Yoav Artzi @yoavartzi Twitter profile

Last Seen Profiles

@asmalouzon

@BOKEPBOCILVIRA3

@helovesne_

@AllroundArsenal

@hasanozkay

@MatthewHornNH

@john_pius8

@glosserafim

@TheHongLab

@hissterious

@Phil_Kelly_

@Jeffnwest

@kobronlakeshow

@RTELateLateShow

@Newtype_Hero_

@REALRAVERANGERS

@ukpassportcheck

@ProperMag

@JawsTheJester

@RahamanKha82882

@YShiblog

@drunkhys

@KristySwansonXO

@davefontenot

@Landon_D_

@wokesocieties

@ducal_39

@KayleighMichael

@fizzymisery

@SnowdenIntBPS

@Jorginhorp

@TSGontweeter

@takiyyoo

@LeoKRogue

@takoyakiuenakk

@Regeneron

Yoav Artzi

@yoavartzi

6 years

NEWSROOM -- a corpus of 1.3M (1,321,995) article-summary pairs for automated summarization. It's big, it's diverse, and it's an open challenge. Oh, and we are pretty excited about it! Joint work with Max Grusky and @informor #NLProc #naacl2018

5

138

385

Yoav Artzi

@yoavartzi

4 years

New study of BERT fine-tuning from @asapptech : Revisiting Few-sample BERT Fine-tuning () with @Tianyi_Zh Felix Wu @katiyar_arzoo @kilianq A sample of the results in the thread.

7

57

306

Yoav Artzi

@yoavartzi

5 years

Just updated our recent paper on BERTScore, a super simple method for evaluating text generation with BERT, with many more experiments. We evaluated with the outputs of 363 MT systems and model selection experiments! --> 41 pages and 29 giant tables :)

2

74

286

Yoav Artzi

@yoavartzi

28 days

Folks, some @COLM_conf stats, because looking at these really brightens the mood :) We received a total of ⭐️1036⭐️ submissions (for the first ever COLM!!!!). What is even more exciting is the nice distribution of topics and keywords. Exciting times ahead! ❤️

4

33

255

Yoav Artzi

@yoavartzi

1 year

We are releasing KiloGram ⚖️, a large-scale resource of tangram images with language annotation, for everyone in #NLProc , CogSci, and many other fields to enjoy (and use)! Coming up in EMNLP -> 🧵 📄 Browse it:

6

44

217

Yoav Artzi

@yoavartzi

5 years

Happy to release Touchdown🧸, a natural language navigation and spatial reasoning dataset using Street View. The task: follow the instructions to reach a goal and find a hidden 🧸 named Touchdown. All the hard work by @howard50b @alsuhr and Dipendra Misra

2

58

193

Yoav Artzi

@yoavartzi

5 years

NLVR goes real! Check out NLVR² — complex reasoning with *natural* language and *real* vision. 107K examples, each caption and a pair of images. Task: predict if the caption is true. A long way to go to human performance of 96%!

3

64

174

Yoav Artzi

@yoavartzi

4 years

This has been 2 years and 3 papers in the making: direct mapping of natural language instructions and first-person observations to continuous velocity control. Yep, we learn the entire pipeline with a single interpretable neural model! #NLProc ❤️ #Robotics

2

30

173

Yoav Artzi

@yoavartzi

11 months

NEW PAPER: w/ @ggaonlp @hungting_chen @eunsolc , we build+deploy QA systems to improve from real human feedback. Over thousands of interactions,we show rapid improvements over time! Human users ask questions, get model-predicted answers, and give feedback🧵

2

33

160

Yoav Artzi

@yoavartzi

2 years

👩‍🎓➡👩‍🏫Congratulations Dr. Alane Suhr @alsuhr ! @cs_cornell @cornell_tech 🗽🌇🔜 @allen_ai 🏔🌋 🔜🔜 @Berkeley_EECS 🐻🌁 [too much on the emojis? 🤷‍♂️]

9

7

160

Yoav Artzi

@yoavartzi

7 years

Excited to release a new dataset for natural language visual reasoning by Alane Suhr, Mike Lewis, James Yeh #NLProc

1

74

147

Yoav Artzi

@yoavartzi

1 year

Users engaged with natural language systems can provide feedback in realtime, and this feedback is a super duper learning signal! So: deploy, train, repeat! Last PhD paper w/ @alsuhr /suhr @sigmoid .social ... 🧵

