ICLR 2020 Recordings

All recordings for papers and workshops are now available to everyone!

​​MLSUM: The Multilingual Summarization Corpus

The first large-scale MultiLingual SUMmarization dataset, comprising over 1.5M article/summary pairs in French, German, Russian, Spanish, and Turkish. Its complementary nature to the CNN/DM summarization dataset for English.

For each language, they selected an online newspaper from 2010 to 2019 which met the following requirements:
0 being a generalist newspaper: ensuring that a broad range of topics is represented for each language allows minimizing the risk of training topic-specific models, a fact which would hinder comparative cross-lingual analyses of the models.
1 having a large number of articles in their public online archive.
2 Providing human written highlights/summaries for the articles that can be extracted from the HTML code of the web page.

Also, in this paper, you can remember about similar other datasets

paper: https://arxiv.org/abs/2004.14900
github: https://github.com/recitalAI/MLSUM
Instructions and code will soon.

#nlp #corpus #dataset #multilingual

Shear, Torsion and Pressure Tactile Sensor via Plastic Optofiber Guided Imaging

CNN applied to tactile sensing

YouTube: https://youtu.be/7wsURXJrq7U
Paper: https://ieeexplore.ieee.org/abstract/document/8990014

​​Martin Calvino's AI-inspired art is such an evoking meta-narrative of "art imitating tech imitating art"

https://www.martincalvino.co/paintings

#ai #art #abstract

🤖 The NetHack Learning Environment


#Facebook launched new Reinforcement Learning environment for training agents based on #NetHack game. Nethack has nothing to do with what is considered common cybersecurity now, but it is an early terminal-based Minecraft (as a matter of fact one might say «console NetHack game» to go ‘all in’ in a word pun game).

NetHack is a wonderful RPG adventure game, happening in dungeon. Players control @ sign moving in ASCII-based environment, fighting enemies and doing quests. If you haven’t played it you are missing a whole piece of gaming culture and our editorial team kindly cheers you on at least trying to play it. Though now there lots of wikis and playing guides, canonicial way to play it is to dive into source code for looking up the keys and getting the whole idea of what to expect from different situations.

#NLE uses python and ZeroMQ and we are looking forward to interesting applications or showcases to arise from this release.

Github: https://github.com/facebookresearch/nle
NetHack official page: http://nethack.org

#RL

​​The Cost of Training NLP Models: A Concise Overview

The authors review the cost of training large-scale language models, and the drivers of these costs.

More at the paper: https://arxiv.org/abs/2004.08900

#nlp #language

By the coincedence we received a couple of help requests with trivial questions.

Thank you for using @opendatasciencebot and we will address the issue in our upcoming Ultimate Post on Where To Start with Data Science.

Our channel doesn’t advertise or spam, so our editorial team runs only on enthuasism (and because we want to give back to the community and spread worthy information). Therefore we do not have enough resources to provide response on technical questions regarding syntax and other errors and we can not help with your requests.

We can only advice to try stackoverflow for getting down to the source of your problems.

​​CREME – python library for online ML

All the tools in the library can be updated with a single observation at a time, and can therefore be used to learn from streaming data.

The model learns from one observation at a time, and can therefore be updated on the fly. This allows to learn from massive datasets that don't fit in main memory. Online machine learning also integrates nicely in cases where new data is constantly arriving. It shines in many use cases, such as time series forecasting, spam filtering, recommender systems, CTR prediction, and IoT applications. If you're bored with retraining models and want to instead build dynamic models, then online machine learning might be what you're looking for.

