Kai-Wei Chang @kaiwei_chang Twitter profile

Last Seen Profiles

@iriesentner

@ByBy54075014833

@mattsmithsoccer

@RecruitSoccerXP

@n_ssouza

@academydublin

@veganmaoism

@kalimat_888

@ZDPFC

@AFLSlasher

@prakhar4real

@KhloeMahaffey_9

@janfrodeno

@Alpro

@thesarzacademy

@catmourie

@crostoher377

@matthewjura

@KoichFuj

@CocoBelleChanel

@CelticDale

@ParadigmSports

@miharatakuto

@kumiko_dreams

@fca_guy

@MaliaKelley2026

@ann_forcino

@BroodSports

@VAIROck14

@2ojworg0Hoqq8Pz

@iPDeZbnAiBLAhDX

@PPNam92

@freedomrises76

@elvosque

@the_avigeek

@budere1

Kai-Wei Chang

@kaiwei_chang

3 years

I’m thrilled to present my best collaboration with @VioletNPeng — our baby girl, Andrea Yalan Chang 🐣Welcome to the world! ❤️

33

4

546

Kai-Wei Chang

@kaiwei_chang

4 years

As AC/author, I see an increasing trend of reviews criticizing results/approaches are not surprised. A scientific paper is not Sci-Fi. We value novel but reasonable approaches; rigor and comprehensive experiments to support the claims. Why do we expect a surprise in a paper?

12

39

498

Kai-Wei Chang

@kaiwei_chang

6 months

If you're seeking an advisor in NLP, consider exploring options with recently appointed faculty. While established senior folks are well-known, junior folks shine as rising stars. In fact, many successful PhDs are the first few students of their advisor. Don't miss the chance!

3

59

483

Kai-Wei Chang

@kaiwei_chang

6 months

Here's a list of NLP superstars 🌟 who are beginning their journey 🚀 in the 2023/24 academic year. @jieyuzhao11 @GabrielSaadia @acbuller @Lianhuiq @ManlingLi_ @yuntiandeng @rajammanabrolu @YueDongCS @tanyaagoyal @MinaLee__ @yuntiandeng @alsuhr @wellecks @hllo_wrld @Xinya16

19

41

288

Kai-Wei Chang

@kaiwei_chang

3 years

Honored to be awarded Sloan Fellowship for our work on fairness, robustness, inclusion in Human Language Technology at #UCLANLP . The award belongs to my students and collaborators. Thank the NLP/ML/AI community and @UCLAengineering to support our work

Four UCLA faculty members awarded 2021 Sloan Research Fellowships

Kai-Wei Chang, Pavel Galashin, Ravi Netravali and Harold Pimentel are among the new class of young researchers recognized for their scientific achievements.

newsroom.ucla.edu

16

9

217

Kai-Wei Chang

@kaiwei_chang

1 year

ACL/ICML highlights threats of LMs like ChatGPT generating paper content. However, I'm more concerned about reviews. Example: ChatGPT generates confident but nonsensical reviews better than any R2. Now, it's AC's job to spot real reviews, but I lack confidence in doing so

4

22

210

Kai-Wei Chang

@kaiwei_chang

2 years

Yaya’s second conference. Thanks #NAACL2002 for preparing a great kidz room!

4

3

206

Kai-Wei Chang

@kaiwei_chang

4 years

The problem is much more beyond data bias. ML systems can be poorly calibrated () and bias in the data might be amplified (, ) i.e., simply diversifying the data source might not solve the problem.

Yann LeCun

@ylecun

4 years

ML systems are biased when data is biased. This face upsampling system makes everyone look white because the network was pretrained on FlickFaceHQ, which mainly contains white people pics. Train the *exact* same system on a dataset from Senegal, and everyone will look African.

109

436

3K

4

50

191

Kai-Wei Chang

@kaiwei_chang

2 months

📢Please join me in congratulating Harold Li @LiLiunian for passing his Ph.D. defense today🎉 Harold has accomplished remarkable work and has been a pioneer in vision-language foundation models. 🧵 1/

4

16

176

Kai-Wei Chang

@kaiwei_chang

5 months

PM me to grab☕️ at #NeurIPS2023 . I am seeking PhD/postdocs to join @uclanlp in Fall24 in areas: - Trustworthy NLP👼: Align LLM with human values and ensure they safe uses - Multimodal🙈: Align vision and language - LLM Reasoning🤔: LLMs in commonsense, logical, math reasoning

1

20

168

Kai-Wei Chang

@kaiwei_chang

2 months

I am honored to be nominated by SIGDAT (the org that oversees EMNLP) to run for VP-elect with other awesome candidates who share the goal of improving our community. Please check your email to vote by 3/24.🗳️ See details:

Alice Oh

@aliceoh

2 months

ACL #SIGDAT members, look in your inbox for VP-elect and Secretary/Treasurer elections. The candidates are really awesome, so you may have a hard time picking just one each. @emnlpmeeting @IAugenstein @MonaDiab77

0

5

15

3

36

133

Kai-Wei Chang

@kaiwei_chang

11 months

I’m at #ACL2023 this week. @uclanlp members 🐻 and my collaborators at @AmazonScience will present the following papers at the conferences on the topics around trustworthy NLP, vision-language, and language+reasoning. See details at 🧵👇

3

21

129

Kai-Wei Chang

@kaiwei_chang

3 years

This made my day ;-) I'm so proud of my group @uclanlp 🐻

0

5

129

Kai-Wei Chang

@kaiwei_chang

3 years

Dear friends, @hhexiy @robinomial @sameer_ and I will present a tutorial on "Robustness and Adversarial Examples in NLP" virtually at #EMNLP2021 9am AST tomorrow (Nov 11). See you there! #NLProc Presentation link: Slides/Website:

0

20

122

Kai-Wei Chang

@kaiwei_chang

6 months

It is excited to see a full room of 250 participants to attend SoCal NLP. We have 151 posters this year!

