Freda Shi @fredahshi Twitter profile

Pinned Tweet

Freda Shi

27 days

🚨Long thread warning: excited to share that I defended my PhD thesis earlier in May! Here's my thesis, Learning Language Structures through Grounding: 1/

30

11

298

Last Seen Profiles

@unilightwf

@Lindsay_13

@AXXXMVII

@zionwrld

@SupRm_Nova

@visualkei_art

@Quriash911

@Myra86379693895

@AShuqrat

@Iukman2

@stwmaniax

@marmara1883

@DavidElle9

@joejonas

@SilverWaveMedia

@vivaciouss01

@CarlosA88119991

@DavidBeck4

@BinorRaja

@bapuchi1986

@StalkingVi96051

@jiwooxng

@CumhurErdeniz1

@sngminaziee

@crofts

@Empathiie169271

@RynWeaver

@seatawin

@cpane94

@FestaUnitaBO

@CheckpointSteve

@pengen_stw

@NezoNezooo

@kaisen0217

@Softtechas

@Edgyaludon

Freda Shi

@fredahshi

1 year

Personal update: I'll be starting in July 2024 as an Assistant Professor @UWCheritonCS and a Faculty Member @VectorInst ! Looking forward to working with all the amazing folks! Prospective students: if you are interested in NLP and/or comp. linguistics, please consider applying!

33

20

322

Freda Shi

@fredahshi

2 years

Large language models show reasoning abilities in English with chain-of-thought prompting - how are their multilingual reasoning abilities? New preprint📄: Language models are multilingual chain-of-thought reasoners. (1/n)

5

53

274

Freda Shi

@fredahshi

3 years

Honored to receive the 2021 Google PhD fellowship in natural language processing. Thanks @GoogleAI for the support! Kudos to my advisors and mentors: thanks for teaching me everything over the past years, and for showing me concrete examples of best researchers---yourselves!

Google AI

@GoogleAI

3 years

Continuing our tradition of supporting outstanding graduate students in their pursuit of research in computer science and related fields, we congratulate our 13th annual PhD Fellowship Program recipients! See the list of 2021 Fellowship recipients below:

15

52

419

9

4

181

Freda Shi

@fredahshi

8 months

🚨(Not Really) Old Paper Alert🚨: sharing our 2-year-old NeurIPS paper that I’m still quite excited about. We learn grounded, neuro-symbolic CCGs from multi-modal data and demonstrate nearly perfect compositional generalization to unseen sentences and scenes. (1/)

2

17

108

Freda Shi

@fredahshi

2 years

Late post but let’s do this! Happy to share our #EMNLP2022 work on translating natural language to executable code with execution-aware minimum Bayes risk decoding 📝Paper: 📇Code: 📦Data (codex output): (1/n)

3

20

102

Freda Shi

@fredahshi

4 years

Just got a paper w/ scores 4, 4, 4 rejected by #acl2020nlp , but the comments from the meta-reviewer and all reviewers are super, super constructive. Would like to say thank you to them all!

1

93

Freda Shi

@fredahshi

2 years

Though time it quite limited, I'm happy to spend most of my weekend reviewing for #iclr2023 - my assigned papers are all interesting, carefully written and relevant (to me), as most ICLR papers I've reviewed before - kudos to the ICLR matching system (and my ACs)!

1

0

39

Freda Shi

@fredahshi

1 year

#ACL2023 attendees: Welcome to Canada! 🇨🇦 I'll be at the conference from Monday to Wednesday. First time attending a conference without presenting a paper, and I’m sure I’ll enjoy all the cool presentations. Old & new friends: please don’t hesitate to come & say hi!

1

0

38

Freda Shi

@fredahshi

9 months

Looking forward to visiting tomorrow!

MichiganAI

@michigan_AI

9 months

📢Delighted to host @fredahshi 's #AI Seminar on "Learning Syntactic Structures from Visually Grounded Text and Speech"! TOMORROW, OCT. 24 @ 4pm ET:

0

2

30

1

36

Freda Shi

@fredahshi

8 months

Yes, we are looking for PhD students at Waterloo! Come join us — apply by Dec 1!

