zhou Yu @Zhou_Yu_AI Twitter profile

Pinned Tweet

zhou Yu

1 year

My lab is looking for a postdoc to work on some exciting LLM and Multimodal work. Please fill this simple form if you are interested: Colleagues and friends, please retweet to spread the words.

17

113

344

Last Seen Profiles

@nargieo

@kookmin_records

@RaufA39732

@Hummingmoth

@Mushkicohen

@RambergViktor

@cubero_alberto

@peytonoleary6

@stw_pdg

@ahm3d711

@Asher_Blackwood

@CP_3_

@laviestbeelle

@DUTH_PILIGRIM

@helshilock

@JaanaLiimatain2

@smoktatsuro

@paceywylan

@TJeangeorge

@SalhLy261

@xiomomo25227938

@Nelso79386

@kohaku_miharuzi

@AnimeLaffs

@miyuki__tabi

@ligiacobo

@skarschu

@vcm_en

@changelt28_

@maievflaky

@vivaleverage

@raspibolt

@st_eckels

@GTRadialUK

@sSonOfGreed

@EXOSCUNION

zhou Yu

@Zhou_Yu_AI

2 years

Hello, non-native English speakers, do you often find it difficult to find someone to practice everyday conversations in English? Try our lab's edubot to practice conversations with a chatbot and receive feedback to improve your English.

48

1K

4K

zhou Yu

@Zhou_Yu_AI

4 years

My research group will be moving to the CS department at Columbia University in Jan 2021 after three awesome years at UC Davis. Feel free to reach out if you are in the NYC area, as we are always open to collaborate on various NLP topics, especially in dialog systems.

50

18

733

zhou Yu

@Zhou_Yu_AI

3 years

I am teaching a new discussion-based class this semester called Conversation AI. Here is my course's reading list with all the wonderful slides made by my students at Columbia. This could serve as a good readinglist for people who want to get into ConvAI.

COMSE6998_006_2021_1 Conversational AI

Presentation Plan Date,Topic,Papers,Presenter1,Presenter 2,Slides Link 1/12/2021,Introduction,1: Social chatbot VS Task-oriented chatbot,Zhou Yu,https://drive.google.com/file/d/1eMvnhqdC-gRLm56d2dF...

docs.google.com

6

70

411

zhou Yu

@Zhou_Yu_AI

3 years

Hi Everyone, I am looking for a postdoc researcher. The position can start as early as Jan 2022. Any time before Sep 2022 is possible. The length of the position can range from one to three years. The lab is looking for someone with a strong NLP and ML background.

5

79

287

zhou Yu

@Zhou_Yu_AI

2 years

GODEL is available on hugging face. Looking for a large open-source pre-trained language model for dialog? GODEL leverages grounded pretraining designed to better support finetuning phases that require information external to the current conversation (e.g. database or document).

3

37

267

zhou Yu

@Zhou_Yu_AI

1 year

大家好！我們是哥伦比亚大学计算机科学系的研究团队，我們最近开发了一个母语是中文的英语学习者打造的AI会话练习系统正在热烈征集线上使用者，欢迎大家试用，请求大家分享和填写问卷提供反馈，这会帮助我们研究和后续改进系统！整个流程15-20分钟左右。谢谢。

9

58

249

zhou Yu

@Zhou_Yu_AI

1 year

Congrats Dr. Weiyan Shi! Weiyan is my first PhD student that graduated from Columbia. It was a pity that we couldn't do this type of celebration last year with my two Davis PhD graduates.

10

3

192

zhou Yu

@Zhou_Yu_AI

5 years

This is why I encourage cleaning existing datasets and creating better new datasets. After all, we are solving problems not building models to fit data sets. We cleaned MultiWOZ recently and will publish a tech report along with the cleaned data soon.

Stanford NLP Group

@stanfordnlp

5 years

On the importance of good, appropriate data sets for #NLProc , but how “the system” tends to wrongly incentivize researchers.

1

90

243

3

30

184

zhou Yu

@Zhou_Yu_AI

2 years

A new collaborative work with MSR on building a larger and better pre-trained dialog model.

