Asli Celikyilmaz @real_asli Twitter profile

Last Seen Profiles

@PauloRangel_pt

@UtkarshSingh_

@barbie4life131

@Fenidelity_INA

@Tomafc83

@urbanevesen

@lalisalovemme

@jandakembangstw

@Cata88978204

@segawajan

@ma_g222

@moretti_bd

@Nouryflixtv

@ahlainci

@TEAMOMPRO

@kinderhooks

@amigosswmx

@MariaMariuru

@MdPakistan8588

@fantasi_emak

@InnovLaval

@BuffetBla

@leap_avax

@VeluPuumala

@cinturadifora

@gobrep

@V9By38DAmQ9dEiZ

@_forestzy

@DanielNoboaOKP

@OCAS_Orlando

@CarltonBrewster

@marineravin

@Rollo_Zen

@kakeksange16

@THORGuards

@LSUUrology

Asli Celikyilmaz

@real_asli

2 months

We have a postdoc and a research engineer position at FAIR to work on LLM+reasoning/alignment with specific focus on social reasoning, metacognition, interaction and others. Please reach out directly to me if you are interested.

11

26

222

Asli Celikyilmaz

@real_asli

5 months

Our team in FAIR (at Meta) is hiring researchers (RS & PostDoc) to work on the broad topics of text and multimodal LLMs. Location: NY, Seattle or Menlo Park for RS, and Seattle for PostDocs. PostDoc: Research Scientist, AI (PhD):

Error

Meta's mission is to give people the power to build community and bring the world closer together. Together, we can help people build stronger communities - join us.

www.metacareers.com

1

17

135

Asli Celikyilmaz

@real_asli

5 years

Just got some really good news! I am now an Affiliate Associate Professor at the Paul G. Allen School of Computer Science & Engineering at University of Washington @uwcse . Thank you @YejinChoinka and @nlpnoah , i really appreciate your support!

8

3

125

Asli Celikyilmaz

@real_asli

2 years

We surveyed works where LMs are augmented with better reasoning and tools: Exploring integration of reasoning and tool-based augmentation in a fully self-supervised manner can lead to more advanced systems for human-machine interaction.

AK

@_akhaliq

2 years

Augmented Language Models: a Survey abs:

7

101

410

1

14

122

Asli Celikyilmaz

@real_asli

3 months

Excited to share our new resource, 'An Introduction to Vision-Language Modeling'! 📘 Dive into the mechanics of VLMs, from mapping images to language to extending to videos. A collaborative effort to boost understanding and innovation in this promising field. 🚀

AI at Meta

@AIatMeta

3 months

📝 New from FAIR: An Introduction to Vision-Language Modeling. Vision-language models (VLMs) are an area of research that holds a lot of potential to change our interactions with technology, however there are many challenges in building these types of models. Together with a set

37

506

2K

2

11

89

Asli Celikyilmaz

@real_asli

5 years

Our paper has just received Best Student Paper award at #CVPR2019 . Another fabulous MSR intern work! Congratulations @xwang_lk Qiuyuan Huang @JianfengGao0217 Lei Zhang @shendinghan . Read the blog post for details! @MSFTResearch

Visually grounded natural language navigation is going places

Overall, there are two central questions facing current Vision Language Navigation models. Firstly, should we backtrack? And if so, where should we backtrack to? And secondly, when do we terminate a...

www.microsoft.com

Microsoft Research

@MSFTResearch

5 years

Natural language is tied to how humans interact with their environment. Can we build intelligent agents that can learn to communicate in different modalities as do humans? Microsoft researchers are using Vision-Language Navigation to find out: #CVPR2019

2

24

70

2

7

67

Asli Celikyilmaz

@real_asli

2 years

Our new work on evaluating step-by-step reasoning of LMs is on arxiv. This was really hard! So we introduce a suite of metrics that can score LM’s reasoning in an unsupervised way (reference free) with @OlgaNLP , @moyapchen , @spencerpoff , @LukeZettlemoyer , @CMacota99 , Maryam F.