Yuntian Deng

@yuntiandeng

8 months

I am hiring NLP/ML PhD students at UWaterloo, home to 5 NLP professors! Apply by Dec 1 Strong consideration will be given to those who can tackle the below challenge: Can we use LM's hidden states to reason multiple problems simultaneously? Retweets/shares appreciated🥰

12

133

486

1

0

36

Freda Shi

@fredahshi

2 years

Finally, I'll be presenting this work at EMNLP 2022 in person! Cannot wait to meet old and new friends - come and say hi!

Freda Shi

@fredahshi

2 years

Late post but let’s do this! Happy to share our #EMNLP2022 work on translating natural language to executable code with execution-aware minimum Bayes risk decoding 📝Paper: 📇Code: 📦Data (codex output): (1/n)

3

20

102

0

4

32

Freda Shi

@fredahshi

2 years

This has been one of the most exciting posters I’ve visited at EMNLP2022. Neat results showing syntax and semantics are learnably separated in spectrums!

Max

@mxmeij

2 years

For #EMNLP2022 , we (w/ @robvanderg , @barbara_plank ) look through differentiale, rainbow-colored glasses to find linguistic timescale profiles for 7 #NLProc tasks across 6 languages 🌈 📑 📽️ 💬 10th Dec 9:00 at Poster Session 7 & 8

1

3

28

0

21

Freda Shi

@fredahshi

5 months

Are there any resource/study showing which words (in any language) are more likely to be mispronounced (by either native speakers or L2 learners)? Any pointer is appreciated!

2

0

17

Freda Shi

@fredahshi

1 year

I very much enjoyed this paper, and of course, the poster! Large-sized data and LLMs present a fantastic opportunity for studying cultural differences.

Emmy Liu

@_emliu

1 year

"आज-कल NLP Research के साथ बने रहना उतना ही आसान है जितना कि मानसून मॆं भीगने से बचे रहना!" . Did you understand? How about LMs? Our #ACL2023 Findings paper explores multilingual models' cultural understanding through figurative language in 7 langs 🌎(1/9)

5

39

204

2

0

17

Freda Shi

@fredahshi

3 years

And she feels so lucky to be a student at @TTIC_Connect ;)

TTIC

@TTIC_Connect

3 years

Third-year PhD student Freda Shi bridges the gap between linguistics and computer science in her natural language processing research. Follow the link to learn more: #computerscience #womeninstem

0

1

9

1

0

15

Freda Shi

@fredahshi

1 year

If you're at ICML, chat with @xinyun_chen_ on this paper in the poster session 3 11am tomorrow!

David Dohan

@dmdohan

1 year

Come by the 11am posters on Wednesday to learn how irrelevant context effects LLMs:

1

0

20

0

1

14

Freda Shi

@fredahshi

2 years

Surprisingly, PaLM-540B shows decent multilingual reasoning ability, solving >40% problems in any of the 10 investigated languages, including the underrepresented ones (such as Bengali and Swahili) that only cover <0.01% tokens of the pretraining data. (3/n)

1

2

15

Freda Shi

@fredahshi

2 years

Back to 2017, when thinking about visually grounded syntax induction (), I dreamed for 1 second if we could parse image in similar ways---apparently it's too difficult for me then (and now), so, super excited to see this! Congrats on the nice work!

Xiaolong Wang

@xiaolonw

2 years

Introducing #CVPR2022 GroupViT: Semantic Segmentation Emerges from Text Supervision 👨‍👩‍👧 Without any pixel label ever, Our Grouping ViT can group pixels bottom-up to open vocabulary semantic segments. The only training data is 30M noisy image-text pairs.

4

128

644

0

14

Freda Shi

@fredahshi

2 years

Again, welcome to check out our paper and dataset for more details! Paper📄: Data💾: (8/n)

GitHub - google-research/url-nlp

Contribute to google-research/url-nlp development by creating an account on GitHub.

github.com

1

0

13

Freda Shi

@fredahshi

1 year

In the coming year, I'll finish my PhD @TTIC_Connect , and visit @roger_p_levy . Huge thanks to my advisors @kevingimpel and Karen, my mentors @LukeZettlemoyer , @sidawxyz and @denny_zhou , and everyone who helped me along the way!