SoCal NLP Symposium

@socalnlp

6 months

This year’s #SoCalNLP has started! 🙌🏼 Opening remarks by @kaiwei_chang on the history of SoCal NLP and NLP research groups around this region!

0

16

1

10

113

Kai-Wei Chang

@kaiwei_chang

6 months

Indeed, it's impressive to see Gemini team act fast on new benchmarks. Our MathVista, released a month ago also been tested there. It's happy to see how the spirit of open science and platforms like @huggingface have simplified model reproduction/testing. P.S. MathVista was led

Yu Su

@ysu_nlp

6 months

Hi @emilymbender , I'm one of the lead authors of MMMU. I can certify that 1) Google didn't fund this work, and 2) Google didn't have early access. They really like the benchmark after our release and worked very hard to get the results. It doesn't take that long to eval on a

10

53

977

0

12

110

Kai-Wei Chang

@kaiwei_chang

7 months

Congrats to @LiLiunian for winning Google PhD Fellowship! 🎉🥳🎊 Harold led pioneering efforts in vision-language research, including developing notable models such as VisualBERT, CLIP, and recently introduced Desco. He will be on the market this year! @uclanlp @UCLAengineering

Google AI

@GoogleAI

7 months

In 2009, Google created the PhD Fellowship Program to recognize and support outstanding graduate students pursuing exceptional research in computer science and related fields. Today, we congratulate the recipients of the 2023 Google PhD Fellowship!

23

94

587

4

7

93

Kai-Wei Chang

@kaiwei_chang

4 years

In the coming days, I'll tweet in English and Chinese for papers in Ethics & NLP and Theme areas @aclmeeting . Kudos to @emilymbender for the initiative of multi-lingual live-microblogging 我將會在tweet上即時轉撥ＡＣＬ會議

1

8

87

Kai-Wei Chang

@kaiwei_chang

6 months

One of my favorite papers!🚀 Instruction fine-tuning datasets are typically generated by mimicking human-annotated seed sets. But, why don't we construct instruction fine-tuning data from real datasets in repositories like in 🤗. Check out our #EMNLP23 paper!

Da Yin

@Wade_Yin9712

6 months

🦖 Dynosaur was accepted at EMNLP 2023! #EMNLP2023 In the new version, we further show Dynosaur’s great perf. on Longform! We’ll present Dynosaur in Poster Session 2 14:00-15:30 SGT Preprint: Code:

0

10

59

1

10

85

Kai-Wei Chang

@kaiwei_chang

2 months

Congrats 🎉 to the newly titled Dr. Lu @lupantech on defending his thesis about mathematical reasoning with language models"! 🧮 Pan has published a series of works on quantifying and improving math and scientific reasoning ability in LLMs. Some highlights:

1

5

82

Kai-Wei Chang

@kaiwei_chang

7 months

Hi friends, We will host the Southern California NLP (SoCal NLP) symposium at UCLA on 11/17 this year. see CFP and more information at

SoCal NLP Symposium

@socalnlp

7 months

Hello World! 🙌🏼 #SoCalNLP2023 is back this year, to be held @UCLA ! 🏝️☀️ Keep an eye here for more announcements, but for now, our CfP is open! More details ⬇️ 🔗 📆Nov. 17, 2023

1

14

29

0

15

77

Kai-Wei Chang

@kaiwei_chang

4 years

@zacharylipton This is the answer from GPT-2😅: We will have real, mass-deployed, fully autonomous self-driving cars in the next O(n) years, where n = 10 000. The theoretical limit of this scenario is not n = 10 000, but it is still, a lot of n's, to do n = 10 000 …

1

5

78

Kai-Wei Chang

@kaiwei_chang

4 years

DM me if you're interested in a postdoc opportunity at UCLA NLP to work on exciting topics including fairness/robustness in NLP, machine common sense, cross-lingual transfer, language generation, and more! @VioletNPeng

Computing Research

@CRAtweets

4 years

NSF DCL: Announcing the CIFellows 2020 Postdocs Project

1

39

60

3

19

76

Kai-Wei Chang

@kaiwei_chang

3 years

Congrats Dr. Ahmad ( @ahmadwasi , ) 🥂🎈🎉 for passing his thesis defense! Wasi has done many impactful works in topics ranging from cross-lingual transfer, information retrieval, to NLP for programming languages. #proudadvisor #NLProc

1

4

72

Kai-Wei Chang

@kaiwei_chang

2 years

GLIP is listed as a finalist for CVPR best paper. Congrats @LiLiunian and coauthors. 👏

Liunian Harold Li

@LiLiunian

2 years

Happy to share our work on Object Detection in the Wild through Grounded Language Image Pre-training (GLIP) (Oral at #CVPR2022 )! Superior zero-shot and few-shot transfer learning performance on 13 object detection downstream tasks!

