Siva Reddy @sivareddyg Twitter profile

Last Seen Profiles

@XCD1829711

@Lostlove1075590

@Hijabbacol2883

@wedjjat

@arenaindepa

@urin_

@sylkikissbot

@couples_mot7arr

@18dart5

@risesuke_

@isaiahphillips_

@manueloropeza68

@IanxEnger

@nicolasmeichel

@Workhuman

@jkubatko

@lililnin144433

@qu_egachan

@righteous_monk_

@SuperFutbol

@levels_ll

@iBabyGirlOf

@gotkdeg

@Exasio

@Trangellabeauty

@tsudajunko

@ghhsbucs

@sodapresh

@TeamMichigan24

@BOXTOKENCARDANO

@rjss1989

@chiawastore

@HODLBOX3D

@vietdungpham

@BigSwan20

@OdellExec

Siva Reddy

@sivareddyg

1 year

My student sent me this list saying they have to improve themselves in many areas. Such a list can do more harm than good. While I appreciate author's intention to motivate one for greatness, I don't think it can be planned. But you can plan to be a "good researcher."

Jason Wei

@_jasonwei

1 year

Enjoyed visiting UC Berkeley’s Machine Learning Club yesterday, where I gave a talk on doing AI research. Slides: In the past few years I’ve worked with and observed some extremely talented researchers, and these are the trends I’ve noticed: 1. When

45

275

2K

13

60

575

Siva Reddy

@sivareddyg

5 years

Excited to share that I will be joining @McGillU and @MILAMontreal as an Assistant Professor in Computer Science and Linguistics from Jan 2020. Looking forward to work with excellent people who are passionate about human language and its role in learning! 🕺🏿🤸🏿‍♂️😊 1/3

91

24

546

Siva Reddy

@sivareddyg

8 months

Introducing WebLINX 🐯, a large benchmark for AI agents navigating real websites with multi-turn dialogue. 100K interactions across 2300 demonstrations on 150 real-word websites. Includes HTML, screenshots and videos. Tests unseen sites, tasks, blind users

7

69

258

Siva Reddy

@sivareddyg

9 months

Mindboggling that an entire paper of ours has been plagiarized and posted on arXiv. And @arXiv autodetect couldn't catch the plagiarism (and it took us a month). Is this a social experiment or a deliberate attempt? A nice example for the dark side of LLMs. Spotted by @JasperJJian

20

40

239

Siva Reddy

@sivareddyg

4 years

Can we improve chatbots after deployment from natural user feedback? A big YES :) User feedback has rich cues about errors but it cannot be used directly for training. So we use GANs to generate training data from feedback. #Findings -of- #EMNLP2020 #NLProc .

5

29

217

Siva Reddy

@sivareddyg

1 year

I have an opening for a #NLProc postdoc at Mila/McGill. Perks: . pursue own interests . mentor talented PhDs . collaborate with Mila profs and industry . access to large compute . live in a vibrant city Please spread the word. I will be in Toronto for #ACL2023NLP . Email me.

4

57

187

Siva Reddy

@sivareddyg

5 years

A glimpse of my journey into NLP and what I am excited about. Thank you CIFAR and @FacebookAI for your incredible support in funding fundamental research. Looking forward to hiring many junior researchers to work on hard problems in #NLProc at @MILAMontreal and @McgillU .

CIFAR

@CIFAR_News

5 years

@cjmaddison @VectorInst @UofT @DeepMindAI Siva Reddy @sivareddyg @MilaMontreal @McGillU builds systems that you can talk to just as naturally as you would with a person. #realbrains

0

8

21

13

10

166

Siva Reddy

@sivareddyg

1 year

I will make my stance clear. I oppose any form of violence against civilians, especially children, be it in Israel, Gaza, Ukraine, Iran, Sudan or elsewhere. My silence does not mean I don't care. I care in limited ways in which I can make a difference while preserving my sanity.

2

5

154

Siva Reddy

@sivareddyg

7 years

All done with PhD at @EdinburghNLP including the paperwork . Looking forward to focusing on postdoc at @StanfordNLP .

18

5

153

Siva Reddy

@sivareddyg

3 years

In most search sessions, people switch between two to ten topics 😯. But work in conversational question answering assumes a session around a single topic (CoQA, QuAC). We launch, TopiOCQA (🗣️Tapioca🧋), a realistic challenge with topic switching #NLProc

3

32

147

Siva Reddy

@sivareddyg

6 months

Mistral is not confused when we enable bidirectionality whereas LLaMA goes off the rails 🤠. We may have unlocked one secret ingredient of why Mistral is better than LLaMA. We believe it is 💥Prefix LM💥. This side finding is exciting in itself!