1

0

13

Freda Shi

@fredahshi

3 years

Same here. Even worse: I feel I'm probably not qualified to review some of them -- no experience in this domain, not quite familiar with recent work, no labmates or close friends working on it -- while relevant papers (I thought) were not assigned to me.

Yufang Hou

@yufanghou

3 years

Got 5 papers to review for ARR today, all from different AEs, the due date is Dec 16! Logged into the system, there's no option to reject the assignment or discuss with AEs to extend the deadline/find a replacement. I wonder what's the average review load for Nov🤔 @ReviewAcl

16

1

56

1

12

Freda Shi

@fredahshi

2 years

In this work, we introduce the Multilingual Grade School Math (MGSM) dataset, by manually translating 250 English GSM8K test examples to 10 typologically diverse languages, and investigate language models’ reasoning ability with it. (2/n)

1

0

11

Freda Shi

@fredahshi

2 years

1. Chain-of-thought prompting is essential for the reasoning performance for both GPT-3 and PaLM; and notably, reasoning steps in English (EN-CoT) almost always outperform the ones in the same language as the problem (Native-CoT). (5/n)

1

11

Freda Shi

@fredahshi

5 years

I'll be talking about Visually Grounded Neural Syntax Acquisition, one of the listed papers, on Monday 4:00 pm at Session 3E! This is a joint work with Jiayuan Mao, @kevingimpel and Karen Livescu. Paper: Project page:

Visually Grounded Neural Syntax Acquisition

We present the Visually Grounded Neural Syntax Learner (VG-NSL), an approach for learning syntactic representations and structures without any explicit supervision. The model learns by looking at...

arxiv.org

ACL2019

@ACL2019_Italy

5 years

We are delighted to announce the list of papers that have been nominated as candidates for ACL 2019 Best Paper Awards! Check the list at #acl2019nlp

1

34

168

0

1

10

Freda Shi

@fredahshi

27 days

2 great surveys centered around the above 2 senses of grounding, respectively: In the Harnad (1990) sense, , by @ybisk , @universeinanegg , @_jessethomason_ and colleagues In the Clark & Brennan (1991) sense, , by folks incl. @ybisk 4/

1

0

10

Freda Shi

@fredahshi

27 days

In my thesis, I discuss a family of tasks: learning language structures from supervision in other sources (through grounding) and corresponding methods to deal with each considered task. As many have recognized, grounding is a highly ambiguous term. More in 🧵 2/

1

0

10

Freda Shi

@fredahshi

2 years

Joint work with Mirac Suzgun, @markuseful , Xuezhi Wang, Suraj Srivats, @CrashTheMod3 , @hwchung27 , @yitayml , @seb_ruder , @denny_zhou , @dipanjand , @_jasonwei (9/9)

0

9

Freda Shi

@fredahshi

27 days

Prior work has mainly categorized grounding into 2 types: semantic grounding (finding meanings for forms; Harnad, 1990) and communicative grounding (finding common ground in dialogue; Clark and Brennan, 1991 + earlier work in pragmatics). 3/

1

0

10

Freda Shi

@fredahshi

2 years

The multilingual reasoning abilities of language models also extend to other tasks: on XCOPA, a multilingual commonsense reasoning dataset, PaLM-540B sets a new state of the art (89.9% average accuracy) using only 4 examples, outperforming the prior best by 13.8%. (7/n)

1

0

10

Freda Shi

@fredahshi

27 days

An interesting and counterintuitive example of grounding under this formalization is GroupViT by @Jerry_XU_Jiarui , @xiaolonw , and folks, where an image segmentation model is trained from textual supervision---vision can be grounded in language, too! 8/

1

0

9

Freda Shi

@fredahshi

27 days

Thanks to @McAllesterDavid , our anti-grounding prof at @TTIC_Connect : thank you for all the inspiring conversations and writings that push back the idea of grounding, e.g., . I hope (and believe) my grounding above is not what you are against :) 10/