5

22

144

Yoav Artzi

@yoavartzi

2 years

Want to do ML/NLP for science?! @arxiv (that small website you visit 100 times a day) is hiring a Lead ML Engineer with focus on NLP! Super exciting data and incomparable impact. Please help distribute and pass around to anyone relevant 🙏

0

45

133

Yoav Artzi

@yoavartzi

10 months

Is it time to reconsider oral sessions @aclmeeting ? Or is it just me finding them less useful, and not attended compared to the lively ongoing poster session

10

6

131

Yoav Artzi

@yoavartzi

2 years

Can we improve a QA system from user feedback *in deployment*? We study how effective this signal is (tldr: very effective) using simulation experiments with existing benchmarks. @aclmeeting #ACL2022 work by Ge Gao collab with @eunsolc

3

21

128

Yoav Artzi

@yoavartzi

4 years

Congratulations to @alsuhr for the 2020 Facebook PhD fellowship! And congrats to @lena_voita for receiving one as well. Good year for #NLProc !

2

4

118

Yoav Artzi

@yoavartzi

3 years

We ( @alsuhr @claravania @meloncholist @MaartenSap @yatskar @sleepinyourhat ) have a crowdsourcing-case-studies tutorial at EMNLP. We have a teaser video! A long time ago, when AI wasn't just ML (😉 @srush_nlp ), people wrote annotation guidelines hundreds of pages long ... #NLProc

2

28

109

Yoav Artzi

@yoavartzi

7 months

Distributional semantics? Reminds me of the "florida" example in the @omerlevy_ and @yoavgo paper from 2014. Granted, contemporary LLMs probably do it much better, but the ability is likely not new

Wes Gurnee

@wesg52

7 months

For spatial representations, we run Llama-2 models on the names of tens of thousands cities, structures, and natural landmarks around the world, the USA, and NYC. We then train linear probes on the last token activations to predict the real latitude and longitudes of each place.

13

38

547

5

14

99

Yoav Artzi

@yoavartzi

1 year

Turing awards for everyone!!! @yoavgo @percyliang @alsuhr @YejinChoinka (who got some bonus awards on the way).... presupposition is a wonderful thing! Do you want a Turing Award? Go to , give yourself one, and send a screenshot to your proud parents 🏆

8

4

95

Yoav Artzi

@yoavartzi

5 years

Many thanks to @GoogleAI and especially to @jasonbaldridge , @dipanjand , and @earnmyturns for their amazing support!

Cornell Computer Science

@Cornell_CS

5 years

Yoav Artzi ( @yoavartzi ), Assistant Professor in the Department of Computer Science and Cornell Tech, has received a Google Focused Research Award to fund exploration of spatial language understanding. He will share the $1.5m award evenly with @mohitban47 .

1

2

34

5

92

Yoav Artzi

@yoavartzi

1 year

Completely agree. This counter culture (sorry, had to pun -- lame, I know) has been going on for a few years, and it's not only annoying, but misleading about what makes progress, both on the personal level and globally on research. If anything, slow down!

1

6

92

Yoav Artzi

@yoavartzi

2 years

Looking for a language+vision ambiguity example for your #NLProc class? (credit to @alsuhr for the find)

1

6

92

Yoav Artzi

@yoavartzi

2 years

Come do your PhD at Cornell. There's free food. See figure below.

Cornell Bowers Computing and Information Science

@CornellCIS

2 years

Interesting Engineering ( @IntEngineering ) features @cs_cornell prof Tapomayukh Bhattacharjee's lab in which robots — including, newly-devised robotic arms — could become crucial caregivers in the near future. @TapoBhat #CornellCIS

0

1

6

5

7

91

Yoav Artzi

@yoavartzi

5 years

Upcoming in EMNLP: Executing Instructions in Situated Collaborative Interactions (). New language collaboration environment and large dataset, modeling and learning methods, and a new evaluation protocol for sequential instructions.

1

15

90

Yoav Artzi

@yoavartzi

6 years

Want a good-ol'-fashioned hard copy of the NEWSROOM summarization dataset ()? Find Max Grusky at #NAACL2018 and get 1.3M article-summary pairs on a bespoke flash drive, limited supplies! -- TALK ON SUNDAY, 11:06 in Empire B #NLProc

6

19

90

Yoav Artzi

@yoavartzi

3 years

We keep updating BERTScore, our generation evaluation method, behind the scenes. Been a while so highlights: - Now supports 53 pre-trained models via @huggingface 's Transformers - WMT-16 to-EN correlations here: --> current best: deberta-xlarge-mnli

BERTScore Default Layer Performance on WMT16

en Model,Best Layer,WMT16 To-English Pearson Correlation,Rank,Max Length bert-base-uncased,9,0.6925,51,510 bert-large-uncased,18,0.7210,28,510 bert-base-cased-finetuned-mrpc,9,0.6722,74,510 bert-ba...

docs.google.com

4

16

79

Yoav Artzi

@yoavartzi

1 year

This is absurd. Beyond credit, authorship is responsibility and liability. OpenAI assumes neither, and it is nonsensical to attribute either to ChatGPT or expect it to assume it (whatever that would even mean! 🤯). This practice is actively misleading the public about LLMs.