AI at Meta

@AIatMeta

2 years

ROSCOE is a first-of-its-kind suite of metrics for scoring step-by-step reasoning. By publishing this study we hope to provide a foundation that enables scalable systematic evaluation and benchmarking of new language models. See the paper on arXiv ⬇️

9

36

181

0

12

62

Asli Celikyilmaz

@real_asli

4 years

We have a paper @icmlconf on Transformers for Reinforcement Learning! Talk to us live on Tuesday:

Working Memory Graphs

Transformers have increasingly outperformed gated RNNs in obtaining new state-of-the-art results on supervised tasks involving text sequences. Inspired by this trend, we study the question of how...

arxiv.org

0

5

60

Asli Celikyilmaz

@real_asli

5 years

🎉4 / 4 papers accepted at @ACL2019_Italy ! Thank you incredible @ABosselut , @shendinghan , @eaclark07 and collaborators @JianfengGao0217 , Yizhe Zhang from @MSFTResearch , and @YejinChoinka , @nlpnoah from @uwnlp , @ai2_allennlp . Details to follow!

0

4

57

Asli Celikyilmaz

@real_asli

3 months

🚀 Exciting news! We're open sourcing Chameleon, our early fusion multimodal foundation model from last year. It handles multimodal inputs with text generation outputs, though it was trained for both text and image generation. #OpenSource #AI #ChameleonModel

AI at Meta

@AIatMeta

3 months

Today is a good day for open science. As part of our continued commitment to the growth and development of an open ecosystem, today at Meta FAIR we’re announcing four new publicly available AI models and additional research artifacts to inspire innovation in the community and

99

529

2K

0

6

46

Asli Celikyilmaz

@real_asli

4 years

Why do i feel like there is always a deadline of some sort (e.g., a paper submission, rebuttal for a paper, a workshop proposal, etc.) when i'm at a conference. 🤔of @NAACLHLT @ @EMNLP2020 .

3

1

46

Asli Celikyilmaz

@real_asli

4 months

Excited to release our work showcasing a stable training recipe for fully token-based multi-modal early-fusion auto-regressive models! Amazing team!

AI at Meta

@AIatMeta

4 months

Newly published work from FAIR, Chameleon: Mixed-Modal Early-Fusion Foundation Models. This research presents a family of early-fusion token-based mixed-modal models capable of understanding & generating images & text in any arbitrary sequence. Paper ➡️

27

199

941

2

45

Asli Celikyilmaz

@real_asli

5 years

Looking for summer intership? @MSFTResearch has research internship positions on DL/RL/NLP. Apply online, email or contact us at @NeurIPSConf .

0

11

40

Asli Celikyilmaz

@real_asli

11 months

Exciting news: We equipped LLMs with Branch-Solve-Merge (BSM) reasoning for improved generation capabilities. Great work by @swarnaNLP 👏

Jason Weston

@jaseweston

11 months

🚨 New paper! 🚨 We introduce Branch-Solve-Merge (BSM) reasoning in LLMs for: - Improving LLM-as-Evaluator: makes Llama 70B chat+BSM close to GPT4. GPT4+BSM is better than GPT4. - Constrained Story Generation: improves coherence & constraints satisfied.

2

124

529

0

5

40

Asli Celikyilmaz

@real_asli

5 months

We'll present Branch-Solve-Merge at #NAACL2024

Swarnadeep Saha

@swarnaNLP

6 months

Branch-Solve-Merge will be presented at #NAACL2024 😀 There's growing interest in using LLM as evaluator. BSM improves its correctness+consistency via task decomposition -- generating granular eval criteria & merging them. @omerlevy_ @real_asli @mohitban47 @jaseweston @xl_nlp

0

19

92

2

4

39

Asli Celikyilmaz

@real_asli

4 years

Indeed. We also compiled "Text Generation Evaluation" methods under a recent survey paper: with my co-authors @eaclark07 and @JianfengGao0217 .