Microsoft Research

@MSFTResearch

2 years

Combining flexibility, utility, and grounding, the GODEL language model helps create dialog agents that are unrestricted in the types of queries they can respond to and the sources of information they can draw from, all while providing useful responses:

4

32

198

1

5

175

zhou Yu

@Zhou_Yu_AI

4 years

Jaime was not only a great researcher but a great department chair. I still remember him paying a semester of my tuition when I left one of my advisors in the mid of my PhD. He is a kind person who believes in students. Jaime will be remembered.

Language Technologies Institute | @CarnegieMellon

@LTIatCMU

4 years

It's with deep sadness that we announce that our founder and longtime director, Jaime Carbonell, has died. Dr. Carbonell was a pioneer in the field of language technologies and an inspiration to those who knew and worked with him.

6

48

152

0

5

174

zhou Yu

@Zhou_Yu_AI

1 year

My son, Eric's first lesson in electro-magnetism

4

1

129

zhou Yu

@Zhou_Yu_AI

5 years

The AAAI rebuttle deadline is this Sunday 8pm PST and we just got the review a few hours ago. This basically means: Academics have to work over the weekends!

6

12

122

zhou Yu

@Zhou_Yu_AI

3 years

Finally got my new website set up.

0

2

115

zhou Yu

@Zhou_Yu_AI

1 year

I asked chatGPT about myself. This content can fool people outside of the NLP field. The glaring factual error is that I don't have an NSF CAREER award!😠

18

5

112

zhou Yu

@Zhou_Yu_AI

3 years

After a major conference result release, there are always happy and sad moments. This year our lab and our collaborators have seven papers in the ACL main conference(including 1 short paper) and 1 ACL finding. Though some of the best work didn't get in, we should still celebrate

3

110

zhou Yu

@Zhou_Yu_AI

3 years

Also looking for Postdoc

ColumbiaCompSci

@ColumbiaCompSci

3 years

. @Zhou_Yu_AI is looking for #PhD students who want to advance the frontier of natural language processing #NLP ! Check out to learn more about her research. For info on our #computerscience PhD programs . The deadline is December 15.

0

24

59

4

18

104

zhou Yu

@Zhou_Yu_AI

4 years

We have three papers all about dialogs, accepted in ACL. Papers and code coming out soon. The first one got 4.5, 4.5, 5 ratings in reviews. Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation, Weixin Liang, James Zou and Zhou Yu

2

6

94

zhou Yu

@Zhou_Yu_AI

4 years

This is pure racism!

Donald J. Trump

@realDonaldTrump

4 years

The United States will be powerfully supporting those industries, like Airlines and others, that are particularly affected by the Chinese Virus. We will be stronger than ever before!

104K

46K

236K

1

85

zhou Yu

@Zhou_Yu_AI

3 years

How do you evaluate your dialog systems?🤔 Our lab's LegoEVAL is here to help. It is a tool for dialog systems evaluation. @aclmeeting demo track. #Preprint :

4

11

81

zhou Yu

@Zhou_Yu_AI

4 years

I am giving a talk at CVPR visual QA and dialog workshop tomorrow 10am PST. If you are interested in visual dialog, please come by.

3

4

77

zhou Yu

@Zhou_Yu_AI

5 years

My first keynote talk! I have done many invited talks before. But this is my first keynote talk.

IWSDS2020

@iwsds2020

5 years

We are happy to announce that @Zhou_Yu_AI from UC Davis, will be one of our keynote speakers. She is an expert in multimodal dialog systems. Her team won the #AlexaPrize ( @alexa99 ) last year, and she was featured in Forbes as 2018: 30 under 30.

0

2

5

2

79

zhou Yu

@Zhou_Yu_AI

3 years

Our school just had a celebration for Alfred Ago on winning the Turning Award this year. Al is in good health.

1

74

zhou Yu

@Zhou_Yu_AI

1 year

Dilek interviewed me for her ICLR 2023 keynote. We talked about why current LLMs are still not solving the Conversational AI.