The Case Against Grounding

A recent NOEMA essay by Jacob Browning and Yann LeCun put forward the proposition that “an artificial intelligence system trained on words and sentences alone will never approximate human understan…

machinethoughts.wordpress.com

1

0

9

Freda Shi

@fredahshi

27 days

@ybisk @universeinanegg @_jessethomason_ One exception is acoustically grounded word embeddings (e.g., Settle et al., 2019), where they encode acoustic knowledge into word embeddings. Perhaps no one thinks the pronunciation of a word is its meaning, but still, this is an acceptable usage of "grounding." 5/

1

0

9

Freda Shi

@fredahshi

27 days

@ybisk @universeinanegg @_jessethomason_ In my thesis, I proposed the following definition of grounding, unifying all cases above. Grounding means processing the primary data X with supervision from source Y (the ground), where the mutual information I(X; Y) > 0, so we can find meaningful connections between them. 6/

1

0

9

Freda Shi

@fredahshi

1 year

Both Heinrich (who didn’t wanna share seat with others) and I enjoyed your excellent defense talk — huge congrats Dr. Kanishka Misra!

Kanishka Misra 😶‍🌫️

@kanishkamisra

1 year

Oh and my favorite photo from the defense was taken by @fredahshi -- I hope everyone here enjoys it as much as I did (what a great cat!) 5/6

1

0

10

1

0

9

Freda Shi

@fredahshi

27 days

@ybisk @universeinanegg @_jessethomason_ In real-world scenarios, the conditional entropy H(Y|X) almost always> 0, meaning that the ground is usually more complicated than what is to be grounded from certain perspectives. 7/

1

0

8

Freda Shi

@fredahshi

2 years

@yoavartzi Congrats on the Best Paper Award!! Super well deserved!

0

8

Freda Shi

@fredahshi

2 years

2. When example problems in the same language as the problem of interest are available, use them for prompting. If not, use examples from a diverse set of languages. (6/n)

1

0

7

Freda Shi

@fredahshi

2 years

In addition, we analyze the effect of the choices on prompting examples and prompting techniques, and highlight the following takeaways. (4/n)

1

0

7

Freda Shi

@fredahshi

27 days

I'm extremely thankful to my advisors Karen and @kevingimpel & my committee members and mentors @lukezettlemoyer and @roger_p_levy , for the great questions and suggestions on my thesis. 12/

1

0

7

Freda Shi

@fredahshi

4 months

Sida is beyond amazing! Go work with him!

Sida Wang

@sidawxyz

4 months

I'm hiring a PhD intern for the FAIR CodeGen (Code Llama) team. Do research on Code LLMs, execution feedback, evaluation, etc. Apply here:

3

31

198

0

5

Freda Shi

@fredahshi

27 days

@McAllesterDavid @TTIC_Connect Also here's a quick guide for readers interested in the additional content covered by my thesis. 11/

1

0

6

Freda Shi

@fredahshi

27 days

To my friends, mentors, coauthors, and everyone who has offered direct or indirect help in the past years, please read my thanks in acknowledgment, which is probably the most exciting part of every PhD thesis. 14/14

0

6

Freda Shi

@fredahshi

6 years

Excited to have the work on tree-based neural sentence modeling (joint with my excellent collaborators Hao Zhou, Jiaze Chen and Lei Li) accepted by #EMNLP2018

0

6

Freda Shi

@fredahshi

1 year

I had some difficulty figuring out the horizontal scroll (横批; héng pī)—while eventually I realize in this case it should be read from left to right, we typically write it from right to left in China :) Happy New Year to my friends who are celebrating!

Language Log

@LanguageLog

1 year

The difficulty of expressing "nothing": This is a clever attempt to write a spring couplet (chūnlián 春聯), not in the usual Sinoglyphs / Chinese characters, but in pictographs: (source) I could figure out about half of the character equivalents (rebuses…

5

10

40

0

5

Freda Shi

@fredahshi

5 months

@akoksal_ Thank you Abdullatif! Definitely checking out!