Evaluation of Text Generation: A Survey

The paper surveys evaluation methods of natural language generation (NLG) systems that have been developed in the last few years. We group NLG evaluation methods into three categories: (1)...

arxiv.org

Arthur Bražinskas

@abrazinskas_nlp

4 years

A very clearly presented tutorial on Stylized Text Generation. Esp enjoyed a broad overview of methods and evaluation techniques. @OlgaVechtomova #Acl2020

0

4

0

7

37

Asli Celikyilmaz

@real_asli

3 years

A must watch talk by @YejinChoinka on CommonseAI, reasoning, generation and evaluation at @iclr_conf . 👏👏

1

35

Asli Celikyilmaz

@real_asli

11 months

🚀 MemWalker: our new approach to long text processing! 📚 Forget traditional methods! With our unique memory tree structure and LLM prompting, we're outperforming long context, retrieval, & recurrent baselines. Great work by @__howardchen !

Howard Chen

@__howardchen

11 months

Long context models are popular, but is it the final solution to long text reading? We introduce a fundamentally different method, MemWalker: 1. Build a data structure (memory tree) 2. Traverse it via LLM prompting Outperforms long context, retrieval, & recurrent baselines. (1/n)

22

132

857

0

3

34

Asli Celikyilmaz

@real_asli

5 years

*New from MSR* Introducing our work on Transformers for RL! Working Memory Graphs. Great results on BabyAI with factored observations. work with @rickyloynd Roland Fernandez, @mhauskn andAdith Swaminathan @MSFTResearch

1

10

31

Asli Celikyilmaz

@real_asli

2 years

Introducing our new work, MURMUR, a neuro-symbolic modular reasoning approach to generate logical, faithful and diverse summaries from structured inputs w/ @swarnaNLP , @XinyanVYu , @mohitban47 , @ramakanth1729

Swarnadeep Saha

@swarnaNLP

2 years

On LogicNLG, human eval shows MURMUR generates 26% more logically consistent summaries vs direct prompting Had a great internship experience w/ amazing collaborators @XinyanVYu @mohitban47 @ramakanth1729 @real_asli ( @MetaAI + @uncnlp ) Feel free to contact me if any questions 6/n

0

1

10

0

8

31

Asli Celikyilmaz

@real_asli

5 years

🙏thanks for inviting. I really enjoyed talking with everyone after.

Paul Bennett

@pnbennett

5 years

Asli Celikyilmaz packing the room with her talk on Learning Structure in Text Generation in Document Intelligence Workshop #NeurIPS2019 @MSFTResearch

0

16

0

27

Asli Celikyilmaz

@real_asli

11 months

Excited to share Crystal, an LM built for introspective reasoning! Operating on two modes, knowledge introspection & grounded reasoning, Crystal provides answers and the reasoning behind them. Great work by @liujc1998 to be presented at #EMNLP2023 .

Jiacheng Liu

@liujc1998

11 months

Introducing 🔮Crystal🔮, an LM that conducts “introspective reasoning” and shows its reasoning process for QA. This improves both QA accuracy and human interpretability => Reasoning made Crystal clear! Demo: at #EMNLP2023 🧵(1/n)

2

30

138

0

3

27

Asli Celikyilmaz

@real_asli

11 months

🚀 Pushing the boundaries in visual language reasoning! Introducing our recent work on dual-system multi-step reasoning for complex vqa tasks.

Peifeng Wang

@PeifengWang3

11 months

How can we use #LLM to answer a complex question over a chart📊? Check out our new work, DOMINO, a dual-system for multi-step visual language reasoning😎! 📜arXiv: 🧑‍💻code:

1

12

58

0

4

24

Asli Celikyilmaz

@real_asli

6 years

Check out our tutorial at #COLING2018 with awesome Yun-Nung Chen and Dilek Hakkani-tur

DeepDialogue

Introduction Goal-oriented spoken dialogue systems (SDS) have been the most prominent component in today’s virtual personal assistants (VPAs). Among these VPAs, Microsoft’s Cortana, Apple’s Siri,...

sites.google.com

0

6

21

Asli Celikyilmaz

@real_asli

6 years

Our workshop on Methods for Optimizing and Evaluating NLG is accepted. Super excited to work with @ABosselut @gh_marjan @sriniiyer88 @ukhndlwl Hanna Rashkin Alexander Rush @dilekhakkanitur @YejinChoinka @jurafsky

