Victor Zhong @hllo_wrld Twitter profile | Pikagi

Pikagi

Victor Zhong

@hllo_wrld

4,256

Followers

450

Following

49

Media

1,529

Statuses

ML+NLP assistant prof @UWCheritonCS . Formerly @MSFTResearch @MetaAI , @SFResearch via @MetamindIO , @uwnlp , @StanfordNLP , @eceuoft .

Seattle, WA

https://t.co/qaEBsUO3aa

Joined February 2011

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

Pinned Tweet

@hllo_wrld

Victor Zhong

1 year

Some personal update: I will join @UWCheritonCS as Assistant Professor and @VectorInst as Faculty Member in 2024! I am *very* excited to be back in @Canada to help grow the Canadian AI ecosystem! Please apply if you are interested in a PhD at the intersection of NLP and ML!

66

23

403

Last Seen Profiles

@JoseLop17537876

@ShaneCarter5

@ItsTonyFresco

@pradabarbi3672

@MitActFacility

@ayamzohor

@phageconsortium

@higehig87972865

@NicoAgu88227340

@LeroyLaine62432

@EuroStarsTour

@simonhouston68

@BEDobbleU

@Mom2babes

@p_crawf

@vitello_sabrina

@WhatevrNevrmnd

@MichMitches

@LabBeyondCities

@RoxanneReaction

@StephanSports

@chaselyons

@Yahia_S_Mghraby

@jenjenosi

@snat_z

@LuizMar78112588

@OniquaMaraj

@otozuki_teru

@hesp_esports

@H_Miss88

@miyosino

@Yarmohammmady

@BriannaRus48888

@HeartHealthPark

@AnneBuunk

@ListyLiterackie

@hllo_wrld

Victor Zhong

2 years

tqdm is one of the most used libraries in machine learning.

28

87

2K

@hllo_wrld

Victor Zhong

3 years

Dear 2020 PhD students: what you're doing is nothing short of amazing. It is hard to start a PhD/collaborate with new people virtually/move to a new city/participate in a new community virtually during a pandemic. It will get better! We're all proud of you! Wish you all the best!

3

92

1K

@hllo_wrld

Victor Zhong

4 years

I wrote a guide on how to get started in NLP/ML research if you do not have a background in AI. If you are an undergraduate student looking to get into research, I hope this helps you!

10

141

647

@hllo_wrld

Victor Zhong

6 months

I am hiring strong PhD students in ML and NLP at the University of Waterloo to start in 2024. This is an excellent opportunity to be a part of a vibrant new NLP group w/ 5 professors. Please see more details here: . Deadline is Dec 1!

12

93

422

@hllo_wrld

Victor Zhong

4 years

Our #emnlp2020 reviews were largely constructive and detailed - I barely squeezed in my response at 900 words after responding to each question! If you are starting out in research and are horrified by academic Twitter please rest assured that there are also great reviewers!

4

7

157

@hllo_wrld

Victor Zhong

4 years

Super excited to share our @iclr_conf 2020 work RTFM: Generalising to Novel Environment Dynamics via Reading ()! Joint work w/ @_rockt and @egrefen at @facebookai research London on RL policies that generalise to new envs via reading! 1/3 👇

Tweet media one

Tweet media two

2

30

144

@hllo_wrld

Victor Zhong

6 years

The Dockerized @PyTorch implementation of our @acl2018 paper Global-Locally Self-Attentive Dialogue State Tracker () is now available on Github (). #nlproc

Tweet card media

GitHub - salesforce/glad: Global-Locally Self-Attentive Dialogue State Tracker

Global-Locally Self-Attentive Dialogue State Tracker - salesforce/glad

0

48

141

@hllo_wrld

Victor Zhong

2 years

I am on the job market this year for academic and research positions - please share broadly! My research is on reading to learn: instead of learning specific problems, how can we learn to interpret language to generalize to new problems? More at #nlproc

1

30

125

@hllo_wrld

Victor Zhong

2 years

Our latest reading to learn paper Language Dynamics Distillation will appear at #NeurIPS2022 ! In LDD, we pretrain the agent to read to model env dynamics. LDD improves generalization on 5 distinct language grounding envs over naive RL, VAE, inverse RL. 🧵

Tweet media one

Tweet media two

2

12

51

@hllo_wrld

Victor Zhong

6 years

Wow this class by @gneubig is probably the most up-to-date #DeepLearning + #NLProc class I've ever seen:

0

26

107

@hllo_wrld

Victor Zhong

6 years

Excited to join @uwnlp in a few weeks to start my PhD! I'm forever grateful to @chrmanning , @RichardSocher , and @CaimingXiong for their help and support. It has been truly humbling and rewarding to be a part of @stanfordnlp , @MetaMindIO , and @salesforce . See you soon, friends!