Interview with Prof. Zhou Yu, Columbia University, about dialogue...

null

www.youtube.com

0

12

67

zhou Yu

@Zhou_Yu_AI

3 years

Good luck to your ACL rebuttals everyone. If you are having a second thought. SIGDIAL 2021 is a good choice to resubmit your paper. The deadline is April 2nd but will be extended to April 10th. You just need to submit a placeholder on April 2nd.

2

3

61

zhou Yu

@Zhou_Yu_AI

3 years

Just registered for in-person EMNLP 2021. Hope to see more NLPers in person in the Dominican Republic!

1

0

61

zhou Yu

@Zhou_Yu_AI

1 year

It was great to just take a train to attend AAAI from NYC to DC. What's more amazing is that I walked to the venue from the union station. What an energy-efficient trip! Excited to meet old friends and make new friends in #AAAI2023

1

0

59

zhou Yu

@Zhou_Yu_AI

1 year

My newly graduated student Weiyan will become a new faculty at northeastern!

Weiyan Shi

@shi_weiyan

1 year

🥳I will join @Northeastern as an Assistant Prof. in Fall 24 and @stanfordnlp as a postdoc with @Diyi_Yang for 23-24. Join my lab, CHATS (Conversation, Human-AI Tech, Security), to work on privacy-preserving dialog systems, as visioned by this demo📌 from CHATS' first project,

29

24

444

0

60

zhou Yu

@Zhou_Yu_AI

1 year

Check out my new collaborative work with Google on PRESTO. A new dataset on multilingual task-oriented dialog parsing. We have included real-world language phenomenons such as code-switch, corrections, etc.

PRESTO – A multilingual dataset for parsing realistic task-oriented dialogues

Posted by Rahul Goel and Aditya Gupta, Software Engineers, Google Assistant Virtual assistants are increasingly integrated into our daily routines....

research.google

1

8

57

zhou Yu

@Zhou_Yu_AI

3 years

Our group has seven papers to present at ACL. Please stay tuned. Code, data and slides are all available on my homepage.

1

2

52

zhou Yu

@Zhou_Yu_AI

2 years

, , .

GODEL Demo - a Hugging Face Space by microsoft

huggingface.co

1

9

52

zhou Yu

@Zhou_Yu_AI

3 years

All aboard to punta cana. Excited to meet old and new friends in EMNLP 2021 @emnlpmeeting

0

48

zhou Yu

@Zhou_Yu_AI

5 years

Both my first(Zhou) and last name(Yu) are generic Chinese names. Zhou is also hard to pronounce. I prefer to be called Jo. What's worse is that because my first name is a more popular last name. People call me Prof. Zhou sometimes. It's Prof.Yu please.:)

Arvind Narayanan

@random_walker

5 years

Today I want to take a break from sharing research to share a personal story instead. It’s a story about my name, why I once decided to quit academia, why I came back, what I learnt from it, and why I’m grateful to have an audience here on Twitter.

63

654

3K

1

0

45

zhou Yu

@Zhou_Yu_AI

4 years

Some media coverage of our recent AAAI 2020 work on Neural news headline editing. The paper is available here, please contact us if you want to access the dataset.

0

7

42

zhou Yu

@Zhou_Yu_AI

5 years

Our new AAAI paper and the code is here One dialog context can have multiple dialog responses that can be appropriate for finishing the goal. Existing datasets do not count in all the possible responses.

davis-nlp / DAMD-MultiWOZ · GitLab

The code and data for AAAI 2020 paper "Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context".

gitlab.com

2

6

42

zhou Yu

@Zhou_Yu_AI

3 years

Really proud of my student Sky, This is a paper he did with Joyce from Michigan during her undergrad. The work is about exploring the theory of mind framework in a MineCraft game.

Sky CH. Wang

@skychwang

3 years

WHA-WHA-WHAAAGHYQUIYAU We just got an outstanding paper award at EMNLP 2021!!!!🎉 #EMNLP Do come to our Oral Session @ 13:45 on 11/7 to find out more!!!

4

7

73

1

0

42

zhou Yu

@Zhou_Yu_AI

2 years

Finally, we are starting a Twitter account for the Columbia NLP group.