3

41

263

0

3

67

Kai-Wei Chang

@kaiwei_chang

3 years

Absolutely second this. A proposal I spent several months on was declined on the same day I received the Sloan award letter. Ping me if you want to hear more failure stories. Sometimes lucky, sometimes not, just believe what you love to do. I'll cheer for you.

1

3

65

Kai-Wei Chang

@kaiwei_chang

7 years

Our paper on reducing bias amplification in structured models got Best long paper Award @emnlp2017 . #FATML #NLProc

Men Also Like Shopping: Reducing Gender Bias Amplification using...

Language is increasingly being used to define rich visual recognition problems with supporting image collections sourced from the web. Structured prediction models are used in these tasks to take...

arxiv.org

emnlp2017

@emnlp2017

7 years

Best long papers 1: Jieyu Zhao et al. Men Also Like Shopping: Reducing Gender Bias Amplification

1

20

33

2

10

64

Kai-Wei Chang

@kaiwei_chang

4 years

Thank you @AmazonScience for supporting our research on building robust contextualized representations

Amazon Science

@AmazonScience

4 years

Congratulations to the 51 award recipients of the 2019 Amazon Research Awards, who represent 39 universities in 10 countries. View the full list and find out how to be added to the 2020 Call For Proposal distribution list here: #AmazonResearchAwards

1

11

69

2

3

60

Kai-Wei Chang

@kaiwei_chang

4 years

Congratulate Jieyu Zhao @jieyuzhao11 on winning the prestigious Microsoft Research Ph.D. Fellowship! Jieyu's research on examining and mitigating social prejudices in NLP models has made a great broader impact. The award is well deserved.

Microsoft Research

@MSFTResearch

4 years

Congratulations to the 2020 Ada Lovelace and PhD Fellowship recipients! Their work, ranging from applications in mental health & neuroscience to quantum computing & model bias, leads a new vanguard in technology’s evolution. Learn more about 2020 fellows:

3

88

319

0

5

57

Kai-Wei Chang

@kaiwei_chang

4 years

The subtitles of ACL recordings generated by ASR are hilarious..🤣 obvious, the language model is off-the-path and should be pre-trained on ACL anthology.. or the ASR should leverage the presenting paper as input when decoding...

1

56

Kai-Wei Chang

@kaiwei_chang

10 months

Welcome to the 3rd TrustNLP workshop! Hal is giving keynote talk now.

1

3

57

Kai-Wei Chang

@kaiwei_chang

6 months

It's application season! We might consider getting help from ChatGPT to draft SOP, reference letters, etc😏. But, hold on!✋ Yixin found that LLMs often perpetuate traditional stereotypes, portraying men as agentic (like natural leaders) and women as communal (such as well-liked

Yixin Wan

@yixin_wan_

6 months

Might be slightly last minute, but I’m thrilled to announce that I will also be giving a talk on our paper in the @gem_workshop this afternoon! 🤩 The session will start at 2pm, in room Leo 2, but it will also be co-hosted through zoom. Drop by and say hi! 😁

0

2

30

1

9

54

Kai-Wei Chang

@kaiwei_chang

3 years

Check out our new #EMNLP2021 paper on non-binary gender in NLP. I learned a lot from this diverse team, which brings in many new perspectives. Thank for the team and survey respondents, who make this happens.

Arjun Subramonian (they/அவங்க/elle)

@arjunsubgraph

3 years

🌈 Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies 🏳️‍⚧️ #EMNLP2021 paper w/ @sunipa17 @MMonajatipoor @ovalle_elia @probablyjeff @kaiwei_chang @uclanlp 👉 paper: 👉 blog post: 👇 🧵

4

30

96

0

9

52

Kai-Wei Chang

@kaiwei_chang

15 days

Congrats Tao Meng ( @TaoMeng10 ) for passing his defense! 🎉 Tao's research centers on integrating constraints into LLM inference and learning, a challenging yet crucial aspect for effectively controlling large LLMs.

1

3

51

Kai-Wei Chang

@kaiwei_chang

4 years

Welcome to the UCLA family :-)

Violet Peng

@VioletNPeng

4 years

I almost feel shy to share personal news during this pandemic time: I'll join UCLA CS as an assist. prof. with my PlusLab this summer. I'm excited about the upcoming collaborations with new colleagues and continuing to contribute to SoCal-NLP. @CS_UCLA #SoCalNLP 1/2

48

8

511

3

0

50

Kai-Wei Chang

@kaiwei_chang

3 years

Can we generate syntactically controlled paraphrase without parallel data? 🧐 Check out our (w/ @kuanhao_ ) recent paper at #EACL2021 . We also apply this to improve the robustness of models against syntactically adversarial attacks.🛡️

Kuan-Hao Huang

@kuanhaoh_

3 years

Check out our #EACL2021 paper on controlled paraphrase generation! We show that it's possible to control the syntax of paraphrases and generate syntactically various paraphrases without using annotated paraphrase pairs. (, w/ @kaiwei_chang ) [1/2] #UCLANLP

1

50

1

10

49

Kai-Wei Chang

@kaiwei_chang

2 months

Thank you to everyone who submitted ICML/ACL-ARR reviews on time or is still working on them during the spring break 🏖️& COLM 🦙 deadline. If you still owe reviews, please kindly respond to your AC/SAC so that they know whether they need emergency reviewers 🙏