0

1

Freda Shi

@fredahshi

18 days

@denny_zhou @kchonyc I believe both explanations are valid, although marginalizing over reasoning paths that share the same result is probably the most natural way to think about it. My thesis (P123) discusses three explanations of SC and MBR-Exec (…)

1

0

5

Freda Shi

@fredahshi

4 months

Go Palatino!

Shuyan Zhou

@shuyanzhxyc

4 months

#COLM template is so visually pleasant, the joy of writing 🆙🆙🆙

2

3

53

1

0

5

Freda Shi

@fredahshi

27 days

Special thanks to @MichaelHBowling , Dale Schuurmans, and @nidhihegde for the wonderful discussion on grounding at a dinner a year ago. The conversation has made the term grounding (in my mind) more articulable. 9/

1

0

5

Freda Shi

@fredahshi

1 month

@MorrisAlper @moranynk @ElorHadar @RGiryes Excited to see more work on quantifying visual concreteness! Our ACL'19 work on quantifying text span concreteness and using it for syntactic parsing might also be of interest:

Visually Grounded Neural Syntax Acquisition

Haoyue Shi, Jiayuan Mao, Kevin Gimpel, Karen Livescu. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2019.

aclanthology.org

0

4

Freda Shi

@fredahshi

6 years

Our work got the same result on sentence encoder!

Graham Neubig

@gneubig

6 years

#EMNLP2018 "A Tree-based Decoder for NMT", a framework for incorporating trees in target side of MT systems. We compare constituency/dependency/non-syntactic binary trees, find surprising result that non-syntactic trees perform best, and try to explain why

4

32

140

1

0

4

Freda Shi

@fredahshi

4 years

Can't agree more. I voted for "that's syntax", but I wouldn't be happy to see a paper using "syntactic features" to refer to POS tags only, and I've been not so happy for >3 times.

C. Gómez-Rodríguez

@carlosgr_nlp

4 years

@emilymbender At the very least it's a misleading use of the term. To me it's like doing linear regression and calling it a neural approach... technically true (linear regression can be seen as a 1-neuron neural network) but I don't see why anyone would say it (w/o context) if not to oversell.

1

9

0

4

Freda Shi

@fredahshi

3 months

And great to see... Yoav brings back the cute llama arts!

Yoav Artzi (PC-ing COLM)

@yoavartzi

3 months

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

1

0

4

Freda Shi

@fredahshi

5 years

See you then, Sam!

0

4

Freda Shi

@fredahshi

6 years

Code for experiments is available at now 😃

GitHub - ExplorerFreda/TreeEnc: [EMNLP 2018] On Tree-Based Neural Sentence Modeling.

[EMNLP 2018] On Tree-Based Neural Sentence Modeling. - ExplorerFreda/TreeEnc

github.com

1

0

4

Freda Shi

@fredahshi

8 months

My brain LM is still favo(u)ring “favorite” - you should seriously consider coming to Canada 🍁

Jiayuan Mao

@maojiayuan

8 months

Definitely one of my top 3 favourite papers :) It marries deep learning with a minimal set of universal grammar rules for grounded language learning. It draws inspiration from lexicalist linguistics and cognitive science (bootstrapping from core knowledge).

0

6

57

0

4

Freda Shi

@fredahshi

3 years

(and guess which is me w/o exact matching on either first or last name! :)

Freda Shi

@fredahshi

3 years

Honored to receive the 2021 Google PhD fellowship in natural language processing. Thanks @GoogleAI for the support! Kudos to my advisors and mentors: thanks for teaching me everything over the past years, and for showing me concrete examples of best researchers---yourselves!

9

4

181

2

0

4

Freda Shi

@fredahshi

5 years

Madhur's course is really nice! I'd recommend it to everyone who wishes to review/learn some fundamental mathematical concepts related to machine learning.

Shubhendu Trivedi

@_onionesque

5 years

@EugeneVinitsky Madhur Tulsiani runs a very similar course every other year (this has links to iterations of the class, the latter ones have more refined notes).