Antoine Bosselut

@ABosselut

6 years

Super excited that our workshop on Methods for Optimizing and Evaluating NLG will be hosted at @NAACLHLT 2019. Reviewers were excited about our invited speakers so make sure to come find out why! See you in Minneapolis! #nlg #neuralgen2019 #nlproc

1

12

47

0

4

21

Asli Celikyilmaz

@real_asli

5 years

Check out our latest paper and the code on "pretrained transformers for abstractive summarization" w/ Andrew Hoang, @ABosselut and @YejinChoinka !

Antoine Bosselut

@ABosselut

5 years

Check out the paper () for more details and more results, and play with the code at 9/

1

2

6

0

3

18

Asli Celikyilmaz

@real_asli

3 months

Check out @jaseweston 's presentation of Branch-Solve-Merge at 2 pm local time in poster session 2 (poster #47 ). @NAACL2024

Swarnadeep Saha

@swarnaNLP

3 months

Folks at #NAACL2024 , check out @jaseweston 's in-person presentation of Branch-Solve-Merge at 2 pm local time in poster session 2 (poster #47 ). BSM plans for+generates sub-problems, solves & then merges them (for both eval+gen tasks). @omerlevy_ @real_asli @mohitban47 @xl_nlp

0

10

29

1

5

18

Asli Celikyilmaz

@real_asli

4 years

Consider submitting papers to the workshop on Neural Conversational AI: Bridging the gap between research and real world with amazing list of speakers!

NeuCAIR @ ICLR-21

Joining workshop On the day of workshop, please enter sessions through this link: https://iclr.cc/virtual/2021/workshop/2133

sites.google.com

0

5

17

Asli Celikyilmaz

@real_asli

4 years

Please consider nominating students!

Microsoft Research

@MSFTResearch

4 years

The Microsoft Research Ada Lovelace Fellowship aims to increase the pipeline of diverse talent receiving advanced computing-related degrees. Second year PhD students could receive tuition & a $42K stipend for 3 years. Submit nominations by August 14, 2020:

2

191

422

0

2

17

Asli Celikyilmaz

@real_asli

6 years

Please tell your friends and students about MSR Dissertation grant program!

Microsoft Research

@MSFTResearch

6 years

Reach the finish line of your doctoral thesis work with help from the Microsoft Research Dissertation Grant. Show us the impact of your research and receive up to $25,000 in funding:

2

102

123

1

5

17

Asli Celikyilmaz

@real_asli

2 years

Do language models really follow the explanations in prompts? To find out more and read about our new findings and approach check out this 🧵and work led by @xiye_nlp , @ramakanth1729 and others.

Xi Ye

@xiye_nlp

2 years

We should prompt LMs by selecting 🚨diverse🚨 in-context examples to solve our target task, because diverse examples may have complementary explanations‼️ 📄Check out our new preprint where we look into how explanations work in-context.

6

23

177

0

1

14

Asli Celikyilmaz

@real_asli

6 years

Excited to be part of the RoboNLP workshop organization taking place together with Spatial Language Understanding (SpLU). Submit papers soon, it will be a great @NAACLHLT 2019 workshop.

Parisa Kordjamshidi

@Kordjamshidi

6 years

Spatial Language Understanding (SpLU) & Grounded Communication for Robotics (RoboNLP) are joining forces @NAACLHLT 2019! Exciting topics (see below) and speakers! See CFP for more details -- Deadline March 6! #robonlp #nlproc

0

16

48

0

3

14

Asli Celikyilmaz

@real_asli

3 months

If you are at @naaclmeeting and interested about our recent work on LLM reasoning, listen to Shridhar's talk on Tuesday at 17:30 at the ML for NLP.