1

2

47

Kai-Wei Chang

@kaiwei_chang

4 years

UCLA-NLP will present at #acl2020nlp . 👇Check out our ACL/TACL papers and pre-recorded talks at Look forward to meeting everyone virtually😄 #NLProc

1

9

48

Kai-Wei Chang

@kaiwei_chang

2 months

I'm grateful for the opportunity to serve as SIGDAT officer. Thank you all for the support and ideas contributing to improving our community. 🥰

Officers & Organizing Committee

SIGDAT officers & organizing committee.

sigdat.org

Kai-Wei Chang

@kaiwei_chang

2 months

I am honored to be nominated by SIGDAT (the org that oversees EMNLP) to run for VP-elect with other awesome candidates who share the goal of improving our community. Please check your email to vote by 3/24.🗳️ See details:

3

36

133

1

4

46

Kai-Wei Chang

@kaiwei_chang

11 months

Congrats @NikilSelvam and our collaborators @sunipa17 , @DanielKhashabi , @tusharkhot for winning the outstanding paper award at #ACL2023 . See details of the paper 👇 @uclanlp

ACL 2024

@aclmeeting

11 months

Outstanding Papers at #ACL2023NLP . Congrats to all authors!! 📚 Backpack Language Models 🔎 CAME: Confidence-guided Adaptive Memory Efficient Optimization 🌍 Causes and Cures for Interference in Multilingual Translation [1/n]

1

25

113

2

5

45

Kai-Wei Chang

@kaiwei_chang

3 years

How to transfer a relation/event extraction model across different languages by leveraging parse structures? 🧐 Come to our Graph Attention Transformer Encoder (GATE) paper () at #AAAI2021 @ahmadwasi @VioletNPeng #UCLANLP (1/3)

1

3

44

Kai-Wei Chang

@kaiwei_chang

6 years

Come to see our poster on gender bias on coref — we identify the source of bias and present debaising approach @NAACLHLT

1

9

43

Kai-Wei Chang

@kaiwei_chang

1 year

Do you have a paper on privacy, robustness, fairness, faithfulness, ethics, or safety in NLP? The 3rd edition of the Trustworthy NLP workshop will be co-located with #ACL2023 . The submission deadline is 4/24. Please find CFP here:

1

8

42

Kai-Wei Chang

@kaiwei_chang

2 months

📢 Attention, trustworthy NLP researchers! 📢 If you have papers on fairness, robustness, ethics, transparency, safety, misinformation, hallucination, etc, in NLP, we invite you to submit your papers to NAACL @trustnlp workshop by 3/27!

Anaelia (Elia) Ovalle

@ovalle_elia

3 months

📢 #NAACL2024 @trustnlp Workshop CFP is out! 🔖Topics include multi-modal generative bias, fairness in LLM+human feedback, misinformation & more! 🌐 ✔️Deadline: March 27 (Direct)/April 5 (Fasttrack) 🌎We esp. encourage regionally-relevant submissions

0

16

26

1

9

38

Kai-Wei Chang

@kaiwei_chang

2 years

@guyvdb Even my acceptance recommendation at the AC level gets overturned 😒. I felt bad for the paper. I spent several hours carefully reading the reviews, discussions, and some of broaderline rating papers like this one. I believe SACs did the same.

1

0

40

Kai-Wei Chang

@kaiwei_chang

11 months

Big congrats to @kuanhaoh_ Varun, @IHung_Hsu , Anoop, @aram_galstyan for winning Area Chair Award at #ACL2023 . @uclanlp , @AmazonScience

Kuan-Hao Huang

@kuanhaoh_

11 months

📢New paper📢 We propose 𝑷𝒂𝒓𝒂𝑨𝑴𝑹, a large-scale syntactically diverse paraphrase dataset constructed by AMR back-translation, and show its 🔥potential🔥 on several NLP tasks! Work w/ Varun, @IHung_Hsu , Anoop, @kaiwei_chang , @aram_galstyan [1/n]

2

8

35

0

7

38

Kai-Wei Chang

@kaiwei_chang

18 days

Congratulations to the @uclanlp alumnus, Kuan-Hao on his new position at TAMU! I'm eager to see him lead transformative AI research in the future. 🤩

Kuan-Hao Huang

@kuanhaoh_

18 days

I am thrilled to share that I will join the Department of Computer Science and Engineering at @TAMU as an Assistant Professor in Fall 2024. Many thanks to my advisors, colleagues, and friends for their support and help. I'm really excited about the new journey at College Station!

34

20

263

0

2

37

Kai-Wei Chang

@kaiwei_chang

3 years

Just realize that there is an abstract submission deadline for ACL...😲 Thank you, whoever retweet this...

