Vered Shwartz @VeredShwartz Twitter profile

Last Seen Profiles

@Rayofsunfull

@Viva_El_Futbool

@teamminuszero

@zoegail2

@feiche35078990

@MAA_LAISE

@oldwac1

@UnSrGeek

@relxenum

@al3ssixo

@guirenguiyu

@rachelkcraig

@bkerogers

@nguoidocsach84

@carmilanesas

@FloodCapital

@forthpcsp

@oname_kunikuni

@shuuquatt

@CogarEddie66881

@onchi555

@wshSmash

@coachamoshurdle

@olympijskytym

@goromajimas_

@ird_fr

@GluePodcast

@RichardGrahamUK

@mubasherlucman

@OGPumps

@FwVo8i5LwPnxrH3

@OverSpeed_Wiki

@Kunluntalk

@andrewfarmer150

@ruiphotoz

@llloup_

Vered Shwartz

@VeredShwartz

3 years

I'm thrilled to announce that this fall I will be joining the University of British Columbia CS department @UBC_CS as an Assistant Professor!

139

20

1K

Vered Shwartz

@VeredShwartz

1 year

My landlord and I are exchanging ChatGPT-generated emails negotiating the rent increase. I wish we could just let ChatGPT negotiate with itself and report the decision to us.

48

59

1K

Vered Shwartz

@VeredShwartz

11 months

I just published Tips for Writing NLP Papers I wrote it for my students so I don't have to sound like a broken record (and edit papers for the same issues over and over again 😃). But some of you might find it useful too.

Tips for Writing NLP Papers

Over the years I’ve developed a certain standard for writing papers (and doing research in general) that I share verbally with my students…

link.medium.com

28

238

1K

Vered Shwartz

@VeredShwartz

4 years

I just published Highlights of ACL 2020 #acl2020nlp

Highlights of ACL 2020

With ACL becoming virtual this year, I unfortunately spent less time networking and catching up with colleagues, but as a silver lining I…

link.medium.com

9

170

555

Vered Shwartz

@VeredShwartz

3 years

Last 2 days on Twitter: work 90hr weeks! See on who published the highest number of first-authored papers! Dear junior NLPers, please ignore this nonsense. Choose quality over quantity and have something other than work in your lives.

7

36

492

Vered Shwartz

@VeredShwartz

3 years

Shout out to the guy who came to yoga class, fell asleep in the first pose, and slept through the entire 1 hour class.

16

6

425

Vered Shwartz

@VeredShwartz

5 years

If you run "pkill -f bert" and you were training one model with BERT and one with RoBERTa, then you kill two berts with one stone.

8

41

389

Vered Shwartz

@VeredShwartz

1 year

The slides for my talk "Everything you wanted to know about ChatGPT (Except for what OpenAI doesn't tell us)" are available here: . I used it for both a guest lecture in an applied ML class and for a talk for non-CS audience.

ChatGPT.pdf

drive.google.com

Vered Shwartz

@VeredShwartz

1 year

I finally prepared a comprehensive slide deck about LLMs for people outside the field, so I kindly request everyone to stop releasing tools and papers so that it stays up to date. No GPT-5 please 😁

13

9

231

11

58

366

Vered Shwartz

@VeredShwartz

2 years

😂

9

8

258

Vered Shwartz

@VeredShwartz

6 years

I just published A potential approach to address the explosion of NLP paper submissions

A potential approach to address the explosion of NLP paper submissions

The number of paper submissions to *CL conferences is constantly growing. It is overwhelmingly difficult to keep up with current…

medium.com

7

61

244

Vered Shwartz

@VeredShwartz

1 year

Hinton's talk at #ACL2023NLP has many good points, but it bothers me that he criticizes researchers that say LLMs don't understand language as being non scientific, while he himself sees every anecdote as a proof that LLMs understand language. Science needs more nuance.

8

19

260

Vered Shwartz

@VeredShwartz

3 years

Sometimes I'm really impressed with the progress of NLP. Other times it's 37°c and a search for a cooling device on Amazon returns heaters.

2

4

247

Vered Shwartz

@VeredShwartz

3 years

Pumpkin carving with (part of) the UBC NLP group! I carved what scares me the most these days 😃

5

7

253

Vered Shwartz

@VeredShwartz

3 years

You know what's worse than packing? Adversarial packing. I'm packing and my husband takes things out of the garbage and recycling bins and asks "why are you throwing it away?".