Vaibhav Adlakha

@vaibhav_adlakha

6 months

We also analyze how enabling bidirectional attention without training affects the representations of decoder-only LLMs 🔍. We find that Mistral-7B is surprisingly good at using bidirectional attention out-of-the-box 🤯 and speculate it was likely trained as a prefix-LM 🤔. 7/N

10

4

122

3

12

135

Siva Reddy

@sivareddyg

4 years

What are your tips for surviving grad school? We will share these with several grad students at #acl2020nlp . My tip: commit to making at least one line of progress (code, writing) every work day even on your bad days. #NLProc #AcademicChatter

roeeaharoni

@roeeaharoni

4 years

Hey #acl2020nlp ! Tomorrow, 9:00-10:00am PDT I'll be hosting a session on "surviving graduate school" with @sivareddyg and @karlstratos - come say hi!

1

4

46

12

26

125

Siva Reddy

@sivareddyg

4 years

Transformer language models are good at reasoning eg if x is a parent of y, and y is a parent of z, they can infer x is a grandchild of z. But can they reason about long number of proof steps? No. See results when trained on 2,4,6 proof lengths and tested on 2-10 #NeurIPS #NLProc

Nicolas Gontier

@nicogontier

4 years

Super happy to finally share my first first-author paper (to appear at #NeurIPS2020 )! Couldn't have done it without my amazing collaborators @koustuvsinha @sivareddyg @chrisjpal

6

9

113

3

19

117

Siva Reddy

@sivareddyg

3 years

Back-training, the back-translation technique for non-translation tasks is here. We use it for unsupervised domain adaptation. We see 9 BLEU points improvement on Question Generation, and 8 points on retrieval performance (P @1 ) #NLPRoc

2

10

111

Siva Reddy

@sivareddyg

1 year

As a student, I find it paralyzing to aiming for greatness because you never know when you met the bar. Instead one should aim to master the craft of research -- a) ideation, experimentation, and communication, and b) graduate and get ready for a research career

3

107

Siva Reddy

@sivareddyg

3 years

School of Computer Science at McGill University @McGillU is hiring a tenure-track faculty position in #MachineLearning . The candidate may also be nominated for a generous CIFAR AI chair at @Mila_Quebec . Join us in Montreal!! Deadline Dec 15th. Details:

0

39

102

Siva Reddy

@sivareddyg

8 years

@zehavoc @kchonyc @rctatman @haldaume3 on the death of double-blind reviewing, I think this will happen more in future and for good reasons.

4

51

106

Siva Reddy

@sivareddyg

1 year

State-of-the-art question answering in 25 lines, and flexible modules that allow to use different retrievers and language models

GitHub - McGill-NLP/instruct-qa: Code and Data for "Evaluating Correctness and Faithfulness of...

Code and Data for "Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering" - McGill-NLP/instruct-qa

github.com

Vaibhav Adlakha

@vaibhav_adlakha

1 year

Using ~25 lines of code 💻 you can easily leverage retrieval-augmented instruction-following models for question-answering! 🚀 🔗 Detailed documentation coming soon! Shoutout to @xhluca , @ncmeade , and @ParishadBehnam for core contributions to the library

1

13

74

1

21

95

Siva Reddy

@sivareddyg

2 years

Today I will be talking at #SPNLP at 15:30 pm Dublin time on "Do we still need inductive biases after Transformer language models?". Come with your answers :), and questions are welcome too. #acl2022nlp

1

11

92

Siva Reddy

@sivareddyg

6 months

LLMs are "secretly" powerful text encoders. LLM2Vec is the key to unlock their embeddings in 1-2 hours in an unsupervised fashion using LoRA. Achieves SOTA on MTEB in the unsupervised category and also among supervised models trained on public data Code:

GitHub - McGill-NLP/llm2vec: Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text...

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders' - McGill-NLP/llm2vec

github.com

Vaibhav Adlakha

@vaibhav_adlakha

6 months

We introduce LLM2Vec, a simple approach to transform any decoder-only LLM into a text encoder. We achieve SOTA performance on MTEB in the unsupervised and supervised category (among the models trained only on publicly available data). 🧵1/N Paper:

14

170

887

1

17

88

Siva Reddy

@sivareddyg

4 years

General sense I am getting out of my #EMNLP2020 submissions: 1. Reviews are unnecessarily critical (an indication of first-time reviewers?) 2. Reviews are short 3. Many borderline scores 4. Low quality reviews (heavy reliance on paper matching?)