5

8

101

@hllo_wrld

Victor Zhong

5 years

I'm excited to announce our work w/ @CaimingXiong @StrongDuality & @RichardSocher Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answering, which obtains SOTA results on @uclmr 's Qangaroo WikiHop! See you @iclr2019 ! #NLProc

Tweet card media

Coarse-grain Fine-grain Coattention Network for Multi-evidence...

End-to-end neural models have made significant progress in question answering, however recent studies show that these models implicitly assume that the answer and evidence appear close together in...

4

31

100

@hllo_wrld

Victor Zhong

2 years

I finally cleaned up the docs for This basically merges @PyTorchLightnin @raydistributed and to boilerplate #nlproc experiments very quickly, with @weights_biases , custom S3 logs/plots, slurm sweeps etc. RL via Moolib coming soon!

A framework for elegantly configuring complex applications

5

14

97

@hllo_wrld

Victor Zhong

3 years

Many prior works in language grounding study single environments. How do we build unified techniques that apply across multiple environments? Our #NeurIPS2021 paper proposes the multi-environment Symbolic Interactive Language Grounding benchmark (SILG).

1

29

97

@hllo_wrld

Victor Zhong

4 years

Our #emnlp2020 paper Grounded Adaptation for Zero-shot Semantic Parsing proposes GAZP, a framework for zero-shot language-to-SQL parsing by synthesizing data in new DBs after reading their schema. 💡 Paper 📰 Thread 👇1/9 #NLProc #MachineLearning

Tweet media one

2

16

90

@hllo_wrld

Victor Zhong

7 years

We are back! DCN+: new single model state of the art for @stanfordnlp 's #QuestionAnswering #DeepLearning #nlproc

Tweet media one

3

35

86

@hllo_wrld

Victor Zhong

5 years

Our #acl2019nlp paper Entailment-driven Extracting and Editing for Conversational Machine Reading (E3) is out! E3 studies conversational machine reading (CMR), a task oriented dialogue problem where reasoning rules aren't fixed but implied by procedural text. Paper/code👇1/10

Tweet media one

2

15

83

@hllo_wrld

Victor Zhong

3 years

I’m very impressed with @openreviewnet handling last minute @NeurIPSConf submissions without slowing down at all. Can we move on from Softconf now??

1

3

82

@hllo_wrld

Victor Zhong

2 years

One thing that I really appreciate is how so many junior faculty paid for students w/o presentations to come to #NAACL2022 . Meeting & getting to know my peers has been one of the most rewarding aspects of academia. COVID has deprived a generation of students of this opportunity.

0

2

79

@hllo_wrld

Victor Zhong

5 years

I had a brilliant 😉 time interning at @facebookai research London - one of the best places for #nlproc + #ReinforcementLearning research. A huge thank you to @egrefen @_rockt and @riedelcastro for having me there!

@_rockt

Tim Rocktäschel

5 years

Fantastic work by Victor Zhong ( @hllo_wrld ) during his internship at @FacebookAI Research London. Procedurally generating environment dynamics and their textual descriptions forces the agent to perform multi-hop reading comprehension. Paper: w/ @egrefen

Tweet media one

5

38

172

1

6

67

@hllo_wrld

Victor Zhong

3 years

Reading reviews from co-reviewers and I just want to say: not every component of the model must be new. Not every single model must be novel. This is one of the frustrations we must deal with with neural nets because there are infinite ways of combining differentiable functions.

1

2

69

@hllo_wrld

Victor Zhong

3 years

Thanks @Apple ! I am honoured and grateful for this fellowship. I would not have received this fellowship without support from my awesome advisor @LukeZettlemoyer and the excellent research institution that is @uwcse .