Delip Rao e/σ

@deliprao

1 year

This is probably the first paper to give ChatGPT coauthor status, and its contact details points to support @openai ! Giving coauthorship to writing assistants is absurd and this practice has to stop. 🧶

19

35

314

5

4

79

Yoav Artzi

@yoavartzi

1 year

An important aspect of LLM deployment not featured much in current discourse. I wrote a one-pager about this about a month ago for an ISAT workshop. Took the opportunity to edit it a bit: [very speculative, I will probably regret posting it 😬]

Peter Nixey

@peternixey

1 year

I'm in the top 2% of users on StackOverflow. My content there has been viewed by over 1.7M people. And it's unlikely I'll ever write anything there again. Which may be a much bigger problem than it seems. Because it may be the canary in the mine of our collective knowledge. A…

568

2K

12K

7

10

78

Yoav Artzi

@yoavartzi

1 year

Super proud of Anya and the team for the @emnlpmeeting best paper, and very appreciative of the hard work of EMNLP and the committee. Maybe it's opportunity to raise something: best paper awards are fun, but should be replaced with larger pool of outstanding awards [🧵1/3]

1

8

73

Yoav Artzi

@yoavartzi

3 years

Really nice to see consistent progress on a hard semantic parsing task 😍 -- NLVR -- with solid algorithm improvements! Most recent, work @nitish_gup @sameer_ @nlpmattg gets 89.5% accuracy, almost to 90% on structured rep. That's from 67.8% when we released the data in 2017 👏

2

3

73

Yoav Artzi

@yoavartzi

10 months

+1 Interest in human language is what drives much of my work. No community compares. This all makes me very sad. NLP faces two pressures: one from industry LLMs, the other wholly self inflicted. Not clear ACL 'll survive as an impactful force if it doesn't get its act together

Zachary Lipton

@zacharylipton

10 months

To be clear, I love the NLP community. I admire the faculty, it’s a joy to teach the students, the vibe is thoughtful & warm. But *CL faces existential threats & has adopted all the wrong remedies. The house is on fire and we’re furiously installing a labyrinthine koi pond.

4

13

127

4

7

72

Yoav Artzi

@yoavartzi

1 year

My feed is now dead for the next week or so .... let's sing along🍌GPT4🕺GPT4🚀GPT4💥GPT4🐘GPT4🤘GPT4🤸‍♂️GPT4🤳GPT4📸GPT4🖼️GPT4🍕GPT4🤖GPT4🦾🧘‍♀️🧘‍♀️🧘‍♀️🧘‍♀️🧘‍♀️

2

6

71

Yoav Artzi

@yoavartzi

1 year

Came to my office this morning to find this. @alsuhr , made my week! And, I appreciate the gentle jab at my frequent typos 😂

3

2

68

Yoav Artzi

@yoavartzi

1 year

Humans learn language by acting in the world. Can RL agents do the same? lilGym is a new benchmark 🏋️ for RL + natural language + visual reasoning Chief RL trainer: @anne_youw , in collboration with @noriyuki_kojima and @xkianteb

4

8

68

Yoav Artzi

@yoavartzi

7 months

Answering two quick questions I received: 1. Yes, it will be an in-person conference! 2. The CfP details what is behind the non-exhaustive list of topics of interest -- read how we break out each term! We are taking a VERY VERY broad view of language modeling an its uses

Sasha Rush

@srush_nlp

7 months

Introducing COLM () the Conference on Language Modeling. A new research venue dedicated to the theory, practice, and applications of language models. Submissions: March 15 (it's pronounced "collum" 🕊️)

34

437

2K

4

10

67

Yoav Artzi

@yoavartzi

1 year

A cool approach for speeding up RL (basically via helping w/exploration): (by @hllo_wrld @jayelmnop @LukeZettlemoyer @egrefen @_rockt ) Took me a bit to get my head around it, but the idea is very simple and elegant ....