Kumar Shridhar

@JupyterAI

3 months

Come check out our Oral presentation tomorrow at 17:30 in the ML for NLP track #NAACL2024

1

6

23

1

13

Asli Celikyilmaz

@real_asli

3 years

Come listen amazing @byryuer talk about our recent work today at 8am PT Aug4 15D, happening now! See the 🧵👇

Shiyue Zhang

@byryuer

3 years

Hi #ACL2021nlp , check out our new work “EmailSum: Abstractive Email Thread Summarization” (11-12p ET Aug4 Wed 15D). 😀 w @real_Asli @JianfengGao0217 @MohitBan47 ( @uncnlp + @MSFTResearch ) Github: Video: 🧵⬇️

1

9

59

0

1

13

Asli Celikyilmaz

@real_asli

5 years

Check out the @NeuralGen Workshop on Thursday if you are at @NAACL2019 ! We have great program and speakers!

NeuralGen Workshop

@NeuralGen

5 years

The *final schedule* and *best papers* of @NeuralGen workshop are out 🎉 Congratulation to the best papers authors! We are really excited about the amazing line-up of speakers & great posters! Full details on the website: See you soon in Minneapolis 🏙️

3

23

68

0

2

13

Asli Celikyilmaz

@real_asli

4 months

I am proud to be part of the alignment and safety team! @ramakanth1729 @andrew_e_cohen @koustuvsinha @aramHmarkosyan @ellenxtan0 @Tianlu_Wang @ping_iris_yu @OlgaNLP @LukeZettlemoyer @gargighosh

0

1

11

Asli Celikyilmaz

@real_asli

2 months

🚀Llama 3.1 is here!

AI at Meta

@AIatMeta

2 months

Starting today, open source is leading the way. Introducing Llama 3.1: Our most capable models yet. Today we’re releasing a collection of new Llama 3.1 models including our long awaited 405B. These models deliver improved reasoning capabilities, a larger 128K token context

269

2K

6K

0

11

Asli Celikyilmaz

@real_asli

6 years

Our recent paper on learning hierarchical contextual structures using reinforcement learning for generating stories is accepted at: #aaai2019 :

Hierarchically Structured Reinforcement Learning for Topically...

We propose a hierarchically structured reinforcement learning approach to address the challenges of planning for generating coherent multi-sentence stories for the visual storytelling task. Within...

arxiv.org

0

11

Asli Celikyilmaz

@real_asli

5 years

At @ACL2019 workshops. @JianfengGao0217 is talking about Deep Learning and dialog maner policy methods of social bot Xiaolce.

Yun-Nung Vivian Chen

@YunNungChen

5 years

Jianfeng is delivering the speech about the most popular social bot - XiaoIce at NLP4ConvAI. #acl2019nlp #ACL2019

0

9

0

10

Asli Celikyilmaz

@real_asli

5 years

Congratulations Lin Xiao @MSFTResearch for the test of time award at #NeurIPS2019 👏👏👏

Sebastien Bubeck

@SebastienBubeck

5 years

Congratulations to our colleague Lin Xiao @MSFTResearch for the #NeurIPS2019 test of time award!!! Online convex optimization and mirror descent for the win!! (As always? :-).)

1

45

248

0

1

11

Asli Celikyilmaz

@real_asli

6 years

Check this great work and new findings on batch normalization to appear at @iclr2019 by @Greg ! @MSFTResearch 👏👏👏

Greg Yang

@TheGregYang

6 years

1/4 Batchnorm causes grad explosion in random-init MLP! Can’t fix this by changing nonlinearities! Relu+batchnorm explodes grad norm^2 by >=1.47 per layer, but linear activation minimizes the explosion rate at (B-2)/(B-3), B=batchsize. Our ICLR 2019 paper

6

55

190

0

10

Asli Celikyilmaz

@real_asli

7 years

#acl2017nlp Deep Learning for Dialog Modelling! Almost full session.

2

3

10

Asli Celikyilmaz

@real_asli

6 years

Congratulations to the 2019 winners of Microsoft Research PhD Fellowship. Very excited that this year we have very stong winner from NLP area, congrats Ram! @ramakanth1729

Microsoft Research

@MSFTResearch

6 years

We're excited to announce the 2019 winners of the Microsoft Research Ada Lovelace Fellowship and PhD Fellowship! Explore inspiring projects from talented PhD students in computing-related fields:

1

41

142

2

10

Asli Celikyilmaz

@real_asli

6 years

AI Deadlines !

