlp

Esin Durmus

6 months

New policy brief discussing our work on the biases of text-to-image models ⬇️

@StanfordHAI

Stanford HAI

6 months

🚨 New policy brief: Millions of images are generated each day using text-to-image AI systems. Our latest brief examines how major image generation models encode a wide range of dangerous biases about demographic groups. Read or download here:

Tweet media one

7

22

48

0

2

8

@esindurmusnlp

Esin Durmus

2 months

This is super useful for quickly prototyping and iterating on prompts

@moritzkremb

Moritz Kremb

2 months

You can now use Claude 3 in Google sheets. It lets you create prompt templates and fill it in with your custom data from the sheet. I'll show you how to set it up and what you can do with it:

Tweet media one

24

82

738

0

0

7

@esindurmusnlp

Esin Durmus

1 year

These stereotypes are further perpetuated when using these systems for creative generation, like story generation.

1

0

6

@esindurmusnlp

Esin Durmus

2 years

Super excited to have Mona at @stanfordnlp this week! ⭐️

@stanfordnlp

Stanford NLP Group

2 years

At this week's NLP Seminar we are delighted to have Mona Diab from George Washington University! The seminar will be Thursday, 11 am to 12 pm PT. Mona will be talking about Systems and Labeling for Arabic Hate Speech Detection. Registration:

Tweet media one

1

8

33

0

0

6

@esindurmusnlp

Esin Durmus

2 years

We look at reference-free metrics for dialog generation and text summarization. In most cases, we find that spurious correlates such as perplexity and word overlap can get similar correlation with human scores as the metrics.

1

0

6

@esindurmusnlp

Esin Durmus

3 years

@StanfordHAI @RishiBommasani @percyliang Many thanks to excellent collaborators @jurafsky @RishiBommasani @faisalladhak @fereshte_khani .

0

0

6

@esindurmusnlp

Esin Durmus

3 years

With great collaborators: @faisalladhak , @hhexiy , Kathleen Mckeown and Claire Cardie.

0

0

6

@esindurmusnlp

Esin Durmus

4 years

@nouhadziri Future work 😀

Tweet media one

1

0

6

@esindurmusnlp

Esin Durmus

6 months

@whynotyet @OlgaOvi @BakerEDMLab Interesting work! We ran similar experiments in this paper and found that LLMs tend to reflect the opinions of some of the Western countries more closely.

1

1

6

@esindurmusnlp

Esin Durmus

4 years

She has been studying the relationship between the discourse structure of the arguments and their persuasiveness. The preprint is coming soon! :)

0

0

5

@esindurmusnlp

Esin Durmus

2 years

We finally propose an adversarially trained metric for faithfulness that has much lower correlation with extractiveness. We show that this metric is more robust and achieves better system-level ranking performance.

1

0

5

@esindurmusnlp

Esin Durmus

1 year

It was fun to contribute to HELM summarization benchmarking efforts. See 👇 for lots of cool findings.

@Tianyi_Zh

Tianyi Zhang

1 year

Two lessons we learned through HELM (Sec 8.5.1; ): 1. CNN/DM and XSum reference summaries are worse than summaries generated by finetuned LMs and zero-/few-shot large LMs. 2. Instruction tuning, not scale, is the key to “zero-shot” summarization.

3

27

110

0

1

5

@esindurmusnlp

Esin Durmus

3 years

We present a framework for evaluating the effective faithfulness of summarization systems, by generating a faithfulness- abstractiveness trade-off curve that serves as a control at different operating points on the abstractiveness spectrum. 3/n

1

0

5

@esindurmusnlp

Esin Durmus

4 years

@barbara_plank @perezjotaeme @IAugenstein @ojahnn @dipanjand @sebgehr Thanks! I agree that it should not be at the same time as the tutorials. Tutorials are super useful and unfortunately this affects attendance of WiNLP. When I attended WiNLP workshops, I always wished that there were more people attending from non minority groups as well.