@uwcse

Allen School

3 years

#UWAllen Ph.D. student @hllo_world in the @uwnlp was named an @Apple Scholar in #AI & #ML to teach machines to generalize by reading natural language specifications and make virtual assistants like #Siri smarter.

Tweet media one

10

14

116

3

3

66

@hllo_wrld

Victor Zhong

6 years

Really cool paper by @JonathanBerant and student on efficient QA over long documents represented as trees. Great idea and very well written! #NLProc

Tweet card media

Learning to Search in Long Documents Using Document Structure

Reading comprehension models are based on recurrent neural networks that sequentially process the document tokens. As interest turns to answering more complex questions over longer documents,...

2

22

67

@hllo_wrld

Victor Zhong

7 years

Switched to a dynamic #deeplearning framework? @ChainerOfficial or @pytorch ? Checkout for experiment monitoring.

3

31

65

@hllo_wrld

Victor Zhong

2 years

I had a fantastic time presenting our work on reading to generalize at the @LTIatCMU colloquium last Friday! The talk is now up at .

Tweet media one

2

10

63

@hllo_wrld

Victor Zhong

2 years

I will be at #NAACL2022 in Seattle and giving my first in person talk in 2 years! Message me if you want to meet up! The talk is titled “Reading to Learn”, happening Friday July 15 2pm at the Multimodal Workshop. I’m also going on the job market this year! Let’s chat! #nlproc

1

3

60

@hllo_wrld

Victor Zhong

2 years

If you are attending #NeurIPS2022 or #emnlp2022 I would love to chat with you (please email). 4 of my papers and collaborations on reading to learn will be presented at @NeurIPSConf and @emnlpmeeting . They are 🧵

@hllo_wrld

Victor Zhong

2 years

I am on the job market this year for academic and research positions - please share broadly! My research is on reading to learn: instead of learning specific problems, how can we learn to interpret language to generalize to new problems? More at #nlproc

1

30

125

4

5

55

@hllo_wrld

Victor Zhong

3 years

So I finally tried @raydistributed - it is **fast**! Built a simple lib to preprocess data. Here's an example of parallel parsing with @stanfordnlp Stanza. I'm seeing 2x speed on laptop w/ toy text + 3 procs. Different large job on server is 100x faster!

2

5

53

@hllo_wrld

Victor Zhong

5 years

@radamihalcea 2019 baseline should be BERT

0

1

49

@hllo_wrld

Victor Zhong

2 years

Just registered for @naacl 2022 - my first in person conference in 2.5 years! Who’s coming to Seattle?? Let’s catch up!!

7

0

50

@hllo_wrld

Victor Zhong

1 year

Our work on Reading to Learn, along with terrific work from @AnimaAnandkumar and @karthik_r_n was recent featured in @QuantaMagazine ! By far the most professional interactions I've had with a news org - a lot of work put into fact checking+editing.

Tweet card media

Machines Learn Better if We Teach Them the Basics | Quanta Magazine

A wave of research improves reinforcement learning algorithms by pre-training them as if they were human.

www.quantamagazine.org

1

11

46

@hllo_wrld

Victor Zhong

3 years

OMG I finally got my first primary contributor patent approved!! On the one hand this is pretty mundane but on the other hand it feels like one of those immigrant story moments. 😅 Cheers to the good times @CaimingXiong @RichardSocher @SFResearch !

Tweet media one

0

0

45

@hllo_wrld

Victor Zhong

3 years

Fantastic to have @Thom_Wolf speak at @uwnlp today! Many exciting things happening at @huggingface - BigScience is such a massive and important undertaking and I cannot wait to see what will happen! Also it has been so exciting to see the growth of @huggingface over the years!!

1

1

44

@hllo_wrld

Victor Zhong

8 years

Our model gets SotA on @stanfordnlp 's SQuAD against AI2, MSR, IBM, Google, and others! @CaimingXiong @RichardSocher

Tweet media one

0

15

42

@hllo_wrld

Victor Zhong

2 years

You know what feels better than getting good convergence? Getting good annotations. Building a dataset right now and boy do I enjoy seeing these good annotations come in.