0

3

8

Asli Celikyilmaz

@real_asli

11 years

Deep learning in your browser http://t.co/2Ftaym95wZ

0

5

9

Asli Celikyilmaz

@real_asli

5 years

Come see our SpLU-RoboNLP 2019 workshop on June 6! @NAACL2019 . We have great program and speakers

Jesse Thomason

@_jessethomason_

5 years

The SpLU-RoboNLP 2019 workshop is excited to bring many great invited speakers together to discuss work across language interactions with embodied agents, spatial language understanding, and language-driven human-robot interaction! Full proceedings:

1

9

25

0

1

9

Asli Celikyilmaz

@real_asli

7 months

Check 👇 out! 🔥

Jiacheng Liu

@liujc1998

7 months

It’s year 2024, and n-gram LMs are making a comeback!! We develop infini-gram, an engine that efficiently processes n-gram queries with unbounded n and trillion-token corpora. It takes merely 20 milliseconds to count the frequency of an arbitrarily long n-gram in RedPajama (1.4T

11

90

383

0

9

Asli Celikyilmaz

@real_asli

4 years

HoloLens 2 provides new capabilities that can be used in conjunction with Research Mode. Specifically, articulated hand-tracking and eye-tracking which can be accessed through APIs while using research mode, allowing for a richer set of experiments.

Microsoft HoloLens 2: Improved Research Mode to facilitate computer vision research - Microsoft...

Since its launch in November 2019, Microsoft HoloLens 2 has helped enterprises in manufacturing, construction, healthcare, and retail onboard employees more quickly, complete tasks faster, and...

www.microsoft.com

0

7

Asli Celikyilmaz

@real_asli

7 years

Excited about our paper "Composite Task-Completion Dialogue System via Hierarchical Deep Reinforcement Learning" accepted! #emnlp2017 "

1

8

Asli Celikyilmaz

@real_asli

5 years

👏👏👏Congratulations to all the authors for the win and great talk!

Andrea Madotto

@AndreaMadotto

5 years

thanks @real_asli for the pictures and for helping organizing the workshop. 😊And finally thanks to @apple for providing a pair of airpods pro to each of the authors 🎉

0

3

0

7

Asli Celikyilmaz

@real_asli

5 years

#AAAI20 A real-world usage of RL!

Debadeepta Dey

@debadeepta

5 years

At #AAAI20 @adityamodi94 will present our latest metareasoning approach using RL for optimizing software pipelines on-the-fly. A real-world usage of RL! with Alekh Agarwal, Adith Swaminathan, @besanushi , @seanandrist , @erichorvitz

0

5

30

0

1

6

Asli Celikyilmaz

@real_asli

7 years

Reading material for vacation

0

2

5

Asli Celikyilmaz

@real_asli

5 years

Yay, Sudha! 🙌 @raosudha89

Pradeep Dasigi

@pdasigi

5 years

#nlphighlights 105: Question Generation with @raosudha89 . We discussed an overview of the settings in which you would want to generate questions, and focused on Sudha's work of generating clarification questions. Thanks for joining us, Sudha!

1

12

40

1

0

5

Asli Celikyilmaz

@real_asli

5 years

Check out the Search Oriented Conversational AI workshop #SCAI_workshop #ijcai2019

Julia Kiseleva

@julia_kiseleva

5 years

@scai_workshop at @TheWebConf is happy to announce the invited talk by Jayesh Govindarajan (VP Data Science at @salesforce ) on "The Conversational Enterprise" #SCAI_workshop #TheWebConf #ConversationalAI

0

4

8

0

5

Asli Celikyilmaz

@real_asli

7 years

The Deep Learning Group at Microsoft Research AI lab seeks applicants for a postdoctoral research position in the areas of deep learning, artificial intelligence, and related fields. via @MSFTResearch

0

3

4

Asli Celikyilmaz

@real_asli

5 years

ACL 2020 - First CFP is out!