0

0

5

@esindurmusnlp

Esin Durmus

3 years

@StanfordHAI @RishiBommasani @percyliang Join the discussion around this topic at our Workshop on Foundation Models, Aug. 23-24.

0

1

4

@esindurmusnlp

Esin Durmus

4 years

@emnlp2020 Also it seems like most of the analysis papers (which I find extremely important) could fall into “findings” category given the criteria, since their main goal is not necessarily to provide methods that are thought to be sufficiently novel.

0

0

4

@esindurmusnlp

Esin Durmus

1 month

@RishiBommasani @shi_weiyan @clairecardie Thanks @RishiBommasani :)

0

0

4

@esindurmusnlp

Esin Durmus

4 years

@danish037 @volkancirik Hahaha, omg! This is a disaster. Here is yet another example of our greatly biased NLP systems :D

0

0

4

@esindurmusnlp

Esin Durmus

1 year

LLM generated outputs seem positive in sentiment, however, they contain words tied to historical legacies of harm

1

0

4

@esindurmusnlp

Esin Durmus

2 years

Work with my amazing collaborators @faisalladhak and @tatsu_hashimoto . #NLProc @stanfordnlp @StanfordAILab

0

0

4

@esindurmusnlp

Esin Durmus

4 years

@seymakabaoglu Sağol canım! Sen de öyle ♥️

0

0

4

@esindurmusnlp

Esin Durmus

3 years

We further learn a selector to identify the most faithful and abstractive summary for a given document, and show that this system can attain higher faithfulness scores in human evaluations while being more abstractive than the baseline system on two datasets. 5/n

1

0

4

@esindurmusnlp

Esin Durmus

29 days

@anko_979 @M1ndPrison @CCFarre @AnthropicAI Participants were not informed about the source of the arguments.

0

0

3

@esindurmusnlp

Esin Durmus

2 years

We further do a system-level analysis for faithfulness in abstractive summarization. We show that faithfulness metrics are not effective in ranking relatively abstractive, faithful systems (current SOTA) potentially due to over reliance to the spurious correlates.

1

0

3

@esindurmusnlp

Esin Durmus

3 years

While prior work has proposed models that improve faithfulness, it is unclear whether the improvement comes from an increased level of extractiveness of the model outputs. 2/n

1

0

3

@esindurmusnlp

Esin Durmus

3 years

We show that the MLE baseline as well as a recently proposed method for improving faithfulness (loss truncation) are both worse than the control at the same level of abstractiveness. 4/n

1

0

3

@esindurmusnlp

Esin Durmus

2 years

We further show that the proposed metrics have a higher correlation with these spurious measures than with human judgements.

1

0

3

@esindurmusnlp

Esin Durmus

1 year

Congrats to amazing @chengmyra1 !!

0

0

2

@esindurmusnlp

Esin Durmus

3 years

@nouhadziri Amazing 🥰

0

0

2

@esindurmusnlp

Esin Durmus

1 month

@manoelribeiro ofc, i really liked your work :)

0

0

2

@esindurmusnlp

Esin Durmus

4 years

@sebgehr @stanfordnlp @jurafsky @tatsu_hashimoto @chrmanning Thanks for always being so supportive!

0

0

2

@esindurmusnlp

Esin Durmus

4 years

@XandaSchofield @clairecardie Thank you! It would be great to get your suggestions on how to have a good connection with the students especially in the current setting. You will do great as always ♥️

1

0

2

@esindurmusnlp

Esin Durmus

10 months

@soldni @chengmyra1 @jurafsky thanks so much, @soldni !!

0

1

2

@esindurmusnlp

Esin Durmus

4 years

@vnfrombucharest @UvA_Amsterdam Congrats 🎊🎈 😍

0

0

2

@esindurmusnlp

Esin Durmus

1 year

Paper link:

2

0

2

@esindurmusnlp

Esin Durmus

1 month

@ClementDelangue @huggingface @AnthropicAI Thanks for the shoutout, @ClementDelangue ! We discuss the results and share more information about our research here:

@AnthropicAI

Anthropic

1 month

New Anthropic research: Measuring Model Persuasiveness We developed a way to test how persuasive language models (LMs) are, and analyzed how persuasiveness scales across different versions of Claude. Read our blog post here:

Tweet media one

56

118

712

0

1

2

@esindurmusnlp

Esin Durmus

7 months

@karinanguyen_ You deserve it and more @karinanguyen_ ❤️

0

0

2

@esindurmusnlp

Esin Durmus

3 years

@mervenoyann @huggingface Congrats!! 🎉 best of luck!