2

8

42

@hllo_wrld

Victor Zhong

5 years

I'm very excited to share my first work @uwnlp - we have two papers accepted to @ACL2019_Italy !! Thanks to my fantastic advisor @LukeZettlemoyer and collaborators @sewon__min and @HannaHajishirzi . Stay tuned for paper and code release! #NLProc

2

1

42

@hllo_wrld

Victor Zhong

5 years

@BBCWorld What a great leader

2

0

34

@hllo_wrld

Victor Zhong

6 years

I, @sewon__min , and @RichardSocher will be presenting two posters tomorrow at @acl2018 on dialogue state tracking ( ) and efficient question answering (). Come check out our work at 12:30! #nlproc

Tweet card media

Efficient and Robust Question Answering from Minimal Context over Documents

Neural models for question answering (QA) over documents have achieved significant performance improvements. Although effective, these models do not scale to large corpora due to their complex...

1

13

41

@hllo_wrld

Victor Zhong

7 years

@stanfordnlp @CaimingXiong @RichardSocher @salesforce Our DCN+ ensemble is now state of the art on @stanfordnlp 's ! #QuestionAnswering #DeepLearning #nlproc #tugowar

Tweet media one

2

18

36

@hllo_wrld

Victor Zhong

6 years

If you squint, transformer is like a densely connected factor graph. Network depth approximates the number of rounds of loopy belief propagation.

2

5

37

@hllo_wrld

Victor Zhong

4 years

The paper and videos for Language in Reinforcement Learning #ICML2020 workshop is now online! Check it out at . Also please join us this Saturday for exciting invited talks and posters!

0

9

38

@hllo_wrld

Victor Zhong

2 years

If you work in #nlproc I highly recommend that you design some sort of project that involves raw Wikipedia or wikidata. You really come face to face with this vast accumulation of human knowledge and it’s honestly very humbling despite all its flaws.

1

2

38

@hllo_wrld

Victor Zhong

5 years

There are no shortcuts to learning. Inspirational YouTube videos do not replace 10 years of practice. The ML “education” hype reminds of the predatory iOS and mobile game bootcamps from the 2000’s, except now global instead of relatively confined to the Bay Area.

@AndrewM_Webb

Andrew M. Webb

5 years

So in @sirajraval 's livestream yesterday he mentioned his 'recent neural qubit paper'. I've found that huge chunks of it are plagiarised from a paper by Nathan Killoran, Seth Lloyd, and co-authors. E.g., in the attached images, red is Siraj, green is original

Tweet media one

Tweet media two

193

1K

4K

1

2

33

@hllo_wrld

Victor Zhong

4 years

I’m happy to chat at #emnlp2020 about my research on reading to generalize as well as @uwnlp ! Feel free to reach out on rocket chat or email. I find these chats especially helpful at virtual confs. I’m currently in two productive collaborations that resulted from these meetings.

1

1

33

@hllo_wrld

Victor Zhong

8 years

#Docker container for running @stanfordnlp CoreNLP server: #NLP #MachineLearning

0

4

29

@hllo_wrld

Victor Zhong

6 years

Efficient and Robust Question Answering from Minimal Context over Documents w/ first author @sewon__min , @CaimingXiong , and @RichardSocher

Tweet card media

Efficient and Robust Question Answering from Minimal Context over Documents

Neural models for question answering (QA) over documents have achieved significant performance improvements. Although effective, these models do not scale to large corpora due to their complex...

0

13

29

@hllo_wrld

Victor Zhong

1 year

Had super exciting discussions about reading to learn + language grounding at #NeurIPS2022 ! I’m at #emnlp2022 Dec 7-12 for works led by @machelreid , @TianbaoX , @ChenHenryWu . Please DM or email to chat! I am on the job market and would love to discuss opportunities as well!

@hllo_wrld

Victor Zhong

2 years

If you are attending #NeurIPS2022 or #emnlp2022 I would love to chat with you (please email). 4 of my papers and collaborations on reading to learn will be presented at @NeurIPSConf and @emnlpmeeting . They are 🧵

4

5

55

0

5

27

@hllo_wrld

Victor Zhong

5 years

I will be presenting Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answering @iclr2019 on May 9th 11am-1pm. Hope to see you there! The 6-month-old CFC is still the top public model! paper: leaderboard:

Tweet card media

Coarse-grain Fine-grain Coattention Network for Multi-evidence...