5

3

230

Vered Shwartz

@VeredShwartz

1 year

I finally prepared a comprehensive slide deck about LLMs for people outside the field, so I kindly request everyone to stop releasing tools and papers so that it stays up to date. No GPT-5 please 😁

13

9

231

Vered Shwartz

@VeredShwartz

4 years

A long-overdue blog post about commonsense reasoning for NLP (based on our ACL 2020 tutorial):

4

68

215

Vered Shwartz

@VeredShwartz

5 years

On my way to the US, going to #naacl2019 and then joining @allen_ai and @uwnlp for a postdoc, where I'll be working with the awesome @YejinChoinka . Exciting times!

20

2

219

Vered Shwartz

@VeredShwartz

4 years

My co-authors and I had 4 papers accepted at #emnlp2020 , and 2 papers accepted at Findings :) Here are some of them (others will be added later):

10

9

219

Vered Shwartz

@VeredShwartz

7 years

In a scholarship ceremony. Everyone else: I study alzheimer and molecules. Me: I teach computers that cat is an animal.

4

34

192

Vered Shwartz

@VeredShwartz

1 year

A reminder for everyone to: sed -i -e 's/utilize/use/g' -e 's/novel//g' -e 's/distinct//g' your_emnlp_submission.tex

10

16

213

Vered Shwartz

@VeredShwartz

6 years

After 3 years of blogging about NLP, with the goal of writing in simple words that non-experts can understand, I finally dared to write about deep learning... it ended up a very long post :)

7

54

192

Vered Shwartz

@VeredShwartz

4 years

New pre-print targeting commonsense QA tasks. We propose an unsupervised framework with one LM as an answer scorer and another as a knowledge source. This is what happens when you don't panic and shut down your models when they talk with each other 😉

2

43

195

Vered Shwartz

@VeredShwartz

3 years

Implicit bias in the wild: an immigration officer upon seeing foreign names on the work permit applications incorrectly assumed my husband was the professor and I the spouse. When my husband mentioned losing his US driver's license, he asked "so who drove here?".

5

2

187

Vered Shwartz

@VeredShwartz

5 years

How well do contextualized word embeddings address lexical composition? They are good in recognizing meaning shift ("give in" is different from "give") but much worse with revealing implicit meaning ("hot tea" is about temperature, "hot debate" isn't).

3

38

174

Vered Shwartz

@VeredShwartz

4 years

I watched back to the future again and I couldn't help but think of this.

4

6

160

Vered Shwartz

@VeredShwartz

4 years

Reviewing a paper with too many equations and Greek letters. Arrest this man, he talks in maths.

10

3

154

Vered Shwartz

@VeredShwartz

6 years

De Morgan is rolling in his grave.

1

26

142

Vered Shwartz

@VeredShwartz

4 years

#acl2020nlp the conference is virtual, but the fatigue is real.

0

3

145

Vered Shwartz

@VeredShwartz

6 years

Are GANs better than LMs in text generation? @GuyTvt and @HabibGavriel provide a simple way to approximate GANs to LMs which allows evaluating them using standard metrics like perplexity & BPC. It turns out GANs perform worse! (work with @JonathanBerant )

Evaluating Text GANs as Language Models

Generative Adversarial Networks (GANs) are a promising approach for text generation that, unlike traditional language models (LM), does not suffer from the problem of ``exposure bias''. However, A...

arxiv.org

2

31

142

Vered Shwartz

@VeredShwartz

2 years

Air Canada sending an apologetic email because my flight will arrive at its destination 10 minutes *earlier* is the most Canadian thing ever.

5

136

Vered Shwartz

@VeredShwartz

4 years

lazyweb: I'm looking for examples of using current NLP tools in real-world applications successfully (e.g. NMT, or Google using BERT for search) or, even more interesting, unsuccessfully (either "bag of words worked better" or "the model was deployed and caused damage" stories).

30

17

135

Vered Shwartz

@VeredShwartz

3 years

Who coined the term "causal language model"? I've seen it used to describe left-to-right (as opposed to masked) language models, but I think it's misleading given that these models were not trained for (and do not excel at) modeling causes & effects.

15

5

137

Vered Shwartz

@VeredShwartz

5 years

What is the difference between a "death" and a "birth"? A "death" is a "death of the body." A birth is a "birth of the soul." - GPT-2, 2019

5

10

131

Vered Shwartz

@VeredShwartz

6 years

I gave a lot of talks in the last 3 weeks, but today was the most challenging one. I gave two 30 min talks about intro to NLP to two groups of 7th graders. I'm hope to meet some of them again at ACL 2028 😀

2

126

Vered Shwartz

@VeredShwartz

5 years

TFW you're moving and you realize you have bizarre collections.