6

8

86

Siva Reddy

@sivareddyg

2 years

Pleased to have @ChrisGPotts 's talk today at @McGillU / @Mila_Quebec on inducing causal structures to enforce systematicity. The key idea is to swap intermediate representations such that the prediction for the intervention conforms to the expected output. Works well for many tasks

4

9

83

Siva Reddy

@sivareddyg

2 years

Vision and language models have a long way to go. When context really matters, @OpenAI CLIP is only slightly better than random. ImageCoDe is probably the wildest dataset ever for pragmatics with natural images! Human performance is ~90% and the best model is at ~30%. #acl2022nlp

Benno Krojer

@benno_krojer

2 years

Can vision & language models retrieve the correct image from a set given its contextual description (e.g. No bridesmaid visible at all)? We show that models struggle with this kind of contextual reasoning #ACL2022

3

22

123

0

14

83

Siva Reddy

@sivareddyg

2 years

Debiasing methods may seem effective at mitigating bias but the trick they rely on is to make the language model worse. They do not generalize beyond gender. An empirical analysis of several debiasing methods on multiple domains and datasets, with a unified codebase! #acl2022nlp

Nicholas Meade

@ncmeade

2 years

Social bias mitigation techniques in #NLProc require a holistic evaluation (bias, language modeling & downstream)! Work w/ Elinor Poole-Dayan & @sivareddyg at #acl2022nlp . 📄Paper: 🔧Code: 📋Website: 1/7

2

9

35

2

12

77

Siva Reddy

@sivareddyg

3 years

At least an exception for people affected directly will be a kind gesture from @EMNLPmeeting ! I am not affected personally, but I can tell you that the situation is dire for many. Over the past few days, most calls with my family end up with news of someone I know dying #NLProc

Shoaib Jameel

@shoaibjameel123

3 years

Wrote to the EMNLP 2021 PC Chairs considering extending the deadline due to COVID-19 "catastrophic" situation in India, but was turned down. I recall in EMNLP 2020 the deadline was extended due to protests in the US, which caused some controversies. Submitting to CIKM 2021 now.

9

78

321

0

4

74

Siva Reddy

@sivareddyg

2 years

Question answering models don't have to die once deployed. Revive them with interactive feedback for an ever improving model both on accuracy and explainability. Introducing FeedbackQA #acl2022nlp Try the demo to see it yourself #NLProc

1

15

73

Siva Reddy

@sivareddyg

8 months

Omar Khattab ( @lateinteraction ) is enlightening us at Mila/McGill with Language Model Programming, an important step towards controllable language models. #NLProc @stanfordnlp

0

10

67

Siva Reddy

@sivareddyg

3 years

Most common method for cross-lingual transfer is to use multilingual encoders instead of translations (translate to English and then do the target task). We find the latter is superior if you directly optimize the translations for the target task & use n-best translations #NLProc

Edoardo Ponti

@PontiEdoardo

3 years

In our new paper, @KreutzerJulia @licwu @sivareddyg and I present a method to enhance translation-based cross-lingual transfer (gains up to 2.7 per task and 5.6 per language). Pdf: . Code: @Mila_Quebec @CambridgeLTL @GoogleAI

2

9

62

2

5

63

Siva Reddy

@sivareddyg

4 years

I might finally see some of my students physically. My heart breaks to see some of them attend a reading group at 3am. Grad life is hard, and this pandemic is making it harder. A reminder to be kind to our students ♥️

Marco Mendicino

@marcomendicino

4 years

Starting in late October, international students attending a designated learning institution that has been identified by their provincial or territorial government as having a COVID‑19 readiness plan will also be able to enter Canada.

209

214

1K

0

63

Siva Reddy

@sivareddyg

1 year

4. Disagree. Deep learning could not have happened if it was not pursued by the few people in their rabbit holes during the AI winter. This is not for everyone and could be highly stressful.

2

60

Siva Reddy

@sivareddyg

4 years

Join us at the BoaF Semantics session on "Linguistic Generalization and Compositional Reasoning Abilities of Large Pretrained Models". #EMNLP2020 Nov 17 Tue 4-5pm EST / 1-2pm PDT Panelists: @DipanjanD , @nlpMattG , @ElliePavlick , @ChrisGPotts Details:

2

10

59

Siva Reddy

@sivareddyg

4 years

Super excited about your decision, thank you! Looking forward to doing important work in the space of language understanding and grounding. Some of the reasons you mention strongly resonate with why I started my research group at @Mila_Quebec .

Benno Krojer

@benno_krojer

4 years

Seems like an eternity since I decided to apply for a PhD farther away than I've ever been. I can finally announce, very excitedly of course, that I'll join @sivareddyg 's lab at @Mila_Quebec & collaborate with other language grounders! Thread on things I'm excited about: 1/n

8

1

67

0

1

59

Siva Reddy

@sivareddyg

1 year

One of the qualities I appreciate of students is to having the ability to reach the finish line of a project. It is easy to hop on multiple projects but requires strength to stay. But I don't mean staying on for too long. Just the right amount. Find your balance :).

3

0

58

Siva Reddy

@sivareddyg

1 year

Along this process, it is fine to have papers that are not great but are scientifically rigor. As you gain more experience, you can aim to maximize impact but it is not guaranteed.