End-to-end neural models have made significant progress in question answering, however recent studies show that these models implicitly assume that the answer and evidence appear close together in...

@hllo_wrld

Victor Zhong

5 years

I'm excited to announce our work w/ @CaimingXiong @StrongDuality & @RichardSocher Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answering, which obtains SOTA results on @uclmr 's Qangaroo WikiHop! See you @iclr2019 ! #NLProc

4

31

100

0

0

24

@hllo_wrld

Victor Zhong

5 years

@stanfordnlp @StanfordAILab I am actually so excited about this. This has been discussed and in the works for soooooo long. People waaay under-appreciate the effort required to maintain large software tools for so many years in a graduate research lab with students who rotate in and out of the program.

1

2

25

@hllo_wrld

Victor Zhong

2 years

#NAACL2022 stragglers: some personal favourites for spending the weekend in Seattle, a thread. Places: Ballard, Ballard Locks, Discovery Park, Golden Gardens, Myrtle Edwards, Gas Works, Green Lake, Arboretum, Carkeek

1

2

24

@hllo_wrld

Victor Zhong

5 years

Long time coming but here it is! Huge thanks to my friend and coauthor @yuhaozhangx !

@stanfordnlp

Stanford NLP Group

5 years

The TACRED dataset—person/organization relations for training relation extraction systems—is available from LDC! (At last—sorry for the delays, etc.; $25 for non-members.) See more in our papers: and

Tweet media one

2

23

64

0

2

23

@hllo_wrld

Victor Zhong

6 years

Global-Locally Self-Attentive Encoder for Dialogue State Tracking w/ @CaimingXiong and @RichardSocher

Tweet card media

Global-Locally Self-Attentive Dialogue State Tracker

Dialogue state tracking, which estimates user goals and requests given the dialogue context, is an essential part of task-oriented dialogue systems. In this paper, we propose the Global-Locally...

2

8

22

@hllo_wrld

Victor Zhong

5 years

While in London this summer, I’ve been using a British keyboard and have finally changed my ze’s to se’s. No longer will reviewer 2 have to point out that this confused Canadian keeps mixing American spelling with British spelling.

1

0

23

@hllo_wrld

Victor Zhong

6 years

Full house here at the Reading Comprehension Workshop @acl2018 for @RichardSocher 's talk on multitask learning for NLP!

Tweet media one

Tweet media two

1

3

22

@hllo_wrld

Victor Zhong

1 year

The number of Tim Hortons in Abu Dhabi is incredible! #EMNLP2022

Tweet media one

Tweet media two

1

1

22

@hllo_wrld

Victor Zhong

5 years

I will be presenting our work E3: Entailment-driven Extracting and Editing for Conversational Machine Reading today at 4pm at poster #7 . Please come check it out! #ACL2019 #nlproc @ACL2019_Italy

@hllo_wrld

Victor Zhong

5 years

Our #acl2019nlp paper Entailment-driven Extracting and Editing for Conversational Machine Reading (E3) is out! E3 studies conversational machine reading (CMR), a task oriented dialogue problem where reasoning rules aren't fixed but implied by procedural text. Paper/code👇1/10

Tweet media one

2

15

83

0

4

21

@hllo_wrld

Victor Zhong

11 months

💪💪💪 if you wanna do a PhD in NLP, definitely apply @UWCheritonCS , we’ve got quite the group! @fredahshi @WenhuChen @lintool

@yuntiandeng

Yuntian Deng

11 months

Excited to share that I'm joining @UWCheritonCS as an Assistant Professor and @VectorInst as a Faculty Affiliate in Fall '24. Before that, I'm doing a postdoc at @allen_ai with @YejinChoinka . Immensely grateful to my PhD advisors @srush_nlp and @pmphlt . This journey wouldn't have

49

19

334

2

2

20

@hllo_wrld

Victor Zhong

4 years

As a first time TA, it feels wonderful to receive a shout out from students. Also makes me appreciate the great TAs I've had over the years.

0

0

19

@hllo_wrld

Victor Zhong

4 years

A Haiku: each hour I refresh / only to find again that / nothing new happened

3

0

20

@hllo_wrld

Victor Zhong

6 years

I think Melbourne may be more hipster than SF

0

5

20

@hllo_wrld

Victor Zhong

3 years

If you’re looking for a quick stats refresher, this StatQuest YouTube channel by @joshuastarmer is both succinct and entertaining!