9

0

129

Vered Shwartz

@VeredShwartz

5 years

I'm happy to update that this paper was accepted to TACL. Final version is available here: (the main change is an additional task, light verb construction classification).

Still a Pain in the Neck: Evaluating Text Representations on...

Building meaningful phrase representations is challenging because phrase meanings are not simply the sum of their constituent meanings. Lexical composition can shift the meanings of the...

arxiv.org

Vered Shwartz

@VeredShwartz

5 years

How well do contextualized word embeddings address lexical composition? They are good in recognizing meaning shift ("give in" is different from "give") but much worse with revealing implicit meaning ("hot tea" is about temperature, "hot debate" isn't).

3

38

174

6

10

119

Vered Shwartz

@VeredShwartz

6 years

If all else fails towards the ACL submission deadline, this book may be the last resort ;)

2

42

124

Vered Shwartz

@VeredShwartz

5 years

I wrote a blog post about text generation: If you're new followers (thanks @kdnuggets !): my blog is about NLP topics for non-experts, with high-level & not too technical explanations.

1

39

122

Vered Shwartz

@VeredShwartz

5 years

Garry Kasparov, about AI: We are in the beginning of MS Dos and people think we are Windows 10. #AMLD2019

6

36

114

Vered Shwartz

@VeredShwartz

3 years

Me, writing a proposal: LMs confuse semantically-similar mutually-exclusive terms. Also me, absentmindedly holding a bag of lemons: should we keep the tomatoes in the fridge?

3

2

121

Vered Shwartz

@VeredShwartz

4 years

New pre-print: pre-trained LMs treat first name mentions as references to prominent named entities ("Donald" always refers to Trump). We turn this "common knowledge" into strong empirical evidence! We came up with the title before everyone was grounded 😬

3

12

117

Vered Shwartz

@VeredShwartz

4 years

I hate having to break a student's heart by recommending to reject their paper, just because (clearly!) their advisor was too lazy to review the submission, not to mention teach them best practices such as doing literature review. As a result, other people's time was wasted.

7

0

117

Vered Shwartz

@VeredShwartz

3 years

@yoavgo It's adorable :) Since my parents learned what I'm working on, my dad occasionally sends me basic NLP tutorials he finds online, and I don't have the heart to tell him I can teach these topics.

0

110

Vered Shwartz

@VeredShwartz

3 years

This thread is sad. As a junior PhD student I used to think "I wish I was religious, it would forbid me to work on Saturday". At some point I realized I'm not less productive and I'm much happier taking weekends off. Now I'm religious about work-life balance!

Prof Rachel Oliver 🐯

@ProfRachelGaN

3 years

Academics who work all weekend: when do you do stuff like laundry, grocery shopping etc? Or indeed get some exercise?

188

48

1K

2

6

117

Vered Shwartz

@VeredShwartz

6 years

I've written a python script that automates generating bib files by searching for bib entries in several sources: It passes sanity checks, but I take no responsibility for anyone's bib files.

4

25

98

Vered Shwartz

@VeredShwartz

5 years

Accepted at #NAACL2019 ! :)

Vered Shwartz

@VeredShwartz

6 years

Are GANs better than LMs in text generation? @GuyTvt and @HabibGavriel provide a simple way to approximate GANs to LMs which allows evaluating them using standard metrics like perplexity & BPC. It turns out GANs perform worse! (work with @JonathanBerant )

2

31

142

3

10

110

Vered Shwartz

@VeredShwartz

5 years

Every talk at #emnlp2019 : Chair: The next speaker is X from Y university who will speak about Z. Speaker: Hi, I'm X from Y university, I will be talking about Z.

12

1

110

Vered Shwartz

@VeredShwartz

2 years

Many thanks to CIFAR @CIFAR_News and Vector Institute @VectorInst for this recognition and opportunity, and congratulations to all the other new Canada CIFAR AI Chairs!

CIFAR

@CIFAR_News

2 years

Finally, @VeredShwartz @VectorInst @UBC_CS is building models capable of human-level understanding of natural language, particularly focused on the implicit meaning ("reading between the lines") in human speech.