ACL 2024

@aclmeeting

3 years

Abstract submission deadline is Jan 25 so hurry up! - the abstract is mandatory - withdraw allowed by Feb 1 - in case of multiple submissions of the same paper, keep only one - check your inbox for the automatic confirmation email after submission #ACL2021NLP #NLProc

3

35

91

0

7

36

Kai-Wei Chang

@kaiwei_chang

4 years

How grammatical errors affect language encoders?🧐Our #acl2020nlp : "On the Robustness of Language Encoders against Grammatical Errors"( w/Fan Yin, Quanyu Long, Tao Meng) diagnoses encoders by simulating grammatical errors with adversarial attacks. #NLProc

On the Robustness of Language Encoders against Grammatical Errors

On the Robustness of Language Encoders against Grammatical Errors Share this page: On the Robustness of Language Encoders against Grammatical Errors Fan Yin, Quanyu Long, Tao Meng, and Kai-Wei Chang,...

web.cs.ucla.edu

1

3

36

Kai-Wei Chang

@kaiwei_chang

3 years

How bias are today's open-ended language generation models? 🧐Check out our #facct2021 paper and a new benchmark on systematically measuring fairness/bias in NLG @AmazonScience #NLProc

BOLD: Dataset and metrics for measuring biases in open-ended language generation

Recent advances in deep learning techniques have enabled machines to generate cohesive open-ended text when prompted with a sequence of words as context. While these models now empower many downstr...

www.amazon.science

Jwala Dhamala

@jwaladhamala

3 years

Our paper & dataset BOLD on measuring fairness in language generation is available: ; coauthors Tony, Varun, @kaiwei_chang @rahul1987iit @yadapruksachatk @Satya87935608 If you are attending #facct2021 , please consider attending our QA session on March 10

1

3

14

1

6

34

Kai-Wei Chang

@kaiwei_chang

3 years

I'll host a BoF Session on Ethics, Bias, and Fairness in NLP, Wed (Jun 9) 15:00 Seattle / 18:00 New York / 23:00 London / Thu(Jun 10) 3:30 Delhi / 6:00 Beijing / 8:00 Sydney. If you have topics you would like to discuss, DM me or post here

NAACL 2021 Annual Conference of the North American Chapter of Computational Linguistics Whova Web...

June 6 – 11, 2021

whova.com

0

7

35

Kai-Wei Chang

@kaiwei_chang

3 years

When performing transfer learning with multiple sources, one key question is how much info one can leverage from each source. In #NAACL2021 paper, Rizwan Parvez @uclanlp developed SEAL-SHAP, an efficient source valuation framework for quantifying the usefulness of the sources 1/n

1

7

34

Kai-Wei Chang

@kaiwei_chang

2 months

Designing an inclusive LLM 👩‍👩‍👧‍👧 requires attention to every detail. The new paper by @ovalle_elia highlights the impact of technical design decisions like tokenization on the model's inclusivity. Congrats on getting it to NAACL-Finding! @AmazonScience

Anaelia (Elia) Ovalle

@ovalle_elia

3 months

🚨LLM problems - esp. those that result in harmful biases - can indeed arise from tokenization! Turns out, BPE tokenization hinders LLM abilities to correctly use gender-neutral pronouns, thereby exacerbating LLM misgendering. Thread below ~ 📝 🧵 [1/n]

3

25

112

1

8

32

Kai-Wei Chang

@kaiwei_chang

4 years

This tweet is about an #acl2020nlp paper "Give Me Convenience and Give Her Death: Who Should Decide What Uses of NLP are Appropriate, and on What Basis?" by Kobi Leins, Jey Han Lau, Timothy Baldwin. 1/n

1

4

32

Kai-Wei Chang

@kaiwei_chang

6 years

I'm honored to receive this research award. Thanks to the donor and my collaborators.

UCLA CS Department

@CS_UCLA

6 years

Congratulations to Professor Kai-Wei Chang for winning the 2018 Okawa Research Grant! Read more about it here:

1

3

12

1

0

31

Kai-Wei Chang

@kaiwei_chang

2 years

The @AmazonScience team that I collaborate with is looking for a postdoc in the area of AI fairness. PM me if you are interested.

1

7

30

Kai-Wei Chang

@kaiwei_chang

3 years

VisualBERT has been added to @huggingface !! Thanks, @gchhablani_ 's great effort! Now you can use VisualBERT in Huggingface 🤗() or in MMF () 😎

Model Zoo | MMF

Here is the list of models currently implemented in MMF:

mmf.sh

0

5

30

Kai-Wei Chang

@kaiwei_chang

6 months

I have to skip EMNLP (but I'll be at Neurips 23). Please talk to our students from UCLA about our work in fairness in NLG, limitations of VIsion-Language models, effective instruction tuning, and Embodied Instruction Following

uclanlp

@uclanlp

6 months

Excited for #EMNLP2023 ? #UCLANLP & members @cfyang58 @Wade_Yin9712 @FanYin63689862 @kamath_amita @DiWu0162 @P_N_Kung @telinwu @sunjiao123sun_ @HaoyiQiu @yufei_t @yu_bryan_zhou will present a range of work on NLG, fairness, instruction tuning, and multi-modality. 🧵👇 (1/18)

1

16

29

0

1

29

Kai-Wei Chang

@kaiwei_chang

6 years

Ben’s group @JHU has a paper with similar title. Similar idea but with a different focus. It’s nice that they put the posters side by side, showing the gender bias in coref is verified independently by two groups.