1

0

19

@hllo_wrld

Victor Zhong

2 years

I finally got access to DALL-E. Late to the party - I know. First impression is that it generates amazing images, but it doesn't really understand compositional language. Here are "a woman proposing to a man" and "a car on top of a man". Great progress, but lots more to do.

Tweet media one

Tweet media two

6

0

18

@hllo_wrld

Victor Zhong

4 years

I was looking through old photos today and realized that among the many things that didn’t happen this year is the @stanfordnlp BBQ 😟

1

1

18

@hllo_wrld

Victor Zhong

3 years

Machel @machelreid is one of the most productive people I have collaborated with. He should definitely be in your top 18 under 18 list 😉 PhD programs: you may want to start your recruiting process now!

@machelreid

Machel Reid

3 years

I'm happy to announce that "LEWIS: Levenshtein Editing for Unsupervised Text Style Transfer" has been accepted to #ACL2021NLP (Findings)! This would have not been possible without my amazing co-author @hllo_wrld ! Preprint will be out soon!

0

8

75

0

2

19

@hllo_wrld

Victor Zhong

5 years

Does anyone know the reason behind removing rebuttals from *ACL? Was there ever a public discussion about this somewhere? @acl2018 @NAACLHLT @emnlp2019 #NLProc

0

1

18

@hllo_wrld

Victor Zhong

4 years

Our @iclr_conf poster sessions will be this Thursday 5-7am GMT / 10pm-12am PDT during Session 1 and 5-7pm GMT / 10pm-12am PDT during Session 4. More details here: Hope to see you there!

@hllo_wrld

Victor Zhong

4 years

Super excited to share our @iclr_conf 2020 work RTFM: Generalising to Novel Environment Dynamics via Reading ()! Joint work w/ @_rockt and @egrefen at @facebookai research London on RL policies that generalise to new envs via reading! 1/3 👇

Tweet media one

Tweet media two

2

30

144

0

3

19

@hllo_wrld

Victor Zhong

1 year

Happy holidays!! We’ve successfully escaped to sunny LA. Our @AlaskaAir flight got cancelled and then fortunately uncancelled (didn’t know this was possible) 😅 Super glad to be out of the #seattleicestorm

0

0

18

@hllo_wrld

Victor Zhong

2 years

I find it difficult to believe that @Tim_Dettmers still manages to improve this already-terrific post for choosing a PhD program. I think every answer I've ever given to "what advice do you have for choosing a PhD program" is found here.

@Tim_Dettmers

Tim Dettmers

2 years

An important but elusive quality to learn in a PhD is research style. It is valuable to be aware of this before you start a PhD. Among other updates, I added an extensive discussion on research style to my "choosing a grad school" blog post. Enjoy!

4

36

188

0

0

18

@hllo_wrld

Victor Zhong

4 years

I will be presenting this work next Tuesday at the @MSFTResearch AI Breakthroughs workshop. Hope to see you there!

@hllo_wrld

Victor Zhong

4 years

Our #emnlp2020 paper Grounded Adaptation for Zero-shot Semantic Parsing proposes GAZP, a framework for zero-shot language-to-SQL parsing by synthesizing data in new DBs after reading their schema. 💡 Paper 📰 Thread 👇1/9 #NLProc #MachineLearning

Tweet media one

2

16

90

0

0

18

@hllo_wrld

Victor Zhong

7 years

Dashboard ready for #deeplearning , @PyTorch , @ChainerOfficial exps! Now w/ @vuejs , bulma, multi-exp, config filter:

0

7

17

@hllo_wrld

Victor Zhong

7 years

TACRED w/ a nomination for best resource paper at #emnlp2017 ! Try it out for your next relation extraction task!

Tweet media one

Tweet media two

Tweet media three

Tweet media four

1

9

17

@hllo_wrld

Victor Zhong

4 years

Just did 4 shots of vaccinations for #iclr2020 😆 This finally forced me to get my vaccination history into one system

1

0

17

@hllo_wrld

Victor Zhong

3 years

TAing during COVID: I feel like I'm moderating a panel during office hours.