Improving Policy Learning via Language Dynamics Distillation

Recent work has shown that augmenting environments with language descriptions improves policy learning. However, for environments with complex language abstractions, learning how to ground...

arxiv.org

2

11

63

Yoav Artzi

@yoavartzi

2 months

Turns out that @alsuhr 's good ol' fashioned (2017!) NLVR remains pretty challenging for SOTA multimodal LLMs ¯\_(ツ)_/¯ New technical report by @anne_youw Particularly striking given the tiny vocabulary size and the simple synthetic images. Why? Not completely sure, but ...

Charlie Snell

@sea_snell

2 months

Does anyone have a favorite task where gpt-4 has near chance accuracy when zero or few-shot prompted? I’m looking for recommendations for tasks like this

40

15

194

3

15

60

Yoav Artzi

@yoavartzi

1 year

Media coverage is absurd, serving interests of companies, where appearance of magic and intelligence translates into dollars. Capitulation of top-notch journalists is embarrassing and sad. (+ Sundar's response to the key question is ridiculous - we don't understand humans ... 🙄)

60 Minutes

@60Minutes

1 year

One AI program spoke in a foreign language it was never trained to know. This mysterious behavior, called emergent properties, has been happening – where AI unexpectedly teaches itself a new skill.

434

743

2K

2

4

60

Yoav Artzi

@yoavartzi

7 years

Raw pixels+instructions --> actions, end-to-end NLU learning with RL - poster now! Run our code #NLProc #emnlp2017

0

25

57

Yoav Artzi

@yoavartzi

2 years

GPT has spoken

6

2

59

Yoav Artzi

@yoavartzi

5 years

I am looking for a postdoc to join my group at Cornell in the Cornell Tech NYC campus. Details in thread. Contact me for details (). Please RT #NLProc

1

39

59

Yoav Artzi

@yoavartzi

1 month

. @cornell_tech PhD students, every year ;)

Mark Dredze

@mdredze

1 month

Stumpy inspired meme. Credit to my PhD students for the idea.

0

2

55

1

57

Yoav Artzi

@yoavartzi

2 months

And... I forgot the link 🤦‍♂️

Yoav Artzi

@yoavartzi

2 months

Turns out that @alsuhr 's good ol' fashioned (2017!) NLVR remains pretty challenging for SOTA multimodal LLMs ¯\_(ツ)_/¯ New technical report by @anne_youw Particularly striking given the tiny vocabulary size and the simple synthetic images. Why? Not completely sure, but ...

3

15

60

4

6

56

Yoav Artzi

@yoavartzi

2 years

Probably the best discussion of image generation so far. Starting strong with phrasal attachment ambiguity, and then diving into compositional semantics, including affordances and selectional preferences. There is a whole #NLProc lecture there

AI Images: Last Week Tonight with John Oliver (HBO)

John Oliver discusses the new trend of AI-generated images based on text prompts, and, of course, what it all has to do with cabbage.Connect with Last Week T...

www.youtube.com

0

8

56

Yoav Artzi

@yoavartzi

4 years

Happy we got the Language Grounding 🤖🖼🚀 track going in @aclmeeting this year! And glad to have SAC-ed its inaugural round :) despite slightly lower acceptance rate, Grounding is bigger than Syntax 🌲 --- how do times change! #NLProc

ACL2020: General Conference Statistics

Official website for the 2020 Annual Conference of the Association for Computational Linguistics

acl2020.org

1

8

55

Yoav Artzi

@yoavartzi

4 years

Hey, attending @iclr_conf ? The BERTScore presentation is online: While listening, install BERTScore! Just “pip install bert-score” or git the source: We will be around to chat on Tuesday (5-7pm, 8-10pm GMT / 1-3pm, 4-6pm EDT)

GitHub - Tiiiger/bert_score: BERT score for text generation

BERT score for text generation. Contribute to Tiiiger/bert_score development by creating an account on GitHub.

github.com

Yoav Artzi

@yoavartzi

5 years

Just updated our recent paper on BERTScore, a super simple method for evaluating text generation with BERT, with many more experiments. We evaluated with the outputs of 363 MT systems and model selection experiments! --> 41 pages and 29 giant tables :)

2

74

286

0

10

55

Yoav Artzi

@yoavartzi

1 year

Joint us for InterNLP 2022 @NeurIPSConf on Dec 3 for our workshop on interactive learning for #NLProc . We have a fantastic set of speakers and submissions! Schedule is here:

1

15

53

Yoav Artzi

@yoavartzi

6 years

Cornell NLVR () is now available in ParlAI #NLProc

0

16

51

Yoav Artzi

@yoavartzi

2 years

The videos for our crowdsourcing @emnlpmeeting tutorial are online via the link in Underline! () We will use the live slot in EMNLP for a 👩‍⚕️Crowdsourcing Clinic💉 (a what?! 👉🧵+video👇), so please watch the case studies in advance

EMNLP 2021 Crowdsourcing Tutorial / Intro [1/8]

EMNLP 2021 TutorialCrowdsourcing Beyond Annotation: Case Studies in Benchmark Data CollectionIntroductionWebsite: https://nlp-crowdsourcing.github.io/Slides:...

www.youtube.com

1

16

52

Yoav Artzi

@yoavartzi

2 years

A new anecdote for the "language is ambiguous" slides of intro to intro to NLP

Kristen

@kristenstockdal

2 years

An interesting development in the Kim <> Kanye saga

718

40K

448K

1

7

52

Yoav Artzi

@yoavartzi

7 years

Outstanding papers session @acl2017 - Cornell NLVR corpus -- also w/structured rep for semantic parsing #nlproc

0

6

49

Yoav Artzi

@yoavartzi

2 months

Finally got around to list @COLM_conf 's 140(!) area chairs on the website! Thanks everyone for your support and help!

1

4

51

Yoav Artzi

@yoavartzi

8 months

This is not only the well-intended, but border-line suicidal arXiv policy. It's also Findings, ARR, checklists, and other onerous submission requirements. We don't need to be creative. We need simplicity. Reset the system!

Yoav Artzi

@yoavartzi

8 months

@adveisner @zacharylipton We really need to stop trying to answer our problems with increased complexity. It's nearly impossible to predict impact over time and at scale. Again and again, and with the best intentions, we have my made our life harder, and undermined ACL

2

4

42

3

4

50

Yoav Artzi

@yoavartzi

1 year

NLP folks, I am thinking of doing paper reproduction projects for grad-level adv. topics class. What are good papers to look at? Paper must be well written, data available, compute is limited 😅, complexity bounded -> 1 semester (students have other [important] obligations).

11

3

50

Yoav Artzi

@yoavartzi

2 years

What GPUs one buys nowadays for an academic lab doing #NLProc , computer vision, RL, etc?

10

5

50

Yoav Artzi

@yoavartzi

9 months

What multi-modal LLMs are currently publicly available? Specifically, models that take as input in the prompt an arbitrary number of images, potentially interleaved within the prompt text. Image generation aside (for this query). I guess Flamingo is one relevant design. Thanks!

8

4

47

Yoav Artzi

@yoavartzi

5 years

Two updates on NLVR2 (). First, we analyzed a potential visual bias, enhanced the evaluation protocol to be robust to it, and confirmed the results of recent work do not take advantage of this potential bias. #NLProc

1

11

48

Yoav Artzi

@yoavartzi

9 months

@dmimno When did LLM use took off? Isn't pre April 22 a bit early? So there's a drop there, but later might be LLMs

2

0

47

Yoav Artzi

@yoavartzi

11 days

We created reviewing guidelines for @COLM_conf . Not intended to automate the committee work, or dictate constraints. But, to inspire a thoughtful reviewing process, for an exciting and impactful program of the highest possible quality. We have a wonderful program committee ❤️

1

11

55

Yoav Artzi

@yoavartzi

1 year

We are recruiting PhD research interns @asapp for the coming summer! Working on challenging ML/NLP problems, with amazing data, and SOTA models. Apply here: (also: hiring for full-time research positions, both scientists and engineers!)

1

17

48

Yoav Artzi

@yoavartzi

1 year

Absolutely no. This is wrong, and maybe based on a misunderstanding of what (academic) research is about. Probably should engage more meaningfully, but 🤷‍♂️

Jingfeng Yang

@JingfengY

1 year

As a NLP researcher doing semantic parsing for nearly 5 years, I have to say semantic parsing and grounding are probably also dead. FYI, semantic parsing is to transform natural language to formal language (code, self-defined functions etc.) and execute it in the real world.

19

80

734

3

47

Yoav Artzi

@yoavartzi

4 years

Between the theory-heavy RL course of Wen Sun () and Sasha’s applied-heavy course, I am seriously considering just going back to school

Sasha Rush

@srush_nlp

4 years

MiniTorch v0.1 (DIY build-your-own Torch) New modules on python GPU programming, pooling and CNNs, and lots of community fixes. (DM me if you are would like access to the teacher's guide with code.)