0

6

28

Kai-Wei Chang

@kaiwei_chang

11 months

Thrilled to be a part of the ECOLE program and work with this incredible team. We will develop human-machine collaborative approaches to analyze image, video, and multimedia data through vision and language in the era of generative AI🚀. @uclanlp

Heng Ji

@hengjinlp

11 months

We are very excited to kick off our DARPA ECOLE project, and extremely proud of this super young and diverse group of PIs for our MIRACLE team that I have put up together with @cvondrick

0

6

68

1

28

Kai-Wei Chang

@kaiwei_chang

5 years

(1/5) UCLANLP is associated with the following presentations at #emnlp2019 / #CoNLL . Interested in fairness in NLP? Check out 1) our tutorial (Mon); 2) talk on bias in NLG ; 3) poster on bias in language with grammatical gender

1

5

27

Kai-Wei Chang

@kaiwei_chang

2 months

Thanks, @_akhaliq for highlighting the paper. See more details in @lupantech 's tweet:

AK

@_akhaliq

2 months

MathVerse Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems? The remarkable progress of Multi-modal Large Language Models (MLLMs) has garnered unparalleled attention, due to their superior performance in visual contexts. However, their capabilities in

1

72

258

0

3

26

Kai-Wei Chang

@kaiwei_chang

3 years

I gave a tutorial on Transferable Representation Learning in NLP at #ODSCWest . The talk summarizes our recent research on cross-lingual transfer, Vision&Langauge pre-training (VisualBERT), Programming&Natural Languages pre-training (PLBART) See slides:

1

3

26

Kai-Wei Chang

@kaiwei_chang

6 months

Hire him! Kuan-Hao completed PhD with me and now is a postdoc at UIUC. He had a series of significant works in NLP, particularly in (1) generative event extraction and (2) enhancing robustness against syntactic perturbations. I'm always amazed by his ideas🤯 He is one of a kind.

Kuan-Hao Huang

@kuanhaoh_

6 months

Heading to Singapore for #EMNLP2023 soon🚀🚀 Let's discuss about language understanding/information extraction/ knowledge generalization! I am on the faculty job market this year. Feel free to schedule a chat with me!

0

4

21

0

3

26

Kai-Wei Chang

@kaiwei_chang

5 years

I'm looking for a postdoc in NLP/ML at UCLA. PM me if you're interested. #naacl2019

0

6

25

Kai-Wei Chang

@kaiwei_chang

3 years

Big congrats @arjunsubgraph for winning the Outstanding Bachelor of Science Award! Well deserved!

UCLA Samueli Engineering

@UCLAengineering

3 years

Congratulations to our @UCLA Engineering #Classof2021 school-wide award winners! #UCLASamueli2021 #UCLA2021 #EngineerTogether

0

3

17

4

1

25

Kai-Wei Chang

@kaiwei_chang

11 months

Our tutorial on indirectly supervised NLP is about to start

Kai-Wei Chang

@kaiwei_chang

11 months

First, on 7/9, I’ll share insights on leveraging indirect supervision signals for learning vision-language representation at the 'Indirectly Supervised NLP' tutorial.

1

0

5

0

2

25

Kai-Wei Chang

@kaiwei_chang

4 years

@annargrs This can be simply done by announcing the ID of accepted papers. CVPR does this...

1

2

25

Kai-Wei Chang

@kaiwei_chang

3 years

Interested in privacy, fairness, explainability, accountability, security, ethics in NLP systems? 🤖Consider submitting papers or participating in TrustNLP workshop at NAACL 2021. Details:

trustnlp

@trustnlp

3 years

Excited to announce our first workshop on Trustworthy Natural Language Processing, held as part of @NAACL 2021 in Mexico City this June. Call for papers and details on submission can be found at . See you there!

1

4

0

3

24

Kai-Wei Chang

@kaiwei_chang

4 years

Thank you, the organizing committee for the amazing #acl2020nlp !!

1

24

Kai-Wei Chang

@kaiwei_chang

4 years

This tweet is for the paper “Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation” by @Tianlu_Wang , @VictoriaLinML , @nazneenrajani , @BMarcusMcCann , @bluevincent , @CaimingXiong at #acl2020nlp #acl2020en #acl2020zht 1/n

1

8

24

Kai-Wei Chang

@kaiwei_chang

3 years

How to bridge typological differences across languages in cross-lingual transfer?🧐 Check out @ahmadwasi 's #ACL2021 paper ()! We showed that explicitly encode dep parse tree with GAT into M-BERT improves cross-lingual transfer. Happy to talk about it at ACL

0

1

24

Kai-Wei Chang

@kaiwei_chang

5 years

Check out our new paper.

Mark Yatskar

@yatskar

5 years

hot off the press -- VisualBert: A simple and performant baseline for vision and language. Language + image region proposals -> stack of Transformers + pretrain on captions = SOTA or near on 4 V&L problems. @LiLiunian +Cho-Jui Hsieh +Da Yin @kaiwei_chang

3

29

107

0

24

Kai-Wei Chang

@kaiwei_chang

5 years

Thanks, @emilymbender 's awesome live tweeting. The full talk “Gender Bias in Contextualized Word Embeddings (NAACL 2019)” is on YouTube now. Great job @jieyuzhao11 !

Gender Bias in Contextualized Word Embeddings (NAACL 2019)

Paper: https://arxiv.org/abs/1904.03310

www.youtube.com

@[email protected] on Mastodon

@emilymbender

5 years

Next up: “Gender Bias in Contextualized Word Embeddings” by @jieyuzhao11 , Tianlu Wang, @yatskar , @ryandcotterell , @bluevincent , and @kaiwei_chang #NAACL2019 #ethnlp

1

5

11

0

5

23

Kai-Wei Chang

@kaiwei_chang

2 years

UCLA CS is hiring this year! 🥳 We have multiple open rank tenure-track faculty positions. We especially encourage candidates who commit to mentor students from underserved populations to apply.