1

9

0

4

Freda Shi

@fredahshi

27 days

Of course, the work covered in this thesis is built on the foundation of the literature—my thanks go to the authors of the papers I cited. I hope I've discussed your work in a fair way. 13/

1

0

4

Freda Shi

@fredahshi

5 months

@mrdrozdov HUGE congrats, Andrew!! 🎉🍾

0

1

Freda Shi

@fredahshi

7 months

@sharonlevy21 Also wonder if this would happen for inanimate objects/subjects as well!

0

2

Freda Shi

@fredahshi

8 months

@maojiayuan @jiajunwu_cs @roger_p_levy As in a CCG, each lexicon entry has its syntactic type and semantic representation. We induce the syntax and semantics of the questions, execute the neuro-symbolic semantic program with visual input, and reward the parser if the execution result is correct. (4/)

1

0

3

Freda Shi

@fredahshi

9 months

@tallinzen That’s part of the reason why I started using GitHub to manage my working papers. Another part is the nice combination of VSCode & LaTeX workshop.

0

3

Freda Shi

@fredahshi

2 years

@RTomMcCoy Sometimes I do Ctrl/Cmd+Shift+V for 2) and 3) XD

0

3

Freda Shi

@fredahshi

7 months

@UndefBehavior Sorry to hear this! As an alternative, my coauthors and I tried to publish at ML conferences (for our case, NeurIPS) on highly linguistic topics. We got constructive feedback from reviewers, but very little attention for our presentation.

0

2

Freda Shi

@fredahshi

7 months

@sharonlevy21 Congrats on the excellent work! I found the Table 1 example very interesting: these four sentences are clearly negative to me, and I can't imagine if anyone would label any of them positive---wonder if more data could fix this?

2

0

3

Freda Shi

@fredahshi

5 years

@amitmoryossef @emilymbender My advisor Karen Livescu is working on ASL as well:

0

3

Freda Shi

@fredahshi

9 months

@kanishkamisra I started to use onenote (not supposed for managing todos though). Just start a new page for all todos this week each Monday morning, and copy leftovers from the prior week.

0

2

Freda Shi

@fredahshi

2 months

@shuyanzhxyc @DukeU @dukecompsci Yay! Congrats Shuyan!

1

0

2

Freda Shi

@fredahshi

5 years

Great paper and impressive results. Very excited to see it!

Andrew Drozdov

@mrdrozdov

5 years

Now with paper link: And code: New results on unsupervised parsing: +6.5 F1 compared to ON-LSTM (2019), +6 F1 compared to PRLG (2011).

1

16

79

0

2

Freda Shi

@fredahshi

26 days

@SonglinYang4 Thanks Sonta! Now I know who to blame if someone calls me Dr Meow at conferences😼

0

2

Freda Shi

@fredahshi

1 year

@xwang_lk @UWCheritonCS @VectorInst Thanks Eric!

0

1

Freda Shi

@fredahshi

6 years

Will also be presented at #EMNLP2018 :

0

2

Freda Shi

@fredahshi

1 year

Definitely reach out to @WenhuChen @yuntiandeng and/or me if you’d like to learn more about Waterloo NLP (and probably catch @hllo_wrld & @lintool next time :)

0

2

Freda Shi

@fredahshi

10 months

@anand_bhattad @TTIC_Connect @IllinoisCS Welcome to TTIC!!!

1

0

2

Freda Shi

@fredahshi

5 months

@lukeZhu20 Yes!! Thanks much, Jian! I should’ve pinged you before asking here ;)

0

1

Freda Shi

@fredahshi

8 months

@joycjhsu This is cool! Can I ask a quick question - why would humans say "no" to the teaser question? From a quick glance, it could perfectly be a "wug" to me :)

3

0

2

Freda Shi

@fredahshi

8 months

@colinraffel Congrats Colin! Looking forward to working with you at Vector!

0

2

Freda Shi

@fredahshi

8 months

We are also aware that the method comes with efficiency issues in complicated real-world settings, and that’s an exciting direction to explore in the future! (13/13)

0

2

Freda Shi

@fredahshi

2 years

@denny_zhou Oh wow, I'm surprised that the homework includes a clear chain-of-thought example! Also I think this is a challenging example for LMs: it's nontrivial to work out generalization from <-2, /3> operations to <+2, /4>, even for the 20-year-ago me.