1

55

Siva Reddy

@sivareddyg

10 months

Conference wouldn't end without a group picture. We were here #EMNLP2023

Arkil Patel

@arkil_patel

10 months

Finishing up #EMNLP2023 after presenting some cool papers from our lab. It was nice catching up with friends and forming new connections. See you all at the next one!

2

1

27

1

0

56

Siva Reddy

@sivareddyg

4 years

How biased are large pretrained language models? Our take on measuring bias in existing LMs. We found that GPT2 is more humane than BERT and others. Terrific work by @moinnadeem (started his work as an undergrad)!! Cautionary warning of offensive examples..

Moin Nadeem

@moinnadeem

4 years

As pretrained language models grow more common in #NLProc , it is crucial to evaluate their societal biases. We launch a new task, evaluation metrics, and a large dataset to measure stereotypical biases in LMs: Paper: Site: Thread👇

2

21

71

2

4

54

Siva Reddy

@sivareddyg

6 months

Many of us at @Mila_Quebec are thrilled to hear from @HinrichSchuetze about generating large scale instruction data in an unsupervised fashion. Recording will be available. My course students also had a bonus course lecture on pattern-exploiting training (PET) and GNNavi.

CIS, LMU Munich

@CisLmu

6 months

Hinrich Schütze is giving a talk, Quality Data For LLMs: Challenges and Opportunities, at @Mila_Quebec right now. Watch it live at the link below:

0

4

19

1

9

54

Siva Reddy

@sivareddyg

5 months

One of most intriguing findings of 2023 is that adversarial triggers that jailbreak one or more LLMs transfer to other models. We were so excited that we spent many months figuring out the conditions for universal transfer but the transfer never happened. It wasn't a bug 😀

Nicholas Meade

@ncmeade

5 months

Adversarial Triggers For LLMs Are 𝗡𝗢𝗧 𝗨𝗻𝗶𝘃𝗲𝗿𝘀𝗮𝗹!😲 It is believed that adversarial triggers that jailbreak a model transfer universally to other models. But we show triggers don't reliably transfer, especially to RLHF/DPO models. Paper:

3

32

99

1

11

63

Siva Reddy

@sivareddyg

8 years

Need logical forms for any language. Not a problem if you have a dependency treebank in UD schema #NLProc #SemanticParsing . Code coming soon

cs.CL Papers

@arxiv_cs_cl

8 years

Universal Semantic Parsing. (arXiv:1702.03196v1 [cs.CL]) #NLProc

1

5

20

2

21

51

Siva Reddy

@sivareddyg

3 years

Really excited that @DBahdanau has joined @McGillU as an adjunct prof, a great strength to our NLP group. Through collaborations with my students, I know how much he cares about the growth of junior people working with him. He will be a fantastic supervisor, please apply #NLProc

🇺🇦 Dzmitry Bahdanau

@DBahdanau

3 years

I am excited to share that as an Adjunct Prof at @mcgillu and member of @Mila_Quebec , I am looking to take 1-2 fully-funded MsC or PhD students this Fall. How to apply: (read carefully!). For possible research topics, see the thread.

3

41

177

0

3

49

Siva Reddy

@sivareddyg

4 years

We submitted a proposal to organize a workshop on document-grounded dialogue and conversational question answering. Excellent line of speakers/panelists and PC! We also have a shared task. More details #NLProc

0

2

49

Siva Reddy

@sivareddyg

3 years

A systematic organization of posthoc interpretability methods in #NLProc . Result of many human hours (much more environmental friendly 🙂) from @andreas_madsen . It is likely that some relevant papers are missing. Please point them in order to be included in the next revision.

Andreas Madsen

@andreas_madsen

3 years

Our new survey on post-hoc interpretability methods for NLP is out! This covers 19 specific interpretability methods, cites more than 100 publications, and took 1 year to write. I'm very happy this is now public, do consider sharing. Read . A thread 🧵 1/6

11

136

552

1

5

45

Siva Reddy

@sivareddyg

7 years

08 Feb @StanfordNLP seminar: Pararth Shah from Google on "Building a Conversational Agent Overnight with Dialogue Self-Play" #NLProc Please join us. Open to all!

The Stanford NLP Group

Performing groundbreaking Natural Language Processing research since 1999.

nlp.stanford.edu

1

18

43

Siva Reddy

@sivareddyg

3 years

Incredibly proud of Edoardo! Not only a brilliant person but a compassionate one. Will be an amazing supervisor, highly recommend! Lucky to have him in my group. This news sets a high bar for current members. Thanks to @AnnalKorhonen for sending one of her best students my way :)

Edoardo Ponti

@PontiEdoardo

3 years

I am delighted to share that I will be joining @EdinburghNLP at @EdinburghUni from 2022 as a lecturer in Natural Language Processing. I am currently recruiting PhD students, so if you are passionate... (1/6)

26

55

399

0

1

41

Siva Reddy

@sivareddyg

5 years

@strubell @ACL2019_Italy @ananya__g @andrewmccallum It is rare to see such papers and I admire your courage for choosing to work on such a problem. Congratulations! Every experiment I run from now on will make me rethink twice. Thank you!