0

1

17

@hllo_wrld

Victor Zhong

5 years

I have updated #WikiSQL to include a new leaderboard for weakly supervised models! Currently the top model is MAPO by Liang, @Mo_Norouzi , @JonathanBerant , @quocleix & Lao. If you know of any other weakly supervised work, please let me know! #NLProc

1

5

17

@hllo_wrld

Victor Zhong

5 years

The worst flight ever: delayed at @Gatwick_Airport for 10 hours by 30 minute increments, when @vueling knew that the flight would have been late by at least 5 hours.

1

5

16

@hllo_wrld

Victor Zhong

3 years

I’ve released the source code at !

Tweet card media

GitHub - vzhong/gazp: Source code for Grounded Adaptation for Zero-shot Executable Semantic Parsing

Source code for Grounded Adaptation for Zero-shot Executable Semantic Parsing - vzhong/gazp

@hllo_wrld

Victor Zhong

4 years

Our #emnlp2020 paper Grounded Adaptation for Zero-shot Semantic Parsing proposes GAZP, a framework for zero-shot language-to-SQL parsing by synthesizing data in new DBs after reading their schema. 💡 Paper 📰 Thread 👇1/9 #NLProc #MachineLearning

Tweet media one

2

16

90

0

0

16

@hllo_wrld

Victor Zhong

1 year

Before I start at @UWCheritonCS , I will be in NYC with @MSFTResearch as a postdoc, where I will work on RL + NLP. If you are in NYC or Toronto and want to get in touch, please reach out!

1

0

14

@hllo_wrld

Victor Zhong

2 years

Great work by @jayelmnop !!! Language descriptions of state space seems like a promising way to remove noise and reduce spurious correlations. Super excited about more work in this area!

@jayelmnop

Jesse Mu

2 years

Excited to share my work from my internship at @MetaAI : improving exploration in RL with language abstractions! Paper: 🧵 (1/8)

5

48

289

1

2

16

@hllo_wrld

Victor Zhong

1 year

@hmkyale @YaleSEAS @dragomir_radev @Yale @YINSedge @YaleCompsci Very sad & sorry to hear this… I had corresponded with Drago as recently as 10 days ago regarding using figures from my work for his book. We then caught up and he wished me good luck for my job search. He has always been so kind and gracious, especially to junior researchers.

0

0

16

@hllo_wrld

Victor Zhong

4 years

I gotta say the #emnlp2020 auto caption is pretty good! however it seems to never get the word "parser". There are also very very rare & funny problems like this one. For the record, no LSD was purchased as a part of our work on GAZP . #NLProc

Tweet media one

0

0

14

@hllo_wrld

Victor Zhong

5 years

2. Multi-hop Reading Comprehension through Question Decomposition and Rescoring w/ the wonderful first author @sewon__min , @LukeZettlemoyer , and @HannaHajishirzi , where we propose a new technique for multi-hop QA by decomposing natural language questions.

1

1

15

@hllo_wrld

Victor Zhong

2 years

Thank you for having me @UBC_NLP !! Super excited to visit!

@UBC_NLP

UBC NLP Group

2 years

We are excited to host @hllo_wrld from @uwnlp for an in-person talk titled "M2RQA: A benchmark for multi-evidence, multi-answer, robust QA". Join us on Wednesday Sep 14 at 12pm @ ICICS X836! @UBCLangScis @CAIDA_UBC @UBC_CS

Tweet media one

0

8

15

0

0

15

@hllo_wrld

Victor Zhong

6 years

@BMarcusMcCann @chrmanning I hope I don't misquote but: empirically, some of the most influential research are produced by universities; it does not seem the case that good research necessarily requires better tech+more resources, otherwise universities would have ceased to exist a long time ago.

0

9

14

@hllo_wrld

Victor Zhong

4 years

Here’s to all my friends in California - hope you are well and safe from the virus and the fires!

1

0

13

@hllo_wrld

Victor Zhong

1 year

I have had a wonder 5 years at @uwcse . I am tremendously grateful to my advisor @LukeZettlemoyer for his help in my journey - I could not have imagined a better advisor. I also want to thank @uwnlp and my office mates in CSE318. I hope our paths cross often in the future!