3

89

335

0

8

47

Yoav Artzi

@yoavartzi

2 years

It makes no sense that "ridge plots" are not called "little prince plots" or "boa plots" (right: boa plots from upcoming work with @hawkrobe -- see the elephants!)

4

2

47

Yoav Artzi

@yoavartzi

4 years

The slides are available here: PDF: HTML w/videos: (also with a lot of supplementary slides)

Stanford NLP Group

@stanfordnlp

4 years

It was great to have @yoavartzi with us today telling us about his really exciting new work on grounded semantics: Robot Control and Collaboration in Situated Instruction Following – even despite the Dec 9 @aclmeeting deadline. #NLProc

0

4

23

0

10

45

Yoav Artzi

@yoavartzi

2 months

Folks, 15 day to the @COLM_conf abstract submission deadline on March 22! Real llamas don't pull all nighters (too often), but their GPUs do!

European Conference on Computer Vision #ECCV2024

@eccvconf

2 months

Congrats to all the students who just submitted their papers to #ECCV2024 !

2

16

134

3

4

45

Yoav Artzi

@yoavartzi

4 years

Seems like so far in the future, but I will be looking to recruit 1-2 PhDs next year, including with special focus on hard core robotics-oriented students for robotics+NLP 🗣🤖 (but not only!)

Benno Krojer

@benno_krojer

4 years

Considering a PhD in NLP and more specifically Grounded Language. So I thought it might a good time to try out Twitter's list feature to stay up-to-date with people like @_jessethomason_ @yoavartzi @FelixHill84 ... Also added some other NLP people for fun.

3

6

33

1

7

45

Yoav Artzi

@yoavartzi

19 days

The @COLM_conf reviewing period has started. Reviewers should now receive emails, and all papers are now assigned. Thanks to all our ACs who adjusted assignments in the last few days. Happy reviewing all!

1

7

45

Yoav Artzi

@yoavartzi

2 months

Hey! @COLM_conf is recruiting reviewers! ███████░░░ 70% recruited 🚀🚀🚀 Did you get an invite? Please respond NOW! Didn't get an invite and want to help? ❤️ please fill this form:

1

16

43

Yoav Artzi

@yoavartzi

4 years

. @emnlp2020 CFP seems to be up, deadline May 8:

0

16

42

Yoav Artzi

@yoavartzi

10 months

@yoavgo We will make everything so costly and inefficient to the point that everything is possible and valid :) Seriously though, it's a cool and interesting idea. Nice to see it in an NLP paper

1

0

42

Yoav Artzi

@yoavartzi

10 months

The forcing of ARR next year is dispiriting. The issues go beyond getting the engineering right, and @chrmanning succinctly summarized during the ARR session …

2

6

43

Yoav Artzi

@yoavartzi

4 years

A lot of @cs_cornell -related movements in the #NLProc faculty market this here. Worth summarizing in one place. Need to update our people page .... Pretty excited about the numbers, especially given that our groups are relatively small :) thread 1/8

Cornell NLP

Natural Language Processing at Cornell

nlp.cornell.edu

2

6

42

Yoav Artzi

@yoavartzi

8 months

@adveisner @zacharylipton We really need to stop trying to answer our problems with increased complexity. It's nearly impossible to predict impact over time and at scale. Again and again, and with the best intentions, we have my made our life harder, and undermined ACL

2

4

42

Yoav Artzi

@yoavartzi

7 months

Took a bit long, but to appear @NeurIPSConf as spotlight 🔦

Yoav Artzi

@yoavartzi

1 year

Users engaged with natural language systems can provide feedback in realtime, and this feedback is a super duper learning signal! So: deploy, train, repeat! Last PhD paper w/ @alsuhr /suhr @sigmoid .social ... 🧵

5

22

144

0

6

42

Yoav Artzi

@yoavartzi

1 year

Research as API usage is problematic. Reproducibility is one issue, but not the biggest one. More critical is opaqueness about what is actually behind the API, and bounding the level of insight because of the restricted access (eg: no distributions, no activations)

Wenhu Chen

@WenhuChen

1 year

OPENAI announced the discontinuation of the Codex API from March 23rd. Then a large set of Codex-based code generation papers are becoming totally irreproducible. 🥲🥲

5

4

60

1

5

40

Yoav Artzi

@yoavartzi

4 years

@srush_nlp These popularity contest lists are largely flawed from the get go. It’s not doing good to our field, or to the students now joining it. I am really happy I didn’t ”grow up” (arguably, still growing up, but you get the point) in this climate