1

0

40

Siva Reddy

@sivareddyg

1 year

5. Disagree. If you are a leader in an area, it is not wrong spending more time in that area while also pursuing other things if it is off the trend. Also, a degree like PhD requires you to come up with a coherent thesis, not papers on different topics stapled together.

1

0

39

Siva Reddy

@sivareddyg

1 year

2. Disagree. It is fine to have pieces of code that are hacky in the ideation phase. Later on when you get a validation of an idea, spending more time is justifiable. In industry, this could be different as there are many processes like code reviewing etc.

2

1

40

Siva Reddy

@sivareddyg

7 years

Is a flea market a market for fleas? Noun compositionality dataset is now on @kaggle . Thank you @rctatman ! #NLProc

1

11

40

Siva Reddy

@sivareddyg

7 years

31 Aug @StanfordNLP seminar: @jacobandreas on "translating neural representations to language" #NLProc open to all!

The Stanford NLP Group

Performing groundbreaking Natural Language Processing research since 1999.

nlp.stanford.edu

0

14

39

Siva Reddy

@sivareddyg

10 months

I am at #EMNLP2023 to catch up with friends, peers and prospectives. DM me. My wonderful students are presenting: #1 LLMs entangle many linguistic phenomena. @JasperJJian designs a clever way to extract syntactic structures from first principles.

Jasper Jian

@JasperJJian

10 months

How can we extract unsupervised syntactic structures from language models that are, well, syntactic? I’ll be presenting 'Syntactic Substitutability as Unsupervised Dependency Syntax' (SSUD) at #EMNLP2023 , on Dec 10 at 9AM in West 3! ✈️ This is work with @sivareddyg . 🧵

3

8

28

1

5

39

Siva Reddy

@sivareddyg

1 year

industry != academia. Once you find your ground, it is easier to take risks and aim for impact. You can still be a good researcher even if your papers are not ground breaking.

1

0

37

Siva Reddy

@sivareddyg

1 year

Coming to the list. 1. Agree. It is important to look at data before thinking about modeling. The first thing to try should be simple, and simple solutions are great solutions. It is also important to observe the behavior of the models qualitatively, and not just quantitatively.

1

37

Siva Reddy

@sivareddyg

3 years

On evaluating the faithfulness of explanations like attention and gradients -- the idea is to retrain a model by removing allegedly important tokens and measure the drop in performance, inspired from ROAR in vision. More faithful an explanation more the drop #NLProc

Andreas Madsen

@andreas_madsen

3 years

Can you trust attention explanations in #NLProc ? What about other explanations? I'm excited to present our answer to these questions in a new paper: I'm proud of this work. I hope you find it useful. If you do, consider sharing or ❤️. What do we find?...

7

34

168

1

6

37

Siva Reddy

@sivareddyg

1 year

3. Disagree. Working independently or in a small group is perfectly fine. But research can be isolating, so leaning on others is a good idea. Make sure you master the craft of each step at least once in different projects. Too many collaborators could also be futile.

1

0

36

Siva Reddy

@sivareddyg

1 year

If you are looking for an NLP problem that is real and not solved by LLMs 🤖, check this out. Real conversations with Statistics Canada agents helping you to find relevant information from thousands of tables containing census data. It can't get more real than this 🙂. #NLProc

Xing Han Lu

@xhluca

1 year

Happy to share our #eacl2023 paper, which introduces a new dataset for Table Retrieval in Conversations: the 🍁ꜱᴛᴀᴛᴄᴀɴ ᴅɪᴀʟᴏɢᴜᴇ ᴅᴀᴛᴀꜱᴇᴛ 🍁 Paper: Homepage: A work with @sivareddyg and @harmdevries77 🧵👇

2

16

38

0

3

32

Siva Reddy

@sivareddyg

7 years

Excited to be the opening speaker at the AI Assistant Summit, SFO. I will be talking about the state of NLU, what's hype and what not, at 9:10 am today. Slides will be posted shortly. #reworkdl #reworkai #nlproc

RE•WORK | Events in Artificial Intelligence

Learn more about AI application, implications and limitations. Gain insights and knowledge from the RE•WORK team of industry experts. Register to our events today.

www.re-work.co

1

5

34

Siva Reddy

@sivareddyg

1 year

6. Disagree. Some real world problems are niche and hard to solve with generic solutions, e.g., working on indigenous languages.

1

32

Siva Reddy

@sivareddyg

8 months

My first interdisciplinary stint -- LLMs meet NeuroScience and BioMedicine. Thank you @DaniloBzdok et al. for this fun collaboration.