1

8

30

12

111

Vered Shwartz

@VeredShwartz

2 years

I'm very excited about this visit, it will be my first in-person talk in a long time! 😃

UCSB Computer Science Department

@ucsbcs

2 years

Attend our 1ST OFFICIAL IN-PERSON TALK of 2022! Join us on Thurs. 02/10/22 from 12pm-1pm @ the Eng Science Building w/ Vered Shwartz (University of British Columbia) on her talk titled, "Incorporating Commonsense Reasoning into NLP Models." Abstract/bio in our FB/IG!

0

1

16

7

8

108

Vered Shwartz

@VeredShwartz

4 years

I stopped myself from tweeting something snarky right after reading my ACL reviews. An hour and a slice of cheesecake later, I'm ready to express some more concrete observations :)

7

6

102

Vered Shwartz

@VeredShwartz

5 years

Idea: a @kaggle competition in which you get several images of Starbucks coffee cups ordered by the same person, and you need to predict the real name of that person.

2

6

100

Vered Shwartz

@VeredShwartz

6 years

Me before going on vacation: - booking flights ✅ - packing ✅ - writing and running a bash script to utilize the lab servers for the entire time I'm away ✅

4

3

93

Vered Shwartz

@VeredShwartz

4 years

5 years later: #emnlp2020 , the #naacl2021 submission deadline and the #eacl2021 review deadline all happen within one week.

Manaal Faruqui

@manaalfar

9 years

Wen I become d president of ACL, the #emnlp deadline, d beginning of #naacl2015 & the #acl2015 camera-ready deadlines wud never be together.

1

2

9

2

101

Vered Shwartz

@VeredShwartz

2 years

My therapist told me to practice self-compassion. This evening I skipped yoga class and I'm having pumpkin spice latte. Am I doing it right?

11

2

99

Vered Shwartz

@VeredShwartz

6 years

Reading an author response where each comment is an argument against my question/comment. It's exhausting and makes me regret the time I've spent helping them improve the quality of the paper. Dear fellow researchers, peer review is not a war and author response is not a battle.

3

7

92

Vered Shwartz

@VeredShwartz

1 year

Ok, ok, I know it's dumb but I just had to.

9

6

98

Vered Shwartz

@VeredShwartz

6 years

I'm TAing in an @nvidia NLP workshop today in which the assignments use @TensorFlow . My main contribution today is converting people to DyNet 😃

4

6

89

Vered Shwartz

@VeredShwartz

4 years

Me, doing a literature review: everyone is doing the same thing. Husband: there are more people working in your field than ideas, so according to the pigeonhole principle multiple people will be working on the same idea.

2

5

92

Vered Shwartz

@VeredShwartz

5 years

Are you still around #acl2019nlp ? I'll be presenting this poster at the MWE workshop near hall 7, 11:00-12:30

12

9

91

Vered Shwartz

@VeredShwartz

1 year

Check out our new Findings paper #acl2023nlp ! We test LLMs on how well they can interpret noun compounds, e.g. a "chocolate bunny" is a chocolate shaped like a bunny. 1/5

6

11

91

Vered Shwartz

@VeredShwartz

1 year

A few years ago, my research areas within NLP were pretty diverse. In 2023, most of them (lexical semantics, discourse, and multiword expressions) fit into the same oral session 😲 #eacl2023

8

4

91

Vered Shwartz

@VeredShwartz

6 years

God, grant me the creativity to come up with new research ideas, and the energy to carry them out when they come weeks before a deadline.

2

3

84

Vered Shwartz

@VeredShwartz

2 years

I'm in Dublin for #acl2022nlp . I look forward to talking research in person! I will be presenting a Findings paper and @TuhinChakr will be presenting our TACL paper. See details below.

2

5

85

Vered Shwartz

@VeredShwartz

4 years

I'm preparing my slides for #emnlp2020 and I'm replacing previous "US president" examples in different examples in hopes that the prior examples will be outdated by the time of the conference in mid November🤞🤞🤞

5

0

80

Vered Shwartz

@VeredShwartz

6 years

Wizzair agent: you didn't pay to select a seat Me: I know, assign me one W: you didn't pay. You don't have a seat M: I didn't pay for a *specific* seat, I'll take *any* seat W: but you didn't pay M: I paid for *a* seat. What else did I pay for?? W: a flight ticket #catch22

2

5

78

Vered Shwartz

@VeredShwartz

7 years

@seb_ruder

0

18

72

Vered Shwartz

@VeredShwartz

3 years

I was curious about it too so I ran a very small-scale MTurk study on this recently. Here are a few highlights. I'll share more details later if people are interested 😀