Isabelle Augenstein

@IAugenstein

5 years

The @aclmeeting deadline has been announced, and it's quite soon: Get your long + short papers ready for 9 December! #NLProc #acl2020 #acl2020nlp

2

19

52

0

4

Asli Celikyilmaz

@real_asli

6 years

Our poster @ICLR18 : "Learning and Analyzing Vector Encoding of Symbolic Representations"

0

1

4

Asli Celikyilmaz

@real_asli

6 years

Convolutional networks should be regarded as a natural starting point for sequence modeling tasks!

Andrej Karpathy

@karpathy

6 years

"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling" good to see more papers on the topic - always start with a CNN before reaching for an RNN. You'll be surprised with how far you can get.

9

343

1K

0

1

4

Asli Celikyilmaz

@real_asli

5 years

@susan_dumais Congratulations on the #LifetimeResearchAward !

Jaime Teevan

@jteevan

5 years

Thrilled to get to celebrate my longtime friend and mentor, @susan_dumais , with the #SIGCHI community. Congratulations on the #LifetimeResearchAward ! #HCI #IR

4

12

67

0

4

Asli Celikyilmaz

@real_asli

1 year

@tallinzen Congratulations, Tal!

0

1

Asli Celikyilmaz

@real_asli

5 years

@xwang_lk @cvpr2019 @WilliamWangNLP @MSFTResearch 👏👏👏👏👏

0

3

Asli Celikyilmaz

@real_asli

6 years

Meet new fellows : @MSFTResearch

0

1

3

Asli Celikyilmaz

@real_asli

6 years

I think next i should work on an article to poster generator!

0

3

Asli Celikyilmaz

@real_asli

6 years

no more rouge155 !

Peter J. Liu

@peterjliu

6 years

My team has open-sourced a pure python implementation of ROUGE (Apache 2 license) that can be used as a replacement for the original perl version (which also had an ambiguous license). @harvardnlp @stanfordnlp

4

78

239

0

3

Asli Celikyilmaz

@real_asli

3 years

@faeze_brh @YejinChoinka @iclr_conf I would assume so, tagging @iatitov .

1

0

3

Asli Celikyilmaz

@real_asli

7 years

@ashwinram @AlexRudnicky @AlborzGr @dilekhakkanitur It was great to be on the @ConversationalAL panel! Thanks #JasonWilliams , @AlborzGr , @AntoineBordes and all the other organizers.

0

3

Asli Celikyilmaz

@real_asli

3 years

@mbodhisattwa @facebookai @yboureau Looking forward to working together 🤗

1

0

3

Asli Celikyilmaz

@real_asli

3 years

Awesome news, well deserved! Congratulations @ABosselut

Antoine Bosselut

@ABosselut

3 years

It’s an honor to have been named to the #ForbesUnder30 Europe list in Science & Healthcare. Looking forward to joining @ICepfl @EPFL in a few months and growing research thrusts in #NLProc , knowledge representations, and reasoning.

21

11

168

0

3

Asli Celikyilmaz

@real_asli

5 years

@sleepinyourhat @jackiecklo Maybe change the location? Too late ? ICASSP 2018 was originally going to take place in Seoul, Korea, but was later moved to Calgary, Canada, citing political tensions in North Korea back then.

0

3

Asli Celikyilmaz

@real_asli

7 years

IJCNLP 2017 in Taipei, Taiwan Long and Short Papers Submission Deadline: July 7, 2017

0

2

Asli Celikyilmaz

@real_asli

9 years

First Call: #NIPS2015 Workshop on Spoken Language Understanding & Interaction http://t.co/0C0uU9dk4S. Amazing speakers! Submission October 4

Home | slunips2015

slunips2015.wixsite.com

0

7

2

Asli Celikyilmaz

@real_asli

10 years

Power of Deep Learning - Microsoft Research http://t.co/r67eagxmYi via @MSFTResearch

0

2

Asli Celikyilmaz

@real_asli

3 months

@swarnaNLP @mohitban47 @uncnlp @AIatMeta @jaseweston Huge congrats @swarnaNLP ! 🎉 Looking forward to working with you on reasoning research.