Danilo Bzdok

@danilobzdok

8 months

How can #LLMs make a difference in #neuroscience and #biomedicine ? Language has more human information per bit than potentially any other form of data. Great collabo with @sivareddyg + @MindstateDesign . @Mila_Quebec @TheNeuro_MNI @mcgillu

3

75

202

1

33

Siva Reddy

@sivareddyg

5 years

Job search has been a roller coaster of emotions. I am glad to have met many incredible people during the process. The toughest part was to bear the guilt of getting paid as a postdoc while I am busy searching and not working. I am grateful to have a very supportive advisor. 2/3

1

32

Siva Reddy

@sivareddyg

1 year

@npc1821633 I got my first troll, I made it to the great list!!

0

31

Siva Reddy

@sivareddyg

6 years

10 May @StanfordNLP seminar: @Alan_Ritter from Ohio State University on "Large Scale Learning for Information Extraction" #NLProc Please join us. Open to all!

The Stanford NLP Group

Performing groundbreaking Natural Language Processing research since 1999.

nlp.stanford.edu

1

10

32

Siva Reddy

@sivareddyg

6 years

12 April @StanfordNLP seminar: @AdjiBoussoDieng from Columbia University on "Deep Sequence Models: Context Representation, Regularization, and Application to Language" #NLProc Please join us. Open to all!

The Stanford NLP Group

Performing groundbreaking Natural Language Processing research since 1999.

nlp.stanford.edu

1

8

30

Siva Reddy

@sivareddyg

5 years

Don't mess with Montreal'ers on climate change. Literally, everybody is on the street today, including me :). #MontrealClimateMarch

1

29

Siva Reddy

@sivareddyg

5 years

If you have any readings on how to get ready for an Assistant Professor job, please share. I have 3 months break to get started. What should I prioritize during this period --- travel, research, course preparation, catch up on tv, rest, or cook :). 3/3

6

1

28

Siva Reddy

@sivareddyg

6 years

Thank you and I am looking forward!

UCI Center for Machine Learning & Intelligent Sys

@UCI_CMLIS

6 years

Siva Reddy @sivareddyg from @StanfordNLP is visiting us today to talk about Conversational QA, #CoQA #NLProc in DBH 4011, 11am.

1

6

20

0

29

Siva Reddy

@sivareddyg

5 years

If you are attending #ICLR2019 , don't miss our workshop on Deep Generative Models for Highly Structured Data (NLP, Vision, Physical Sciences). An excellent line up of invited speakers (e.g., Yoshua Bengio), and awesome papers #ICLRDeepGen

0

4

28

Siva Reddy

@sivareddyg

4 years

Tip 2: Meet your supervisor regularly (even for 5 mins) especially when you feel you are not progressing and don't have enough updates. Intrinsic motivation is hard to rely on. Meeting supervisor was my extrinsic motivation (or fear of embarassing myself which happens sometimes)

1

29

Siva Reddy

@sivareddyg

7 years

11 Jan @StanfordNLP seminar: Pushpak Bhattacharyya from @iitbombay on "Sarcasm Detection: A Computational Cognitive Approach" #NLProc Please join us. Open to all!

The Stanford NLP Group

Performing groundbreaking Natural Language Processing research since 1999.

nlp.stanford.edu

0

9

27

Siva Reddy

@sivareddyg

4 years

@sleepinyourhat I sympathize with them partly. I just saw someone who almost had a panic attack realizing that they are the only one in the QA session. Icebreaking can be done from the authors' end. Good starter question is "Where are you from?, How do you find the conference?" and small talk.

1

0

28

Siva Reddy

@sivareddyg

7 years

08 March @StanfordNLP seminar: Michael Auli from Facebook AI Research on "Sequence to Sequence Learning: Fast Training and Inference with Gated Convolutions " #NLProc Please join us. Open to all!

The Stanford NLP Group

Performing groundbreaking Natural Language Processing research since 1999.

nlp.stanford.edu

0

6

27

Siva Reddy

@sivareddyg

1 year

I know many people are silent for similar reasons. Don't equate silence = approval of atrocities. Humanity is not dead. Please don't lose hope.

Siva Reddy

@sivareddyg

1 year

I will make my stance clear. I oppose any form of violence against civilians, especially children, be it in Israel, Gaza, Ukraine, Iran, Sudan or elsewhere. My silence does not mean I don't care. I care in limited ways in which I can make a difference while preserving my sanity.

2

5

154

0

1

27

Siva Reddy

@sivareddyg

4 years

EMNLP/*ACLs assess the interest of a workshop through a survey (😐). If you work in the areas of dialogue/conversational question answering, please show your interest through votes here (scroll to the 5th page, category: discourse, dialogue). #NLProc

Siva Reddy

@sivareddyg

4 years

We submitted a proposal to organize a workshop on document-grounded dialogue and conversational question answering. Excellent line of speakers/panelists and PC! We also have a shared task. More details #NLProc

0

2

49

2

9

27

Siva Reddy

@sivareddyg

7 years

GOP tax plan will reduce annual stipend of PhD students by 25 percent, e.g., at CMU from $29,566 to $22,191. While Canada is investing millions in research, USA is taking away food from PhD students.