1

2

41

Yoav Artzi

@yoavartzi

8 years

A new data release from the @nytimes

Our Tagged Ingredients Data is Now on GitHub

We’re excited to release the roughly 180,000 labeled ingredient phrases that we used to train the machine learning model we referred to in “Extracting Structured Data From Recipes Using Conditional...

archive.nytimes.com

0

18

40

Yoav Artzi

@yoavartzi

8 months

ACL is supposed to be my intellectual home. Not sure ML venues can really replace that. It's sad beyond the collapse of an important pub venue. And that was before the unfortunate dragging of arXiv (❤️) into the mud most recently 😢

Tim Rocktäschel

@_rockt

8 months

@PMinervini @nsaphra @aryopg Yeah, I've mostly stopped submitting NLP work to NLP conferences.

1

6

29

0

2

39

Yoav Artzi

@yoavartzi

2 months

Happy pi day from @COLM_conf ! This little llama is preparing for the abstract deadline in 8 days 😳

0

4

39

Yoav Artzi

@yoavartzi

2 years

This is how you show Likert scores! ❤️ Not means .... :)

Tanya Goyal

@tanyaagoyal

2 years

We collect human preference annotations for news summaries generated by current SOTA and zero-shot GPT-3 models. For multiple settings (generic + keyword) and datasets (CNN + BBC), GPT-3 summaries beat prior fine-tuned models! [2/6]

1

0

33

3

1

38

Yoav Artzi

@yoavartzi

3 months

We put together a list of papers (that is NOT exhaustive of the styles COLM is looking for -- that thread would be truly endless), and @srush_nlp made a looong thread out of it. Looking forward to seeing your submission at COLM!

Sasha Rush

@srush_nlp

3 months

The Conference on Language Modeling 🦙 () has the mission of "creating a community of researchers with expertise in different disciplines, focused on understanding, improving, and critiquing the development of LM technology." 🧵 Here are 17 papers from 17…

5

152

703

0

4

38

Yoav Artzi

@yoavartzi

3 years

New NLP+robotics+vision paper: Few-shot Object Grounding and Mapping for Natural Language Robot Instruction Following @ CoRL 2020 Work done by Valts Blukis Three core contributions make this happen, let’s upack them ...

1

11

38

Yoav Artzi

@yoavartzi

11 months

Congratulations to @alsuhr for an ACM dissertation award honorable mention! 👏👏👏

Association for Computing Machinery

@TheOfficialACM

11 months

“Reasoning and Learning in Interactive Natural Language Systems” by @alsuhr : #ACMAwards #computing #research

1

6

1

3

37

Yoav Artzi

@yoavartzi

4 years

Including our GIANT Newsroom summarization dataset

Thomas Wolf

@Thom_Wolf

4 years

Surviving every AI wave, two kernels have consistently been the beating hearts of Natural Language Processing: Datasets and Metrics Today we release "nlp", a library to easily share & load data/metrics already providing access to 99+ datasets! Try it👉

17

408

2K

0

4

37

Yoav Artzi

@yoavartzi

9 months

The UK is a wonderful source for NLP class examples :)

Satan

@s8n

9 months

you plan to WHAT

1K

11K

152K

3

0

36

Yoav Artzi

@yoavartzi

4 years

Now including BERTScore: Thanks to the super fast Felix Wu ()

Felix Wu's Homepage

Bio Felix Wu is a Research Scientist at ASAPP. He received his Ph.D. in Computer Science from Cornell University under the supervision of Prof. Kilian Q. Weinberger and his B.S. in Computer Science...

sites.google.com

Thomas Wolf

@Thom_Wolf

4 years

Surviving every AI wave, two kernels have consistently been the beating hearts of Natural Language Processing: Datasets and Metrics Today we release "nlp", a library to easily share & load data/metrics already providing access to 99+ datasets! Try it👉

17

408

2K

1

5

36

Yoav Artzi

@yoavartzi

5 years

. @NAACLHLT attendees (and these just watching from afar), I am looking for a postdoc next year. Position will be at the @cornell_tech campus in NYC. Happy to chat at NAACL (or later on at @ACL2019_Italy ) -- please DM/email to find a time, and spread the word

0

15

35

Yoav Artzi

@yoavartzi

3 years

New paper: can observational behavioral signal facilitate continual instruction generation learning? Yes! Observe what people do -> they don't do what you want? -> maybe you said it wrong by @noriyuki_kojima in collaboration w/ @alsuhr and myself. 🧵...