Columbia NLP

@columbianlp

2 years

Hello everyone, this is the Columbia NLP Twitter account. We will post new work produced by the Columbia NLP group. Please stay tuned.

9

23

275

2

0

41

zhou Yu

@Zhou_Yu_AI

1 year

Drago contributed to the NLP community so much, especially to the Columbia NLP group, where he received his Ph.D. and taught NLP classes as an adjunct. His family needs help. Drago's daughter, Victoria, needs medical care. Please help them.

Help Dragomir Radev's family, organized by Kathleen McKeown

Dragomir L. Radev, the A. Bartlett Giamatti Professor of Computer Science at Yale Univer… Kathleen McKeown needs your support for Help Dragomir Radev's family

www.gofundme.com

2

19

39

zhou Yu

@Zhou_Yu_AI

4 years

I find following related work in NLP really challenging these days. There are so many papers out every month! After panicking for a while, I decide to only read several papers in depth and just scan the abstract of the rest. I also highly recommend having reading groups.:)

Sasha Rush

@srush_nlp

4 years

Some musings on NLP/ML self-study. tldr: * Reading a paper is really hard, give yourself a lot of time and slack. * Pick depth over breadth. If you do depth well, you get breadth for free. * Be actively skeptical of all claims. Read your own drafts with 2x that skepticism.

11

121

686

0

4

37

zhou Yu

@Zhou_Yu_AI

5 years

Finally we are done with the ACL deadline! It has been a while since I worked till the last minute of a paper deadline. But I kind of cheated this time by being in China. It is only 8pm now.:) All the good wishes to our group's hard work.

0

35

zhou Yu

@Zhou_Yu_AI

4 years

I will give a talk at the JHU JSALT workshop this Friday 7am PST. I know it is early. :) You can also watch a video later. :)

JHU CLSP

@jhuclsp

4 years

JSALT 2020's first plenary speaker presentation - which is open to the public - is set for this Friday (July 3) at 10 AM EDT! @Zhou_Yu_AI is our presenter, and the title of her talk is "Seamless Natural Communication between Humans and Machines." Info:

1

4

16

0

2

37

zhou Yu

@Zhou_Yu_AI

1 year

Check out our new paper on speech based few-shot emotion detection

Max Chen

@maximillianc_

1 year

Super excited to share my new #INTERSPEECH2023 paper with my advisor @Zhou_Yu_AI on pre-finetuning for few-shot learning in speech tasks! Our work is motivated by the difficulty of out-of-domain speaker adaptation. Paper: Code:

3

6

54

0

1

36

zhou Yu

@Zhou_Yu_AI

5 years

Congrats to our group for 5 AAAI acceptance. We will release all the final version soon. Weixin Liang, Youzhi Tian, Chengcai Chen, and Zhou Yu, MOSS: End-to-End Dialog System Framework with Modular Supervision, AAAI, 2020

MOSS: End-to-End Dialog System Framework with Modular Supervision

A major bottleneck in training end-to-end task-oriented dialog system is the lack of data. To utilize limited training data more efficiently, we propose Modular Supervision Network (MOSS), an...

arxiv.org

2

3

36

zhou Yu

@Zhou_Yu_AI

5 years

While everyone is in NeurIPS, I had a nice trip in Beijing. I finally got my U.S. visa renewed. I can attend all the conferences next year! It's a good time to invite me for talks out of the states. :)

1

0

35

zhou Yu

@Zhou_Yu_AI

1 year

Our AAAI 2023 work: MIGA: A Unified Multi-task Generation Framework for Conversational Text-to-SQL will happen at 2:30 today at 149AB , ,

0

3

35

zhou Yu

@Zhou_Yu_AI

4 years

Excited to be at NYC for #AAAI2020 Tomorrow I will give an invited talk 4:00-4:40pm at the conversation recommendation system workshop. My student Weiyan will talk about our non-collaborative dialog challenge in DSTC workshop. Hope to see you soon!

0

4

35

zhou Yu

@Zhou_Yu_AI

2 years

Looking forward to attending @NAACL2022 in person. My group has several papers to present. Details can be found on my homepage:

0

3

34

zhou Yu

@Zhou_Yu_AI

1 year

Hi All, Please try our new dataset to evaluate your LLM's EQ.