Dr. Anna Prysłopska

@anna_pryslopska

3 years

In Polish, 3 am is night, but 4 am is morning. How is it for other languages? Is nighttime a blur or does day start between 3 and 4?🤔 #linguistics #nosleep

37

7

61

9

73

Vered Shwartz

@VeredShwartz

4 years

Anyone in need of a gloomy playlist? It goes well with pandemics, smoky skies, and soon-to-come EMNLP rejections :)

End of the world playlist

End of the world playlist · Playlist · 36 songs · 9 likes

open.spotify.com

3

70

Vered Shwartz

@VeredShwartz

4 years

2) A short paper should *not* be judged as a 4 pages long paper, but rather as a small, focused contribution. Reviewers often expect authors to solve NLP in 4 pages. And they reject the paper based on lack of experiments which are clearly outside the scope of the paper.

3

5

64

Vered Shwartz

@VeredShwartz

9 months

I'm in Canada, where snow geese fill the serene blue sky (top image), reading the horrendous news from Israel, where Hamas is filling the sky with missiles (bottom image), while slaughtering innocent civilians and kidnapping women, children, and elderly people from their homes,1/

2

5

69

Vered Shwartz

@VeredShwartz

4 years

4) It's completely OK to point out a problem without offering a solution. (I guess this goes back to the thread from a few days ago about other contributions apart from new models).

4

66

Vered Shwartz

@VeredShwartz

7 years

A watched neural network never converges.

2

9

66

Vered Shwartz

@VeredShwartz

1 year

The difference in my motivation, and the pace and quality of my grant proposal writing before and after eating that chocolate chip cookie is so significant that I'm almost considering listing it as a co-applicant.

1

0

66

Vered Shwartz

@VeredShwartz

5 years

Every time I forget something I knew, search for it and find something I wrote about it (lecture notes, Quora answer...), I feel a combination of pride and shame. But I think a more comforting way to look at it is that I store most of my knowledge on the cloud instead of locally.

5

0

62

Vered Shwartz

@VeredShwartz

2 years

I'm increasingly seeing left bracket written without a preceding space. I'm suspecting it's a generational difference (I'm reading mostly text written by younger people these days...). Any ideas why this is changing? I'm assuming there's a better explanation than efficiency.

16

1

64

Vered Shwartz

@VeredShwartz

4 years

3) I don't think it's fair to ask authors to perform experiments that require more resources than most institutes can afford. (And certainly not when these experiments are in any case beyond the scope of the paper).

1

3

59

Vered Shwartz

@VeredShwartz

4 years

Someone I hardly know and don't work with sent me an email on Friday at 11:30 PM, another one on Monday at 4am ("I think you missed my previous email"), and their colleague sent an email at 5 am. Have you heard of weekends, folks. I'll get to it when I'm done with my actual work.

6

0

60

Vered Shwartz

@VeredShwartz

7 years

Fun game: take famous quote, replace nouns with similar w2v words: "I have a daydream that one week this country..."

1

14

56

Vered Shwartz

@VeredShwartz

5 years

Git is so passive-aggressive when you accidentally commit a large file: doesn't warn you before you do, lets you go on with commits without telling you something is wrong, eventually bursts out when you push, and there's nothing you can do to fix it.

2

0

58

Vered Shwartz

@VeredShwartz

4 years

@tallinzen @nlpnoah The SustaiNLP workshop at EMNLP will focus on this exactly! (Except for the invite-only part, we welcome everyone! I hope the lack of exclusivity doesn't make it less appealing ;) ).

2

1

56

Vered Shwartz

@VeredShwartz

2 years

There is a special place in hell to the Vered whose email address differs in one letter from mine, who keeps mistyping her email address and signing me up to websites and mailing lists.

7

0

62

Vered Shwartz

@VeredShwartz

2 years

This video is an excellent demonstration of the state of text generation with LMs: hallucinations, inconsistencies, memorization of the training corpus, and nonsense... But the AI-generated cake "does kinda taste alright"

A.I. wrote me an Oreo Cake Recipe ... is it any good?! GPT-3

Artificial Intelligence (AI) wrote me a recipe and I baked it. It's weird but does it taste good?Cookbook Mothers Day Deals: https://bit.ly/ARcookbookSigned ...

www.youtube.com

2

7

60

Vered Shwartz

@VeredShwartz

4 years

HR: you are all encouraged to take days off and rest! My brain: Take a day off now and spend it staring at the ceiling? Here's a better idea. Why don't I work until I break and won't take a vacation until I can spend it sipping cocktails on the beach in an exotic destination?