1

0

2

Asli Celikyilmaz

@real_asli

7 years

Microsoft creates an AI research lab to challenge Google and DeepMind via @techcrunch

0

2

Asli Celikyilmaz

@real_asli

8 years

@NipsConference Alon Musk

0

2

Asli Celikyilmaz

@real_asli

5 years

same here! Also missing the tutorials due to ACL deadline. At least i get to look at this amazing mountain-view! Good luck!

🇺🇦 Alex Polozov

@Skiminok

5 years

Current status: missing #NeurIPS2019 workshops, wearing sweater+overcoat in my ❄freezing❄ Vancouver hotel room, fighting LaTeX to finish our ACL submission. Not the best timing, @aclmeeting ☹

1

0

5

1

0

2

Asli Celikyilmaz

@real_asli

6 years

@mohitban47 @ramakanth1729 @MSFTResearch @unccs @unccollege @UNC @UNCResearch Congrats @ramakanth1729 !

1

0

2

Asli Celikyilmaz

@real_asli

8 years

Probably thousand+ people at #NIPS2016 Deep RL workshop.

0

2

Asli Celikyilmaz

@real_asli

7 years

@zacharylipton @smolix Becoming to be a great book @zacharylipton .

0

1

2

Asli Celikyilmaz

@real_asli

7 years

@mohitban47 @sivareddyg @percyliang @karlmoritz (2) great if you invite dialog researchers from academia as well. Also I would be more than happy to help for the next round 😉

1

0

2

Asli Celikyilmaz

@real_asli

5 years

@cpburgess_ @Azhag @RishabhKabra @irinavlh Great work! The VAE component is much simplified version of attend-infer-repeat paper with less latent variables, and introduces the background component (somewhat similar to using global variable in Disentangled Sequential Autoencoder ).

Disentangled Sequential Autoencoder

We present a VAE architecture for encoding and generating high dimensional sequential data, such as video or audio. Our deep generative model learns a latent representation of the data which is...

arxiv.org

0

2

Asli Celikyilmaz

@real_asli

2 years

@tallinzen @RTomMcCoy @jacobandreas Congrats Dr. @RTomMcCoy !

1

0

2

Asli Celikyilmaz

@real_asli

7 years

“The GAN Zoo” by @hindupuravinash

0

2

Asli Celikyilmaz

@real_asli

7 years

Is there a recent GAN survey paper covering recent methods ?

0

1

Asli Celikyilmaz

@real_asli

5 years

@ybisk @SCSatCMU @LTIatCMU @CMU_Robotics Congrats @ybisk

0

1

Asli Celikyilmaz

@real_asli

6 years

Silicon Valley’s Giants Take Their Talent Hunt to Cambridge

0

1

Asli Celikyilmaz

@real_asli

10 years

Microsoft's new personal assistant = Cortana http://t.co/zFRRpR9VUv

1

0

1

Asli Celikyilmaz

@real_asli

3 years

@najoungkim @BULinguistics @NYUDataScience Congratulations 👏 @najoungkim

0

1

Asli Celikyilmaz

@real_asli

7 years

@mohitban47 @DARPA @unccs @UNC Congrats @mohitban47

1

0

1

Asli Celikyilmaz

@real_asli

4 years

@xwang_lk @UCSC_BSOE @ucsc 👏👏👏

1

0

1

Asli Celikyilmaz

@real_asli

3 years

@WilliamWangNLP Congratulations William 🎉🥳🥂

1

0

1

Asli Celikyilmaz

@real_asli

3 months

@adawan919 @AIatMeta ii. Yes, these are indeed statistical methods - they learn from data by optimizing a loss function, which is a statistical process. But i think the performance of such models also contribute to their ability to learn hierarchical representations or perform transfer learning etc.

1

0

1

Asli Celikyilmaz

@real_asli

3 years

@complingy @VeredShwartz @UBC_CS Congratulations @VeredShwartz !

0

1

Asli Celikyilmaz

@real_asli

5 years