Weiyan Shi

@shi_weiyan

1 year

Put ChatGPT at a cocktail party🥂. Can it - understand people's conversations, gestures - figure out their relations, - and even chime in with social advice? 🦍Announce KokoMind. 🌟Check out this demo! More at #AI #GPT4 #ChatGPT #OpenAI #Shrinking 🧵

13

88

306

2

3

33

zhou Yu

@Zhou_Yu_AI

11 months

Hi All, Please check out a joint work between Salesforce and our lab at Columbia on a comprehensive collection of dialog data with diverse domains and tasks.

Caiming Xiong

@CaimingXiong

1 year

Introducing 🎙️DialogStudio🎙️, the largest and most diverse dialogue dataset collection with diverse goals （e.g. task-oriented, open-domain, NLU, etc.) and different domains (e.g. finance, insurance software, movie, etc.) #NLP #AI

4

49

209

0

4

34

zhou Yu

@Zhou_Yu_AI

4 months

Our lab's recent work on understanding why LLMs have in-context-learning abilities.

Yanda Chen

@yanda_chen_

4 months

[1/7] Pre-trained LMs can do in-context learning, but this is unexpected given the distribution shift between pre-training data and ICL prompts. What structures of pre-training data yield ICL? Check out our work “Parallel Structures in Pre-training Data Yield In-Context Learning”

2

20

87

0

1

33

zhou Yu

@Zhou_Yu_AI

5 years

Our EMNLP poster this Tuesday on How to train a user simulator for RL-based dialog system. There is no perfect user simulator, the key is to train and test your system on multiple imperfect simulators with different pros and cons, so your system is not biased.

1

6

33

zhou Yu

@Zhou_Yu_AI

4 years

UC Davis Gunrock Team Statement on Amazon Alexa Prize 2019 Disqualification

UC Davis Gunrock Team Statement on Amazon Alexa Prize 2019 Disqualification .pdf

drive.google.com

1

3

33

zhou Yu

@Zhou_Yu_AI

4 years

Have you wondered what makes a chatbot sound more like human?Whether chatbot's agency (bot or human) will influence the persuasive power of the chatbot ? Come to see our CHI 2020 paper by @shi_weiyan . link: Video link:

2

6

31

zhou Yu

@Zhou_Yu_AI

5 years

We had a group BBQ at my housewith all the old and new lab members and friends of Davis NLP groups.

0

32

zhou Yu

@Zhou_Yu_AI

4 years

Dialogs are still going strong

ACL2020: General Conference Statistics

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

acl2020.org

0

4

31

zhou Yu

@Zhou_Yu_AI

5 years

Complete list of ACL workshop! I am organizing the Conversational AI team with many great colleagues.

0

1

30

zhou Yu

@Zhou_Yu_AI

2 years

Please retweet to help us reach more English learners.

2

7

28

zhou Yu

@Zhou_Yu_AI

5 months

Our new work on language learning

Billy Xuanming Zhang

@XuanmingZhang07

5 months

🤔As an English second-language learner, I usually have trouble replacing a word, that I frequently used in my essays, with substitutes that show better language proficiency. ✍️Introducing ProLex: a benchmark for language proficiency-oriented lexical substitution 🧵(1/n)

2

12

78

0

1

28

zhou Yu

@Zhou_Yu_AI

3 years

New NSF postdoc fellowship available ENGINEERING FELLOWSHIP, Applications will be accepted from June 21 through July 6, 2021.

0

7

28

zhou Yu

@Zhou_Yu_AI

3 years

Joint work from our lab and CoAI on emotional support dialogs. We collected a dialog dataset to provide emotional support.

TsinghuaCoAI

@TsinghuaCoAI

3 years

Emotional support is a crucial ability to dialog systems, while providing effective ES is not intuitive. In our #ACL2021 paper, we define the Emotional Support Conversation task, propose an ESC Framework, and present an ESC dataset. #NLProc #TsinghuaCoAI

2

3

15

0

2

28

zhou Yu

@Zhou_Yu_AI

3 years

If you want to join my group as a postdoc to work on NLP or NLP+Vision at Columbia. Please apply the CRA fellowship below.