Oren Etzioni

@etzioni

7 years

Grad Students Are Freaking Out About the GOP Tax Plan. Just when you thought they couldn't stoop any lower..

1

9

3

2

11

27

Siva Reddy

@sivareddyg

7 years

24 Aug @StanfordNLP seminar: Lea Frermann is presenting "Deep Multi-View Representations" #NLProc . Visitors welcome!

The Stanford NLP Group

Performing groundbreaking Natural Language Processing research since 1999.

nlp.stanford.edu

1

10

25

Siva Reddy

@sivareddyg

7 years

19 Oct @StanfordNLP seminar: @jayantkrish on "Neural Semantic Parsing with Type Constraints" #NLProc Open to all!

The Stanford NLP Group

Performing groundbreaking Natural Language Processing research since 1999.

nlp.stanford.edu

0

10

25

Siva Reddy

@sivareddyg

6 years

@nlpmattg I listened to many voices on podcasts. But I did not anticipate a day where I would listen to my own voice. Thanks @nlpmattg and @waleed_ammar for making this possible! This is so much fun, and a bit strange :).

1

0

24

Siva Reddy

@sivareddyg

5 months

Llama-3 for instruction-based text embeddings is here 💥

Vaibhav Adlakha

@vaibhav_adlakha

5 months

LLM2Vec meets Meta-Llama-3 → new SOTA among models trained on public data 🥇. We applied our LLM2Vec approach to Meta-Llama-3-8B and it works like a charm. Each step of the LLM2Vec pipeline improves the model's performance on embedding tasks 👇. 1/N Models:

3

23

156

0

6

25

Siva Reddy

@sivareddyg

7 years

14 Sep @StanfordNLP seminar: Felix Hill on "learning language from scratch from interactions" … #NLProc Open to all!

The Stanford NLP Group

Performing groundbreaking Natural Language Processing research since 1999.

nlp.stanford.edu

0

7

25

Siva Reddy

@sivareddyg

10 months

Belated but thrilled to welcome David to join the NLP faculty at McGill. He will be recruiting several students, a great opportunity to work on low-resource languages.

David Ifeoluwa Adelani 🇳🇬

@davlanade

11 months

Thrilled to announce that I will be joining the @mcgillu School of Computer Science as a Tenure-Track Assistant Professor & Core Academic Member @Mila_Quebec starting early next year. A big thank you to my advisor, mentors & friends. God has surrounded me with amazing mentors.

95

55

507

1

2

25

Siva Reddy

@sivareddyg

8 months

Incredible effort by @xhluca and @ZdenekKasner in pulling off this behemoth task of building everything from scratch. They could have raised millions in funding for a startup, but instead, they decided to write a 40-page academic paper and release all data and code publicly.

0

2

25

Siva Reddy

@sivareddyg

4 years

This 👇. Thanks @chrmanning for sharing your wisdom in the mentoring session!

Samujjwal (sam)

@Samujjwal_Sam

4 years

@sivareddyg #acl2020nlp Tips for surviving grad school: Chris Manning: achieving SOTA should not be the goal of Grad students. It's about choosing a niche area and come up with small useful ideas.

1

7

52

1

3

25

Siva Reddy

@sivareddyg

9 months

Congratulations Dr. Mosbach! Looking forward to the exciting work we will do together at @Mila_Quebec . BTW cool hat 🤠

Marius Mosbach

@mariusmosbach

9 months

I successfully defended my PhD thesis yesterday 🎓. Many thanks to my advisor Dietrich Klakow, my committee @JonathanBerant , Vera Demberg, and Mareike Hartmann as well as my amazing colleagues and collaborators 😍. Next step 👉 @Mila_Quebec with @sivareddyg 🚀

20

2

117

1

0

24

Siva Reddy

@sivareddyg

7 years

09 Nov @StanfordNLP seminar: Eunsol Choi from @UWNLP on "Scaling Up Reading Comprehension" #NLProc Open to all

The Stanford NLP Group

Performing groundbreaking Natural Language Processing research since 1999.

nlp.stanford.edu

1

8

23

Siva Reddy

@sivareddyg

1 year

. @ReviewAcl Is it true that in order to be a reviewer, one should already have 5+ published papers at NLP venues? My student with multiple *ACL/NeurIPS papers kindly volunteered but came to know they are ineligible. How is this scalable as most submissions are from students?

