Photos and videos
Thy Thy retweeted
18 Oct 2023
As capabilities of foundation models are waxing, *transparency* is waning. How do we quantify transparency? We introduce the Foundation Models Transparency Index (FMTI), evaluating 10 foundation model developers on 100 indicators.
crfm.stanford.edu/fmti/
11
68
239
54,823
Thy Thy retweeted
29 Mar 2022
We are excited to announce the public beta of the @UKPLab SQuARE platform for Question Answering research square.ukp-lab.de. Run, deploy, and compare QA Skills online without writing code! 🚀
Check out our ACL 2022 paper 📜 arxiv.org/abs/2203.13693 for more details!
2
23
67
Thy Thy retweeted
20 Oct 2021
Simulated Chats for Building Dialog Systems: Learning to Generate Conversations from Instructions arxiv.org/abs/2010.10216
1
Thy Thy retweeted
4 Jun 2021
Contrastive learning aims to learn representation such that similar samples stay close, while dissimilar ones are far apart. It can be applied to supervised / unsupervised data and has been shown to achieve good results on various tasks.
📚 A long read: lilianweng.github.io/lil-log…
13
271
1,346
Thy Thy retweeted
21 May 2021
New work: "Unsupervised speech recognition"
TL;DR: it's possible for a neural network to transcribe speech into text with very strong performance, without being given any labeled data.
Paper: ai.facebook.com/research/pub…
Blog: ai.facebook.com/blog/wav2vec…
Code: github.com/pytorch/fairseq/t…
21 May 2021
Today we are announcing our work on building speech recognition models without any labeled data! wav2vec-U rivals some of the best supervised systems from only two years ago.
Paper: ai.facebook.com/research/pub…
Blog: ai.facebook.com/blog/wav2vec…
Code: github.com/pytorch/fairseq/t…
3
92
446
Thy Thy retweeted
26 Apr 2021
day1: i have an idea!
day2: i implemented my idea and added it to the NN and it improved 10 points!
day3: oops i had a bug and "my idea" was turned off when i achieved this gain, it was just hyper-param
how many times did this happen to you?
how many times you didn't reach day3?
9
9
281
Thy Thy retweeted
10 Mar 2021
🚨 New Paper !🚨
Want to measure how different groups (e.g. GOP v Dems) "understand" words differently (e.g."immigration")? check out our "Embedding Regression" paper (w @prodriguezsosa @b_m_stewart). Inference framework software. Comments welcome! (1/4)
github.com/prodriguezsosa/Em…
3
44
207
Thy Thy retweeted
6 Mar 2021
Just one week till the start of MIT's @edXOnline course on Machine Learning for Healthcare - open to the whole world and free to audit! edx.org/course/machine-learn…
7
120
464
Thy Thy retweeted
10 Feb 2021
Such a important formula, such an ambiguous mess in matrix notation...
What if there was a better way?
namedtensor.github.io/
19
99
612
Thy Thy retweeted
20 Jan 2021
The ACL Anthology is looking for a (paid) assistant to help with routine operations. There will also be time during slow periods to help with the implementation of new futures and with future planning. Please share! github.com/acl-org/acl-antho……
1
39
56
Thy Thy retweeted
1 Jul 2020
Happy to be giving an #ICML2020 tutorial on Bayesian Deep Learning and Probabilistic Model Construction. This area has made astounding progress in the last year. I'm grateful for the opportunity and thank the organizers for their efforts!
icml.cc/Conferences/2020/Sch…
9
105
627
Thy Thy retweeted
30 Jun 2020
🥳Really excited to be attending #MLSS2020. Great set of talks by @bschoelkopf & Stefan Bauer starting from 101 causality to Representation Learning for Disentanglement 💯! Re-watch them here:
📺 (Part I): youtu.be/btmJtThWmhA
📺 (Part II): youtu.be/9DJWJpn0DmU
1
43
263
Thy Thy retweeted
9 Jun 2020
Exploration strategies in deep RL are such a critical topic. I almost immediately regretted it when I started writing on this big subject because it has so much more content than I expected.
But here it comes, phew:
lilianweng.github.io/lil-log…
25
314
1,537
Thy Thy retweeted
28 Apr 2020
Is there a formal definition of what it means for a language model to "know" something? E.g. which of the following scenarios counts as knowing that Paris is the capital of France?
12
12
105
Thy Thy retweeted
25 Apr 2020
As we near the ACL camera-ready deadline, here's a checklist that will help you make sure the paper looks nice and the repo is maintained even after you've graduated and left to pursue a professional surfing career in the Philippines. Did I miss anything?
3
36
145
Thy Thy retweeted
3 Apr 2020
Given the current situation, @tpilehvar and I have decided to openly release the first draft of our book “Embeddings in Natural Language Processing”. We also thank @MorganClaypool for agreeing to this early draft release.
Link: josecamachocollados.com/book…
20
308
915
Thy Thy retweeted
11 Mar 2020
Efficient BERT models from Google Research, now available at github.com/google-research/b…!
We hope our 24 BERT models with fewer layers and/or hidden sizes will enable research in resource-constrained institutions and encourage building more compact models.
arxiv.org/abs/1908.08962
2
191
597
Thy Thy retweeted
13 Jan 2020
2020 edition of CMU CS11-747 "Neural Networks for NLP", is starting tomorrow! We (co-teacher @stefan_fee and 6 wonderful TAs) restructured it a bit to be more focused on "core concepts" used across a wide variety of applications. phontron.com/class/nn4nlp202… 1/2
8
67
292
Thy Thy retweeted
13 Jan 2020
🔥 Introducing Tokenizers: ultra-fast, extensible tokenization for state-of-the-art NLP 🔥
➡️github.com/huggingface/token…
9
192
848
Thy Thy retweeted
7 Jan 2020
I completed my 1st data science project ~30 years ago. Since then I've been continuously developing a questionnaire I use for all new data projects, to ensure the right info is available from the start.
I'm sharing it publicly today for the first time.
fast.ai/2020/01/07/data-ques…
50
898
3,191