Computing Research

@CRAtweets

3 years

CRA/CCC Announces CIFellows 2021 Program

0

71

124

2

5

28

zhou Yu

@Zhou_Yu_AI

2 years

Check out our latest NLP and CSS work on emotional reactions to music, coming to EMNLP 2022!

Sky CH. Wang

@skychwang

2 years

Do we react emotionally to music in different ways? 今天你网抑云了吗? Our @columbianlp #EMNLP2022 paper (w. @SmaraMuresanNLP and @Zhou_Yu_AI ) answers these questions across a social music platform, Netease Cloud Music. tl;dr answer: yes! a 🧵

4

11

84

0

1

28

zhou Yu

@Zhou_Yu_AI

3 years

SIGDIAL 2021 will close paper registration on April 2nd(23:59 GMT-11). The paper submission deadline is extended to April 10th. But please remember to submit a placeholder tomorrow!

1

6

27

zhou Yu

@Zhou_Yu_AI

4 years

Another talk tomorrow.

LMSS @ Cornell Tech: Zhou Yu (UC Davis)

Learning Machines Seminar Series What: LMSS @ Cornell Tech: Zhou Yu (University of California, Davis) When: Friday, September 18th, 11:30AM Where: Zoom "Personalized Persuasive Dialog Systems" Dialog...

events.cornell.edu

1

0

27

zhou Yu

@Zhou_Yu_AI

5 years

This is a previous Podcast on dialog systems I did with NLP highlights with @nlpmattg @waleed_ammar We talked about some topics such as domain adaptation in dialog systems and end-to-end training.

89 - Dialog Systems, with Zhou Yu

In this episode, we invite Zhou Yu to give an overview of dialogue systems. We discuss different types of dialogue systems (task-oriented vs. non-task-oriented), the main building blocks and how they

soundcloud.com

0

2

25

zhou Yu

@Zhou_Yu_AI

3 years

Please come to see our CVPR paper on Multilingual and Multimodal Pretraining tomorrow!

Mingyang Zhou

@MingyangKevinZh

3 years

The live session for our #CVPR paper UC2 is on Tuesday 6:00 AM - 8:30 AM EDT. If you are interested in Multi-lingual Multi-modal Pre-training, please feel free to check our paper: and bring questions to us!

2

4

1

0

25

zhou Yu

@Zhou_Yu_AI

5 years

My group has four events this Tuesday at EMNLP. Please come to meet my students and learn about dialog research! You should definitely come to chat with our Amazon Alexa Prize winner, Gunrock. My students can answer all your questions, for example, how we won the $500,000 prize

1

5

23

zhou Yu

@Zhou_Yu_AI

3 years

@deviparikh This is amazing. My mom also loves knitting, here is a bunny she made for my baby.

1

0

24

zhou Yu

@Zhou_Yu_AI

5 years

Excited to organize the ACL 2020 the 2nd Conversation AI workshop! Hope we will have a lot of submission this year again.

Mihail Eric

@mihail_eric

5 years

Super excited to be organizing the 2nd NLP For Conversational AI Workshop held at #acl2020 . If you like Seattle coffee ☕, Washington hikes ⛰️, and talking machines 🤖, we look forward to seeing you there! @aclmeeting

1

21

107

1

2

22

zhou Yu

@Zhou_Yu_AI

4 years

Two Positions in ML/NLP/Vision at UC Davis (All Ranks). I really enjoyed being at Davis. Please consider applying.