0

2

59

Vered Shwartz

@VeredShwartz

4 years

I will be hosting a "Discourse and Pragmatics" birds of a feather session on Monday Nov 16 19:00-20:00 UTC / 11:00-12:00 PST. Join us in () and rocket chat () #emnlp2020

2

8

55

Vered Shwartz

@VeredShwartz

3 years

#ACL2021NLP rebuttal

2

0

55

Vered Shwartz

@VeredShwartz

4 years

Are you concerned about the cost, environmental impact, and usability of large NLP models? Are you convinced that abundant data and compute are imperative for true language understanding? Help us collect questions for the SustaiNLP panel at #emnlp2020 !

SustaiNLP Workshop

@SustaiNLP2023

4 years

We are collecting questions for the SustaiNLP panel at #emnlp2020 - do you have any questions to our panelists regarding their view on efficiency of NLP models?

1

6

16

1

14

56

Vered Shwartz

@VeredShwartz

1 year

I'm super excited about our new dataset and I look forward to see models developed to solve it! This project was fun to work on and @_eunjeong_hwang did amazing job😃

EunJeong Hwang

@_eunjeong_hwang

1 year

Check out our new work! We present the task of meme captioning and release a new dataset, MemeCap, containing 6.3K memes along with the title of the post containing the meme, the meme captions, the literal image caption, and visual metaphors. 1/3

2

13

85

5

9

56

Vered Shwartz

@VeredShwartz

7 years

I wrote a new blog post about ambiguity in language

2

12

52

Vered Shwartz

@VeredShwartz

3 years

We are organizing an AKBC workshop on commonsense and KBs (with @ABosselut , @xiang_lorraine , and @billyuchenlin ). Consider submitting new or previously-published papers. We will also have awesome invited speakers and panelists! More details here: .

CSKB@AKBC21

Workshop on Common-Sense Knowledge Bases at AKBC 2021

akbc-cskb.github.io

0

14

55

Vered Shwartz

@VeredShwartz

9 months

@emilymbender Emily, your silence since this tweet is troubling. I think your intentions are good and I don't think you condone the Hamas, but I find the lack of condemnation troubling. You're in a position of power as soon-to-be ACL president. 1/

2

4

54

Vered Shwartz

@VeredShwartz

4 years

TFW you read a paper that cites an old paper of you that does X, yet still claims "To the best of our knowledge, we are the first to propose X" (even I wasn't the first! 😄).

7

0

48

Vered Shwartz

@VeredShwartz

4 years

What annoying habits have your neighbors developed during the pandemic? My neighbor is learning to play the saxophone and she has been playing the same 7 note sequence for hours a day since March.

7

0

51

Vered Shwartz

@VeredShwartz

4 years

3

0

54

Vered Shwartz

@VeredShwartz

1 year

This seems consistent with my experience lately. We had to manually verify text written by annotators and filtered out quite a bit of text that looked LM-generated. In addition, the annotations for verification/ranking tasks were so noisy that we decided to not do them in mturk.

Manoel

@manoelribeiro

1 year

One of our key sources of human data is no longer fully “human"! We estimate that 33-46% of crowd workers on MTurk used large language models (LLMs) in a text production task - which may increase as ChatGPT and the like become more popular and powerful.

48

584

2K

1

13

54

Vered Shwartz

@VeredShwartz

2 years

Join us tomorrow at @csrr_workshop to learn about new research in commonsense! We have an exciting program with excellent invited speakers and lightning talks. We will be in person at the Liffey A and on zoom. #acl2022nlp

1

14

50

Vered Shwartz

@VeredShwartz

6 years

Long paper with Ido Dagan: a model for noun compound paraphrasing (apple cake -> cake made of apples) that better generalizes for unseen noun compounds ("pear tart" has the same relation as "apple cake") and for similar paraphrases ("w2 made of w1" and "w2 containing w1").

0

3

52

Vered Shwartz

@VeredShwartz

5 years

Proud of @ShanyBarhom for her first paper! We jointly predict entity and event coreferences based on their predicate-argument relationship. Our model achieved state-of-the-art performance on the ECB+ dataset. We will upload the camera-ready version soon.

Shany Barhom

@ShanyBarhom

5 years

I'm more than happy to announce that our long paper "Revisiting Joint Modeling of Cross-document Entity and Event Coreference Resolution" got accepted to #ACL2019nlp @ACL2019_Italy ! 😃 with the wonderful @VeredShwartz and @AlonEirew .

5

8

31

0

1

50