UCLA Computer Science

@UCLAComSci

2 years

Multiple open-rank faculty positions are available at UCLA Computer Science Department. Apply today:

0

3

8

0

2

23

Kai-Wei Chang

@kaiwei_chang

2 months

Check out Xiao's paper on argument sufficiency assessment👩‍🏫. She proposed a framework to determine whether the conclusion is well-supported by premises using probability of sufficiency. Congrats on getting it to NAACL!

Xiao Liu

@xxxxiaol

2 months

Excited to get CASA accepted by NAACL! Is your conclusion sufficiently supported by the premises? Check out our framework at

0

5

24

1

23

Kai-Wei Chang

@kaiwei_chang

6 months

Kareem, co-advised by @guyvdb and me is on the faculty job market🚀 Grab ☕️ w/ him at #NeurIPS2023 if your dep. is hiring. He has done amazing work on neuro-symbolic AI 🤖 This specific paper enables us to inject logical constraints in autoregressive models like language models.

kareem ahmed

@KareemYousrii

6 months

Neuro-Symbolic (NeSy) methods inject constraints into NNs, but do not support autoregressive models e.g. transformers. We propose Pseudo-Semantic loss a NeSy framework for injecting arbitrary logical constraints into autoregressive models. At #NeurIPS2023 !

1

12

53

0

2

23

Kai-Wei Chang

@kaiwei_chang

5 months

Check out the new analysis of Visual Math Reasoning with Bard, GPT-4V, Gemini by @lupantech . Interestingly, Gemini and GPT-4V have slightly different skill sets (see the radar graph). Thanks @lupantech for the quick analysis during the confernece, @JeffDean to connect us to

Pan Lu

@lupantech

5 months

💥💥Update Alert! Radar graphs & leaderboard on #MathVista now feature detailed scores for the #Gemini family models. 🚀 🔍 Insight: Gemini Ultra leads the pack, outperforming GPT-4V by 3.1%! Yet, each model shines uniquely in various math reasoning & visual contexts. 🙏 Big

2

16

83

0

2

23

Kai-Wei Chang

@kaiwei_chang

5 years

@yatskar @LiLiunian Our source code and models are public now

GitHub - uclanlp/visualbert: Code for the paper "VisualBERT: A Simple and Performant Baseline for...

Code for the paper "VisualBERT: A Simple and Performant Baseline for Vision and Language" - uclanlp/visualbert

github.com

0

4

22

Kai-Wei Chang

@kaiwei_chang

6 months

Very proud to be a colleague of these young talents! Congrats @GabrielSaadia & @adityagrover_

UCLA Samueli Engineering

@UCLAengineering

6 months

Congrats to @UCLA Asst. Prof. @adityagrover_ and incoming Asst. Prof. Saadia Gabriel @GabrielSaadia of @CS_UCLA on being named to @Forbes ' 30 Under 30 list in science. Grover and Gabriel were each recognized for their work using artificial intelligence.

0

4

20

1

22

Kai-Wei Chang

@kaiwei_chang

5 years

Appendix A in our NIPS paper explicitly discusses the same issue of 3COSADD as in the "Sensational" paper. This is the reason why we need to design a different experiment.

Adam Tauman Kalai

@adamfungi

5 years

"Sensational" paper criticizes our paper on bias in word embeddings for using the parallelogram analogy alg. (min_x |x-y+a-b|), but we don't use that alg. at all (see img) and we UPPER-bound |x-y| not lower-bound it. Don't trust everything on arxiv. :-)

10

50

168

2

3

22

Kai-Wei Chang

@kaiwei_chang

3 years

Check out our #ACL2021 paper() on NLP for privacy policy docs. We collaborate w/ security researchers and law school to annotate PolicyIE, a corpus consisting of 5,250 intent & 11,788 slot annotations over 31 policies of websites and mobile applications. 1/

1

3

20

Kai-Wei Chang

@kaiwei_chang

7 years

We are moving to LA this summer! I will be joining UCLA-CS, and Nanyun will start her career at USC-ISI. Looking forward!

0

19

Kai-Wei Chang

@kaiwei_chang

3 years

Our #NAACL2021 paper demonstrates the challenges when applying NLP in analyzing narratives from USA’s CDC National Violent Death Reporting System. We showed that Coref suffers from poor transferability due to domain gaps, especially in narratives involved LGBT individuals 1/n

1

6

19

Kai-Wei Chang

@kaiwei_chang

3 years

Check out our #ICML2021 paper on mining constraints with integer linear programming from data.

An Integer Linear Programming Framework for Mining Constraints from Data

An Integer Linear Programming Framework for Mining Constraints from Data Share this page: An Integer Linear Programming Framework for Mining Constraints from Data Tao Meng and Kai-Wei Chang, in ICML,...

web.cs.ucla.edu

Tao Meng

@TaoMeng10

3 years

Can a model learn problem structure/constraints from data? E.g., given pairs of adjacent matrix and corresponding minimal spanning tree, can a model learn to solve MST? Check out our #ICML2021 paper on constraint mining with ILP w/ @kaiwei_chang 1/4

1

5

25

0

3

18

Kai-Wei Chang

@kaiwei_chang

5 years

Check out our EMNLP 19 paper. Congrats to @peizNLP on his first full conference paper. He will be a PhD student at USC.