Job Opportunities

Job Opportunities Tenure-Track Assistant Professor in the Department of Computer Science Artificial Intelligence and Machine Learning Apply here: https://recruit.ucdavis.edu/JPF06133 The University...

cs.ucdavis.edu

1

5

22

zhou Yu

@Zhou_Yu_AI

1 year

We just extended the deadline for a week. Please consider submitting to our Social Influence in Conversations workshop at ACL 2023

Social Influence in Conversations Workshop

@SIConWorkshop

1 year

📢📢 The direct paper submission deadline for SICon at ACL 2023 has been officially extended to April 24th!! Check out the Call for Papers here: #ACL2023 #SICon2023 #ConversationalAI #NLProc

0

4

7

0

1

22

zhou Yu

@Zhou_Yu_AI

5 years

My undergrad intern is discouraged from @iclr_conf reviews and refused to improve the submission for future conferences. I am not blaming this on the conference review process. The question is What should we do as mentors to help students battle critical reviews?

6

3

20

zhou Yu

@Zhou_Yu_AI

5 years

This paper says that disclosing bot's identity hurts sales. But the bot's quality has a huge effect on its persuasiveness. We have a study dives deeper on this issue but on a different task (under review). Also I wonder if the culture difference will play a role in this.

Stanford NLP Group

@stanfordnlp

5 years

Interesting new datapoint on the ethical issue of ChatBots disclosing that they are not human: Voice assistant sales agents work as well as humans when they don’t disclose but are not very effective if they do. HT @catherinebuk

4

35

92

0

7

22

zhou Yu

@Zhou_Yu_AI

4 years

Data!! Model!!!

Mihail Eric

@mihail_eric

4 years

What are dialogue researchers thinking about in 2020? Here are the most frequent terms appearing in papers at the @aclmeeting ConvAI workshop:

2

1

8

1

0

21

zhou Yu

@Zhou_Yu_AI

3 years

Check out our new paper on how to design a new differential privacy notion that fits natural language generation models.

Weiyan Shi

@shi_weiyan

3 years

Have you wondered if your name's been used to train GPT2? How to train high-utility privacy-preserving language models 🧐? Check out our new paper on "Selective Differential Privacy"! @Zhou_Yu_AI @ruoxijia #NLProc Paper: Code:

3

2

18

0

22

zhou Yu

@Zhou_Yu_AI

4 months

Melanie Subbiah on LinkedIn: How well do LLMs understand narrative as judged by creative writers? I...

How well do LLMs understand narrative as judged by creative writers? I was excited to combine my longstanding love of fiction writing with my work on LLMs for…

www.linkedin.com

0

3

19

zhou Yu

@Zhou_Yu_AI

3 years

I also like this idea of posting accepted paper ID. CVPR does this and I liked it. Then I don't have to wait for all my students to forward their paper decisions to me. I would be relieved to avoid that awkward question of "how did your paper do?"

0

20

zhou Yu

@Zhou_Yu_AI

4 years

I am also very concerned. We have so many students with F1 Visa in computer science.

Hal Daumé III

@haldaume3

4 years

Appears to apply even if your university is in "hybrid" mode, if _you_ in particular happen to only be taking online courses. Hopefully directed research counts as in person, but it will definitely take some university lawyers to try to figure this out.

5

22

132

0

20

zhou Yu

@Zhou_Yu_AI

4 years

Tomorrow we have another two spotlight talk on dialogs. One on dialog planning and another on dialog understanding.

1

18

zhou Yu

@Zhou_Yu_AI

3 years

We all need some cute baby animal pictures to process our ACL reviews.

omnitrix 🇪🇸

@omsdotcom

3 years

happy sunday here’s some cute bby animals

2

8

55

1

0

20

zhou Yu

@Zhou_Yu_AI

2 years

We have two related papers on this project. -Using Chatbots to Teach Languages -ErAConD: Error Annotated Conversational Dialog Dataset for Grammatical Error Correction

ErAConD : Error Annotated Conversational Dialog Dataset for...

Currently available grammatical error correction (GEC) datasets are compiled using well-formed written text, limiting the applicability of these datasets to other domains such as informal writing...

arxiv.org

0

1

20

zhou Yu

@Zhou_Yu_AI

4 years

#ICLR2020 Please come to our poster

0

19

zhou Yu

@Zhou_Yu_AI

5 years

This is one of the interview of me on dialog systems.