3

5

24

Siva Reddy

@sivareddyg

4 years

Dataset biases can easily overpower inductive biases giving us a false impression of progress. It is critical to have both in-distribution hard splits and out-of-distribution splits to measure generalization. We examine language grounding 1/n

Arjun Akula

@arjunreddy2613

4 years

Are SOTA models grounding the language correctly? Are the benchmarks evaluating them right? No! We observe that neural module networks (NMNs) are simply relying on input words instead of exploiting structure. ViLBERT is relatively robust (1/4) #acl2020nlp

5

13

57

1

5

23

Siva Reddy

@sivareddyg

6 years

A short and nice blog post summarizing the CoQA 🍃 paper. Also contains a link to the QuAC paper. Thank you @hunter_heiden ! #NLProc #CoQA

0

1

23

Siva Reddy

@sivareddyg

6 years

I spoke at the Bay Area NLP & ML meetup a few weeks ago. Today this arrived at my door. Such a kind gesture. Thank you @MyaSystems , @sanjana_rampi , Zac for making my day and organizing this event! Great reception & friendly audience. I recommend my #NLProc friends to speak here🙂

2

23

Siva Reddy

@sivareddyg

7 years

17 Aug @StanfordNLP seminar: Mike Lewis is taking about "chat bots that negotiate" #NLProc . Feel free to attend.

The Stanford NLP Group

Performing groundbreaking Natural Language Processing research since 1999.

nlp.stanford.edu

0

6

23

Siva Reddy

@sivareddyg

3 years

Congratulations Dhanya, another exciting addition to @Mila_Quebec , very looking forward!!

Dhanya Sridhar

@dhanya_sridhar

3 years

Thrilled to share that starting Jan 2022, I'll be an assistant professor at the University of Montreal and a core academic member of @Mila_Quebec ! I'm extremely grateful to my amazing collaborators and mentors, especially @lgetoor and @blei_lab ! (1/2)

33

10

396

1

0

23

Siva Reddy

@sivareddyg

7 years

Woohoo.. Two power-packed invited speakers at #ACL2017 : Mirella Lapata and Noah Smith #NLProc

1

12

21

Siva Reddy

@sivareddyg

3 years

Congratulations Vered, great news NLP/AI community in Canada. Looking forward to joint projects :). #NLProc

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

1

0

22

Siva Reddy

@sivareddyg

3 years

#NLProc folks: Is there a way to access past rebuttals on softconf (for our own submissions)? This is valuable data to train future students, and I am not sure why conferences hide it after the review period. At least I can see reviews which was not the case until recently (2021)

1

2

21

Siva Reddy

@sivareddyg

7 years

Want your kid to learn NLP? Send them to @linghacks training day on Nov 18! #NLProc @ai4allorg

LingHacks

LingHacks, a project of Hack+, is an international nonprofit dedicated to harnessing the intersection of math and language to equip students of all backgrounds with cutting-edge technology, problem...

linghacks.weebly.com

1

9

20

Siva Reddy

@sivareddyg

4 years

@sleepinyourhat The expectation from authors and participants that they have to watch the video beforehand is unrealistic. I find it liberating to give up on that idea. Just go to a session and ask what the main contribution is or listen to other people questions.

2

0

19

Siva Reddy

@sivareddyg

8 months

Glad to see that NoPE still holds its superiority over RoPE on length generalization as we also find in [1]. But this FIRE is truly on fire 🔥 [1]

AK

@_akhaliq

8 months

Google Deepmind presents Transformers Can Achieve Length Generalization But Not Robustly paper page: Length generalization, defined as the ability to extrapolate from shorter training sequences to longer test ones, is a significant challenge for language

2

65

302

1

4

19

Siva Reddy

@sivareddyg

7 years

cool paper on semantic parsing with type constraints ; SOTA on WikiTableQs; pradeep @jayantkrish @nlpmattg #emnlp2017

1

7

19

Siva Reddy

@sivareddyg

1 year

World affairs are depressing and I find it is important to preserve my mental sanity to make an meaningful impact. Otherwise, I find everything in my life goes downhill (including family time) and any efforts thereafter are a lost cause.

0

18

Siva Reddy

@sivareddyg

7 years

Slides on "The State of Natural Language Understanding" are at #reworkdl #reworkai #nlproc

2

4

18

Siva Reddy

@sivareddyg

7 years

Can we build logical forms without knowing anything about the target language other than its syntax? Speaking today at 10:55 #emnlp2017 talk

1

2

18

Siva Reddy

@sivareddyg

2 years

Let a bot be a bot. Let it acknowledge what it doesn't know but still be helpful and creative. Current dialogue datasets encourage the opposite and license models to hallucinate alarmingly ( #naacl ). FaithDial (preprint) is all about trustworthy chatbots

Nouha Dziri

@nouhadziri

2 years

📢 Excited to share our new work 💥 FaithDial: A Faithful Benchmark for Information-Seeking Dialogue 📄 🌐 👩‍💻 joint work w. @sivareddyg , @PontiEdoardo , @ehsk0 , @ozaiane , Mo Yu, Sivan Milton #NLProc

2

18

60

1

5

17