Pei Zhou

@peizNLP

5 years

Our EMNLP paper "Examining Gender Bias in Languages with Grammatical Gender" is on (w/ @WeijiaShi2 @jieyuzhao11 @kuanhao_ @muhao_chen @ryandcotterell @kaiwei_chang ). We separate semantic and grammatical gender info and found asymmetry between genders.

2

6

19

0

1

18

Kai-Wei Chang

@kaiwei_chang

3 years

📢 New blog post by @jwaladhamala on a new dataset for evaluating bias in natural language generation models.

Amazon Science

@AmazonScience

3 years

At @FAccTConference , Amazon researchers presented a new dataset and methodology for evaluating bias in language models like BERT and GPT-2. Initial experiments did find evidence of bias in texts generated by popular language models. #facct2021

0

2

10

0

4

18

Kai-Wei Chang

@kaiwei_chang

5 years

@VioletNPeng kicks off the second socal NLP symposium hosted by @nlp_usc

0

1

17

Kai-Wei Chang

@kaiwei_chang

3 years

Please consider submitting your work to the Responsible AI #KDD2021 workshop organized by @sunipa17 , Mehrnoosh Sameki, @jwaladhamala , and Cho-Jui Hsieh

Responsible AI @ KDD 2021

@ResponsibleAIK1

3 years

Call for papers for Workshop on Measures and Best Practices for Responsible AI @kdd_news Paper Submission Deadline: May 10th, 2021 Additional details in the link below. #KDD2021

0

7

18

0

2

17

Kai-Wei Chang

@kaiwei_chang

4 years

To read more about fairness research in NLP, see our tutorial slides at EMNLP 19 and resources listed in aclweb #NLProc

0

5

17

Kai-Wei Chang

@kaiwei_chang

7 years

@IAugenstein is presenting NLP beyond sentence-level now at #SPNLP workshop @emnlp2017

0

4

17

Kai-Wei Chang

@kaiwei_chang

4 years

@yoavgo I made a cartoon for a NeuRIPS paper in 2016 as a 3-min highlight. After trying several times and realizing that I cannot speak naturally, I just use a robotic narrative and it's actually not bad🤣...Check it out...

A credit assignment compiler for joint prediction

Many machine learning applications involve jointly predicting multiple mutually dependent output variables. Learning to search is a family of methods where t...

www.youtube.com

0

2

16

Kai-Wei Chang

@kaiwei_chang

11 months

DesCo🪩: Can we teach a vision-language model to recognize objects by language descriptions as a kid does? 🔥 Our new approach leverages LLM for training vision models based on rich descriptions @uclanlp

Liunian Harold Li

@LiLiunian

11 months

Excited to share our new work DesCo () -- an instructing object detector that takes complex language descriptions (e.g., attributes & relations). DesCo improves zero-shot detection (+9.1 APr on LVIS) and ranks 1st at the #OmniLabel Challenge of CVPR2023!

2

14

80

0

4

16

Kai-Wei Chang

@kaiwei_chang

4 years

Cool live notes of the KG-BIAS workshop at AKBC!! Also, congrats @jieyuzhao11 for delivering her first invited talk ;-)

Edgar Meij

@edgarmeij

4 years

As a reminder, we're tweeting about the KG-BIAS workshop (co-located with @akbc_conf ), specifically focusing on bias in the context of knowledge graphs. We're keeping live notes here: , and you can find more info at #KGBIAS

1

3

8

0

3

16

Kai-Wei Chang

@kaiwei_chang

3 years

This is awesome, @arjunsubgraph !

AllenNLP

@ai2_allennlp

3 years

We've added a new chapter to the guide, thanks to @arjunsubgraph , all about fairness metrics, bias metrics, and bias mitigation tools for your models. Learn how you can apply bias mitigation to large, contextual language models directly from a config file!

1

8

46

1

15

Kai-Wei Chang

@kaiwei_chang

4 years

@rctatman Thank you, Rachael for mentioning this. It is a tutorial in EMNLP 2019 w/ @vinodkpg @bluevincent @mmitchell_ai and slides can be found here

Tutorial: Bias and Fairness in Natural Language Processing

Instructors: [Kai-Wei Chang](http://kwchang.net), [Vicente Ordonez](http://vicenteordonez.com), [Margaret Mitchell](http://www.m-mitchell.com), [Vinodkumar Prabhakaran](https://www.cs.stanford.edu/...

web.cs.ucla.edu

0

5

15

Kai-Wei Chang

@kaiwei_chang

2 months

AI agent folks: can you build an automatic review chaser 😂 @ysu_nlp

1

14

Kai-Wei Chang

@kaiwei_chang

4 years

Also, see @bluevincent 's Genderless demo based on ICCV 19 paper on Gender Bias in Visual Recognition and tweet by @yatskar :

Balanced Datasets Are Not Enough: Estimating and Mitigating Gender...

In this work, we present a framework to measure and mitigate intrinsic biases with respect to protected variables --such as gender-- in visual recognition tasks. We show that trained models...

arxiv.org

0

2

14

Kai-Wei Chang

@kaiwei_chang

4 years

@AnimaAnandkumar @VioletNPeng @OpenAI This reminds me of "Model Cards for Model Reporting" by @timnitGebru @mmitchell_ai etal -- "released models should be accompanied by documentation detailing their performance characteristics"

1

3

13

Kai-Wei Chang

@kaiwei_chang

8 years

2 papers accepted by NIPS: credit assignment compiler for L2S , debiasing wordembedding

0

1

14