1

0

14

@hllo_wrld

Victor Zhong

3 years

@xtimv my brother also works in IT

0

0

14

@hllo_wrld

Victor Zhong

5 years

1. E3: Entailment-driven Extracting and Editing for Conversational Machine Reading w/ @LukeZettlemoyer , where we achieve SOTA on @uclmr 's conversational machine reading task () by modeling latent rules in text & entailment through dialogue.

1

0

13

@hllo_wrld

Victor Zhong

4 years

I’m super excited to see the work the team has done since our initial WikiSQL paper 4 (!) years ago!!

@VictoriaLinML

Victoria X Lin

4 years

Talk to your databases -- Photon 🌌 v1.1 is here! What's new? - A dual input mode that accepts both NL and SQL queries - Enhanced GUI with more test databases - New blog post Blog post: Live demo: ArXiv:

7

42

142

0

2

13

@hllo_wrld

Victor Zhong

7 years

At @emnlp2017 for our work on relation extraction w/ @yuhaostanford & @stanfordnlp ! Come see the oral Sat @10 :30!

0

6

13

@hllo_wrld

Victor Zhong

5 years

Paper: Dockerized code: 10/10 #nlproc #ACL2019NLP #DeepLearning

Tweet card media

GitHub - vzhong/e3: Dockerized code for E3: Entailment-driven Extracting and Editing for Conversa...

Dockerized code for E3: Entailment-driven Extracting and Editing for Conversational Machine Reading. - vzhong/e3

1

5

11

@hllo_wrld

Victor Zhong

4 years

Please consider submitting your work on semantic parsing! #NLProc

@intexsempar2020

Interactive and Executable Semantic Parsing

@intexsempar2020

4 years

How do we turn natural language instructions💬 into programs executable by machines 🤖? Join us at the first workshop on interactive and executable semantic parsing (IntEx-SemPar) Nov 19 at @emnlp2020 ! Call for paper at ! Deadline Aug 14🗓️

2

11

32

0

0

13

@hllo_wrld

Victor Zhong

4 years

Sincere thanks to our friends and colleagues @UWVirology , y’all are the real doctors and we appreciate you very much! #seattlecoronavirus

0

0

12

@hllo_wrld

Victor Zhong

6 years

❤️❤️❤️

@stanfordnlp

Stanford NLP Group

6 years

People usually get information from others in a multi-turn conversation. To approach this, we’ve released CoQA 🍃—A Conversational Question Answering Challenge by @sivareddyg • @danqi_chen • @chrmanning . 127K Qs— free-form answers—with evidence—multi-domain.

Tweet media one

Tweet media two

6

216

457

0

1

12

@hllo_wrld

Victor Zhong

5 years

I will present this work tomorrow at 11am at @iclr2019 ! Come say hi at poster #5 ! The CFC is still the top public model after 8 months! #NLProc

@hllo_wrld

Victor Zhong

5 years

I'm excited to announce our work w/ @CaimingXiong @StrongDuality & @RichardSocher Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answering, which obtains SOTA results on @uclmr 's Qangaroo WikiHop! See you @iclr2019 ! #NLProc

4

31

100

0

0

12

@hllo_wrld

Victor Zhong

4 years

Do you use #slurm and #Python ? Here's a Python slurm launcher

GitHub - vzhong/slrm: python library to submit slurm jobs

python library to submit slurm jobs. Contribute to vzhong/slrm development by creating an account on GitHub.

2

0

11

@hllo_wrld

Victor Zhong

4 years

@Tim_Dettmers When will you start making your own GPUs Tim, I’d like to preorder

1

0

12

@hllo_wrld

Victor Zhong

2 years

After living here for a decade I still don't understand America. Why is the state to be able to regulate someone going to the hospital to do something to THEIR OWN BODY and not regulate weapons in public? Where is the boundary b/w fed and state and individuals?

0

0

11

@hllo_wrld

Victor Zhong

7 years

I spy ICLR papers on #WikiSQL ! If you'd like results to show up on , please send pull request (after ICLR review)! 🙌

0

3

12

@hllo_wrld

Victor Zhong

4 years

@Tim_Dettmers Recommended reading if you are considering grad school!! FWIW, @Tim_Dettmers @sewon__min @AkariAsai @wittgen_ball @yizhongwyz and I make up our office @uwnlp 😁 It's a fun time for sure!

0

1

10