Arturo

@arturoShares

5 years

NLP Highlights: 89 - Dialog Systems, with Zhou Yu ⁦ @allen_ai ⁩ ⁦ @Zhou_Yu_AI ⁩ 👏🗣🤖

0

5

1

18

zhou Yu

@Zhou_Yu_AI

5 years

A Chinese company advertises their AI Meetup. Can anyone see the problem?

2

0

19

zhou Yu

@Zhou_Yu_AI

5 years

Please consider Davis. We are only one hour away from the Bay area. Our department is colleageal and welcoming. If you have any questions, feel free to email me.

zhou Yu

@Zhou_Yu_AI

5 years

We are hiring ML at UC Davis. Please consider us

1

8

13

0

2

18

zhou Yu

@Zhou_Yu_AI

4 years

Here is a blog post of our new AAAI paper on news headline editing. You can find paper, code, and data on it. Stay tuned for our presentation in AAAI next week.

0

1

17

zhou Yu

@Zhou_Yu_AI

4 years

I am gonna give a talk at UCLA Center for Language, Interaction and Culture. Excited to meet experts in various domains.

0

1

18

zhou Yu

@Zhou_Yu_AI

4 years

This year ACL is virtual, so feel free to reach out though ACL chat to me on topics such as dialog systems, multimodal learning and language generation.

1

0

18

zhou Yu

@Zhou_Yu_AI

4 years

Please let me know if you are interested in doing dialogs or language generation.

Computing Research

@CRAtweets

4 years

CRA and @compcomcon are pleased to announce a new Computing Innovation Fellows Program for 2020 #NSFCISE #computing #Phd #postdoc

0

46

111

0

18

zhou Yu

@Zhou_Yu_AI

5 years

This is the worst situation I can imagine. It's already very difficult for women to have a successful academic career and a happy family, due to the tenure system. Taking away funding during a women's material leave is outrageous!!

Rhiannon Pugh

@PughRhiannon

5 years

I'm sad that the funding we were successfully granted has been revoked because I am going on maternity leave and apparently an extension to account for this is beyond the remit of the funders. It's hard to win funding, to have it taken away again after so much work is gutting 😭

558

2K

11K

0

1

16

zhou Yu

@Zhou_Yu_AI

5 years

Spoken dialog has disfluences, such as hmm, ah, and self-correction. In addition, spoken dialog has a lot of ellipses and ASR errors! If you want to know how to build a dependency parser for spoken dialog systems Come to our EMNLP dialog session on Tuesday.

1

2

17

zhou Yu

@Zhou_Yu_AI

4 years

Coming soon

Xin Eric Wang

@xwang_lk

4 years

Our #acl2020nlp workshop on Advances in Language and Vision Research (ALVR) is approaching! We have a great multi-disciplinary lineup of speakers: @yoavartzi , JJ Liu, LP, @mark_riedl , @lspecia , @Zhou_Yu_AI . Welcome to join #ALVR2020 on July 9! Website:

3

15

71

0

1

17

zhou Yu

@Zhou_Yu_AI

5 years

I had a great visit to UC Irvine. The campus is very green and the beach close by is gorgeous. Thanks @sameer_ for inviting me.

0

1

16

zhou Yu

@Zhou_Yu_AI

5 years

If you are struggling to make your RL-based dialog systems speak coherent sentences, please check our recent work in EMNLP. Mingyang will present it in the first day dialog track. Ask him for the code if you want to try this out yourself!

0

2

16

zhou Yu

@Zhou_Yu_AI

5 years

Had a nice visit in Beijing.

1

0

15

zhou Yu

@Zhou_Yu_AI

4 years

Great resource for NLP students

Graham Neubig

@gneubig

4 years

I've started to upload the videos for the Neural Nets for NLP class here: We'll be uploading the videos regularly throughout the rest of the semester, so please follow the playlist if you're interested.

3

72

304

0

2

15

zhou Yu

@Zhou_Yu_AI

1 year

We just released a new work evaluating whether the LLMs' explanation is faithful.

Yanda Chen

@yanda_chen_

1 year

[1/9] Large Language Models (LLMs) can mimic humans to explain human decisions. But can they explain THEMSELVEs? How to evaluate explanations along this axis? Check out our work “Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations”!