1

0

2

@esindurmusnlp

Esin Durmus

3 months

@michaelryan207 @natolambert @johnschulman2 @jackclarkSF @johnamqdang Great research! Thanks for building on our work :)

1

0

2

@esindurmusnlp

Esin Durmus

4 years

@asayeed @Tuhin66978276 but I think citation count itself is more correlated with how trendy the topic is rather than the quality of the work.

1

0

1

@esindurmusnlp

Esin Durmus

2 years

Needless to say, @aylin_cim and her work is amazing!! Go work with her!! ✨

@aylin_cim

Aylin Kamelia Caliskan

2 years

I'm recruiting Ph.D. students interested in "Implicit Machine Cognition" to study AI Ethics and Bias & Human-AI interaction in ML, NLP, Computer Vision, and Speech. Apply to @UW_iSchool & @uwcse and join our @uwnlp & @uwdub communities. Please share!

12

92

316

0

0

1

@esindurmusnlp

Esin Durmus

3 years

@jmhessel @allen_ai @uwcse 🥳 Congrats!

0

0

1

@esindurmusnlp

Esin Durmus

4 years

*are you doing 😬

1

0

1

@esindurmusnlp

Esin Durmus

4 years

@barbara_plank @stanfordnlp @jurafsky @tatsu_hashimoto @chrmanning Thanks a lot @barbara_plank ♥️

0

0

1

@esindurmusnlp

Esin Durmus

1 year

@bkhmsi Good luck!! :)

0

0

1

@esindurmusnlp

Esin Durmus

4 years

@bastings_nlp Congratulations 🎉 😊

0

0

1

@esindurmusnlp

Esin Durmus

11 months

@MonaDiab77 Thanks Mona ❤️❤️

0

0

1

@esindurmusnlp

Esin Durmus

4 years

@nouhadziri @emnlp2020 @JialuLi96 @uncnlp Thank you😊

0

0

1

@esindurmusnlp

Esin Durmus

4 years

@thompson_laure @UMassAmherst Congrats Laure! 😊

1

0

1

@esindurmusnlp

Esin Durmus

2 years

@nouhadziri @allen_ai @YejinChoinka Congratulations ❤️ will definitely visit you in Seattle ☺️

1

0

1

@esindurmusnlp

Esin Durmus

4 years

@JialuLi96 Of course!! Thanks for your hard work 😊

0

0

1

@esindurmusnlp

Esin Durmus

4 years

@dipanjand @CNNTravel @manaalfar Wow. How did I miss these 😀

0

0

1

@esindurmusnlp

Esin Durmus

12 days

@GriffinAdams92 @answerdotai @jeremyphoward @ericries Congrats @GriffinAdams92 ! Very excited for you and @answerdotai :)

0

0

1

@esindurmusnlp

Esin Durmus

4 years

@Diyi_Yang @clairecardie Thank you! ♥️

0

0

1

@esindurmusnlp

Esin Durmus

4 years

@migballesteros Congrats!

0

0

1

@esindurmusnlp

Esin Durmus

2 years

@manningcics @MohitIyyer @open_phil Congrats @MohitIyyer !

0

0

1

@esindurmusnlp

Esin Durmus

11 months

@tanyaagoyal @UTCompSci @gregd_nlp @jessyjli Congrats! enjoy Gimme coffee at Gates ☕️

1

0

1

@esindurmusnlp

Esin Durmus

4 years

@TuhinChakr Thank you so much!

0

0

1

@esindurmusnlp

Esin Durmus

3 months

@colinmegill Thank you @colinmegill ! ♥️

0

0

1