1

0

2

Freda Shi

@fredahshi

7 months

@kanishkamisra Yeah still remember how surprised I was on a syntax class seeing people had different acceptability judgment to “y’all”.

1

0

2

Freda Shi

@fredahshi

7 months

@universeinanegg I occasionally came across this before — — perhaps it’s something close to what you’re looking for?

HistoInformatics2021 workshop

sites.google.com

1

0

2

Freda Shi

@fredahshi

8 months

In summary, we show what will happen when neuro-symbolic models meet grammars (generalized CCGs), where we achieve significantly improved performance on compositional generalization. (12/)

1

0

2

Freda Shi

@fredahshi

6 years

Excited to see this!

0

2

Freda Shi

@fredahshi

8 months

Paper📝: Project page🌐: Work was led by the amazing @maojiayuan , and done jointly with @jiajunwu_cs , @roger_p_levy , and Josh Tenenbaum. (2/)

1

0

2

Freda Shi

@fredahshi

5 years

Happy days!

TTIC

@TTIC_Connect

5 years

Midwest Speech and Language Days | Day 2. Thank you to all participants, speakers and organizers!

0

1

0

2

Freda Shi

@fredahshi

1 year

@WangBinxu @UWCheritonCS @VectorInst Thanks Binxu!

0

1

Freda Shi

@fredahshi

2 years

Surprisingly, with only program input and no access to ground-truth output, MBR-Exec shows significant improvement over all execution-unaware methods on Python program generation, tested on the MBPP dataset. (4/n)

1

0

1

Freda Shi

@fredahshi

4 years

Just in case people have similar issue: I solved this by switching browser -- Win10 + Chrome 81.0.4044.138 doesn't work, but MS Edge does :)

Freda Shi

@fredahshi

4 years

I am trying to make a submission to @emnlp2020 , but the system asks me to fill out the reviewer data form. I filled it, and it says "thank you", and I was redirected to the home page, and everything repeats for another time. Anyone has similar problem?

0

1

Freda Shi

@fredahshi

24 days

@xwang_lk Thank you Eric! Excited to join the PI club😼

0

1

Freda Shi

@fredahshi

1 year

@sur4js @UWCheritonCS @VectorInst Thanks Suraj!

0

1

Freda Shi

@fredahshi

24 days

@ChengleiSi Thanks Chenglei! Enjoy NAACL :)

0

1

Freda Shi

@fredahshi

4 years

I am trying to make a submission to @emnlp2020 , but the system asks me to fill out the reviewer data form. I filled it, and it says "thank you", and I was redirected to the home page, and everything repeats for another time. Anyone has similar problem?

0

Freda Shi

@fredahshi

9 months

@wzhao_nlp @denny_zhou Agreed and that’s our motivation for proofreading multiple times before submitting a paper :) I’d love to see more human experiments and rigorous comparison!

0

1

Freda Shi

@fredahshi

2 months

@xiye_nlp @UAlberta @PrincetonPLI Congrats Xi & welcome to Canada🍁!

0

1

Freda Shi

@fredahshi

1 year

@Eric_Wallace_ @UWCheritonCS @VectorInst Thanks Eric!

0

1

Freda Shi

@fredahshi

2 years

Language models spread their probability over multiple programs with slightly different implementations but the same underlying functionality. When we only have one chance to choose an output program for each natural language sentence, how should we select it? (2/n)

1

0

1

Freda Shi

@fredahshi

3 months

@m2saxon @yuvalmarton This is an excellent point! Starting with America ≠ US, I spent some time realizing America = US in most of my conversations, and then some more time bringing back America ≠ US.

0

1

Freda Shi

@fredahshi

26 days

@akoksal_ Thank you Abdullatif!

0

1

Freda Shi

@fredahshi

1 year

@ChenhaoTan @ChicagoHAI This is fantastic! Congrats Chenhao!

1

0

1