MIT NLP Group @mitnlp

MIT Natural Language Processing group. nlp.csail.mit.edu Cambridge, MA Joined September 2017

Tweets

29
Followers

897
Following

22
Likes

16

Anastasios Nikolas Angelopoulos @ml_angelopoulos

3 years ago

I’m thrilled to announce Conformal Risk Control: a way to bound quantities other than coverage with conformal prediction. arxiv.org/abs/2208.02814 Check out the worked examples in CV and NLP! The best part is: it’s exactly the same algorithm as split conformal prediction🤯🧵1/5

2 29 141 0 42

Download Image

YujiaBao @yujia_bao

3 years ago

Need to debias your new task? Learn how, from your old one. Check out our #ICML2022 paper "Learning Stable Classifiers by Transferring Unstable Features" with @CodeTerminator and @BarzilayRegina Paper -> arxiv.org/abs/2106.07847 Code -> github.com/YujiaBao/tofu

2 15 36 0 8

Download Image

Tal Schuster @TalSchuster

4 years ago

New Preprint with @adamjfisch, T.Jaakkola and @BarzilayRegina. We present Consistent Accelerated Inference via 𝐂onfident 𝐀daptive 𝐓ransformers (CATs) CATs can speed up inference 😺 while guaranteeing consistency 😼. The code is available🙀 🔗people.csail.mit.edu/tals/static/Co… #NLProc

3 9 50 0 16

Download Image

Adam Fisch @adamjfisch

4 years ago

Large pre-trained Transformers are great, but expensive to run. But making them more efficient (e.g., early exits) can give undesirable performance hits. In our new work, we speed up inference while guaranteeing consistency with the original model up to a specifiable tolerance.

Tal Schuster @TalSchuster

4 years ago

3 9 50 0 16

Download Image

1 6 29 0 5

Adam Fisch @adamjfisch

4 years ago

New #NAACL2021 paper out on robust fact verification. Sources like Wikipedia are continuously edited with the latest information. In order to keep up, our models need to be sensitive to these changes in evidence when verifying claims. Work with @TalSchuster and @BarzilayRegina!

Tal Schuster @TalSchuster

4 years ago

3 4 17 0 3

Download Image

0 5 13 0 1

Tal Schuster @TalSchuster

4 years ago

Is your Fact Verification model robust enough? Consider adding #VitaminC 🍊 Check out our new #NAACL2021 paper: "Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence" with @adamjfisch and @BarzilayRegina 🔗 arxiv.org/abs/2103.08541 #NLProc #FakeNews📰 🧵1/N

3 4 17 0 3

Download Image

Tal Schuster @TalSchuster

6 years ago

In our @IEEESSP paper, led by @RoeiSchuster, we control the embeddings of words by introducing minimal changes to the pretraining data (e.g. #Wiki edits). This #word_embeddings attack affects many downstream #NLProc tasks! @cornell_tech @MIT_CSAIL link: arxiv.org/abs/2001.04935

Roei Schuster @RoeiSchuster

6 years ago

0 7 27 0 1

Download Image

0 3 6 0 0

MIT NLP Group @mitnlp

6 years ago

Congratulations!

YujiaBao @yujia_bao

6 years ago

Congratulations!

1 12 33 0 3

0 0 3 0 0

Shiyu Chang @CodeTerminator

6 years ago

#NeurIPS2019 Our work with MIT improves the interpretability of NLP models with an adversarial class-wise rationalization technique, which can find explanations towards any given class. Poster: Tue @ East Exhibition Hall B + C #1. @MITIBMLab @neurobongo @MIT_CSAIL @Bishop_Gorov

1 6 27 0 2

Download Image

MIT NLP Group @mitnlp

6 years ago

If you're at @emnlp2019, don't miss our talks: Towards Debiasing Fact Verification Models * Wednesday 15:42 (2B) * @TalSchuster @darshj_shah Working Hard or Hardly Working: Challenges of Integrating Typology into Neural Dependency Parsers * Thursday 15:30 (201A) * @adamjfisch

0 2 8 0 0

Darsh J Shah @darshj_shah

6 years ago

Check-out our new paper - arxiv.org/pdf/1909.13838… Automatic Fact-guided sentence modification. Method to automatically modify the factual information in a sentence. Joint work with @str_t5 , Prof. Regina Barzilay.

0 6 8 0 0

Tal Schuster @TalSchuster

6 years ago

Are we protected from GPT-2, #GROVER style models generating fake content? What happens if they are also used legitimately as writings assistants? Check our new report: arxiv.org/abs/1908.09805 with @RoeiSchuster, @Darsh71307636, Regina Barzilay. #NLProc #emnlp2019 #FakeNews #GPT2

0 6 10 0 0

Download Image

YujiaBao @yujia_bao

6 years ago

Few-shot Text Classification with Distributional Signatures. What happens if you take meta-learning for vision and apply it to NLP? Prototypical Networks with lexical features perform worse than nearest neighbors on new classes. How can we do better? ;) arxiv.org/abs/1908.06039

1 14 36 0 4

Download Image

Tal Schuster @TalSchuster

6 years ago

Our #emnlp2019 paper is now on arxiv:arxiv.org/abs/1908.05267 * Extending #FEVER (fact-checking) eval dataset to eliminate bias. * Regularizing the training to alleviate the bias. Coauthors: Darsh Shah, @yeodontsay, Daniel Filizzola, @ESantus, Regina Barzilay @emnlp2019 #nlproc

1 4 18 0 0

Download Image

MRQA Workshop @MRQA_workshop

6 years ago

Development datasets released! 6 in-domain and 6 out-of-domain including BioASQ, DROP, DuoRC, RACE, RelationExtraction, TextbookQA! Also released BERT baseline results. All the information at github.com/mrqa/MRQA-Shar…. Check out and let us know if you have questions! #mrqa2019

0 29 67 0 8

MIT NLP Group @mitnlp

6 years ago

The new shared task in QA at @MRQA2019 Workshop is released

MRQA Workshop @MRQA_workshop

6 years ago

The new shared task in QA at @MRQA2019 Workshop is released

0 28 39 0 2

0 0 2 0 0

Yujie Qian @Yujie_Qian

7 years ago

Our paper "GraphIE: A Graph-Based Framework for Information Extraction" has been accepted to #NAACL2019. We study how to model the graph structure of the data in various IE tasks. Joint work with @ESantus @jiangfeng1124 @ZhijingJin and Regina Barzilay. (arxiv.org/abs/1810.13083)

0 4 9 0 0

MIT NLP Group @mitnlp

7 years ago

Congratulations Tal! @str_t5

Tal Schuster @TalSchuster

7 years ago

Congratulations Tal! @str_t5

4 13 53 0 7

0 0 5 0 0

David Alvarez Melis @elmelis

7 years ago

Our paper: "Gromov-Wasserstein Alignment of Word Embedding Spaces" is now available (arxiv.org/abs/1809.00013). TL;DR: The Gromov-Wasserstein distance provides a simple, principled objective to align (w/o supervision) word embedding spaces, even of different dimensionality!