Continual Learning for Grounded Instruction Generation by...

We study continual learning for natural language instruction generation, by observing human users' instruction execution. We focus on a collaborative scenario, where the system both acts and...

arxiv.org

2

9

36

Yoav Artzi

@yoavartzi

5 years

Happy to release the Dynamic Robot Instruction Following (DRIF) framework, including a 3D simulator and data for natural language instruction to a realistic quadcopter drone Video for our recent #CoRL paper using DRIF:

Quadcopter Following Navigation Instructions

Demo video for the paper:Mapping Navigation Instructions to Continuous Control Actions with Position-Visitation Prediction.

www.youtube.com

1

11

34

Yoav Artzi

@yoavartzi

1 year

Great to see what everyone around here have been noticing going through a good-old-fashioned empirical test 👏 LLMs are a wonderful artifact, and will be super useful, but search is such a bad choice for current models!

1

4

35

Yoav Artzi

@yoavartzi

3 months

We have a venue! This is the informal view of things ... COLM is serious, so the official account would never do some thing like this ;)

Conference on Language Modeling

@COLM_conf

3 months

We are pleased to announce that the first Conference on Language Modeling will be held at the University of Pennsylvania in Philadelphia at the Zellerbach Theatre. Thanks so much to UPenn CS as well as Mark Yatskar and Zachary Ives for facilitating the amazing venue.

2

44

254

1

35

Yoav Artzi

@yoavartzi

17 days

Not the one who told Noam this, but I don't filter based on paper counts. I find publication record to often be more of a distraction than a helpful signal ¯\_(ツ)_/¯

Noam Brown

@polynoamial

18 days

Someone on the admissions committee for a top CS PhD program told me they no longer filter based on paper count because too many of the applicants already have multiple publications. Instead, they now filter by citation count. Not sure if he was joking but I believed it.

10

19

234

3

2

34

Yoav Artzi

@yoavartzi

5 months

Some big expansion in schools that were maybe less on the NLP map, such as Waterloo and UChicago (following a giant expansion in recent years by USC). Applicants should update their lists...

Kai-Wei Chang

@kaiwei_chang

5 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

0

1

34

Yoav Artzi

@yoavartzi

3 years

For the current fleeting moment, Valts' work tops the ALFRED leaderboard, *but* with a cool twist: only using the high level instructions! Completely without the low level ones. More details soon. Work by Valts Blukis, @chris_j_paxton , @animesh_garg Dieter Fox and myself.

2

34

Yoav Artzi

@yoavartzi

4 months

and cs.LG submission stats on @arxiv , from 2009 (incidentally, when I started my PhD) to 2023 (just went up) 🤯 🚀🚀🚀🚀

1

4

34

Yoav Artzi

@yoavartzi

2 months

NLP folks, I am looking for a textual similarity dataset where given 2 sentences (with maybe different words), we have word-level similarity judgements between them (not necessarily for all pairs). Is there something like this?

9

4

33

Yoav Artzi

@yoavartzi

7 months

Excited to start COLM! If you are interested (of course you are!), please check out our survey: We are looking to gauge interest and recruit program committee.

Sasha Rush

@srush_nlp

7 months

Introducing COLM () the Conference on Language Modeling. A new research venue dedicated to the theory, practice, and applications of language models. Submissions: March 15 (it's pronounced "collum" 🕊️)

34

437

2K

0

4

33

Yoav Artzi

@yoavartzi

10 months

Will be in #ACL2023NLP Mon-Fri. Looking forward to catchup and discuss research. So much going on, all over the place, and all at once... not even sure what I am interested in any more. Well, natural language is a big one :)

0

32

Yoav Artzi

@yoavartzi

2 years

So Cornell NLP and MacArthur a thing? Regina was a postdoc here, @YejinChoinka a PhD. Just saying 😉

Cornell Computer Science

@Cornell_CS

2 years

Congratulations to Yejin Choi ( @YejinChoinka )! The 2010 @Cornell alumna and pioneer in the field of natural language processing has been awarded a 2022 MacArthur Fellowship, or “genius grant.” Read more:

1

6

67

0

2

33

Yoav Artzi

@yoavartzi

2 years

. @cs_cornell is (heavily) hiring faculty across dimensions ⟀ (areas, and locations: Ithaca and NYC!), including #NLProc . Self-filtering is often suspect, so just apply! Feel free to DM with Qs (answers will often be: yes, apply!)

1

9

32