Here are some benefits of using creme (and online machine learning in general):
• incremental – models can update themselves in real-time
• adaptive – models can adapt to concept drift
• production-ready – working with data streams makes it simple to replicate production scenarios during model development
• efficient – models don't have to be retrained and require little compute power, which lowers their carbon footprint


api reference: https://creme-ml.github.io/content/api.html
github: https://github.com/creme-ml/creme

#ml #online #learning

​​the latest news from :hugging_face_mask:

[0] Helsinki-NLP

With v2.9.1 released 1,008 machine translation models, covering of 140 different languages trained with marian-nmt

link to models: https://huggingface.co/models?search=Helsinki-NLP%2Fopus-mt


[1] updated colab notebook with the new Trainer

colab: https://t.co/nGQxwqwwZu?amp=1


[2] NLP – library to easily share & load data/metrics already providing access to 99+ datasets!

features
– get them all: built-in interoperability with pytorch, tensorflow, pandas, numpy
– simple transparent pythonic API
– strive on large datasets: nlp frees you from RAM memory limits
– smart cache: process once reuse forever
– add your dataset

colab: https://t.co/37pfogRWIZ?amp=1
github: https://github.com/huggingface/nlp


#nlp #huggingface #helsinki #marian #trainer # #data #metrics

🔥Nvidia product release livestream


https://youtu.be/nurL3N1Etuc

​​Transformer Reasoning Network for Image-Text Matching and Retrieval

A new approach for image-text matching using Faster-RCNN Bottom-Up and BERT.

Usually, downstream applications use the ResNet or one of its variants as the backbone CNN. Its simple and modular design can be easily adapted to various tasks. However, since ResNet models are originally designed for image classification, they may not be suitable for various downstream applications because of the limited receptive-field size and lack of cross-channel interaction.

Authors suggest an architecture, where images and texts are processed at first, and then their representations are combined.

Main contributions of the paper:
- TERN Architecture
- NDCG metric in addition to Recall@K
- show SOTA result on the benchmark


Paper: https://arxiv.org/abs/2004.09144
Code: https://github.com/mesnico/TERN

#computervision #deeplearning #bert #imagetextmatching

​​Brilliant article on different float types used in DL

FP64, FP32, FP16, BFLOAT16, TF32, and other members of the ZOO by Grigory Sapunov

Link: https://medium.com/@moocaholic/fp64-fp32-fp16-bfloat16-tf32-and-other-members-of-the-zoo-a1ca7897d407

#dl #engineering #cs #floatingpoint

S2IGAN — Speech-to-Image Generation via Adversarial Learning

Authors present a framework that translates speech to images bypassing text information, thus allowing unwritten languages to potentially benefit from this technology.

ArXiV: https://arxiv.org/abs/2005.06968
Project: https://xinshengwang.github.io/project/s2igan/

#DL #audiolearning #speechrecognition

​​Blackcellmagic extension for jupyter

There are people who like dark themes and are fond of them, but this extension helps to format the code.

Extension: https://github.com/csurfer/blackcellmagic
Black formatter: https://github.com/psf/black

#codestyle #python #jupyter

Dear subscribers we remind you that our channel remains focused on DS-related news and updates, so you are welcome to read and submit any DS-related news to our separate repo: https://github.com/open-data-science/ultimate_posts/tree/master/COVID_2019

PRs are mostly welcome.

​​CURL: Contrastive Unsupervised Representations for Reinforcement Learning

This paper introduces a new method that significantly improves the sample efficiency of RL algorithms when learning from raw pixel data.

CURL architecture consists of three models: Query Encoder, Key Encoder, and RL agent. Query Encoder outputs embedding which used in RL agent as state representation. Contrastive loss computed from outputs of Query Encoder and Key Encoder. An important thing is that Query Encoder learns to minimize both RL and contrastive losses which allow all models to be trained jointly.

The method was tested on Atari and DeepMind Control tasks with limited interaction steps. It showed SOTA results for most of these tasks.

Paper: https://arxiv.org/abs/2004.04136.pdf
Code: https://github.com/MishaLaskin/curl


#rl #agent #reinforcement #learning

​​Mypy stubs, i.e., type information, for numpy, pandas and matplotlib for your #ds #python projects.

Lots of functions are already typed, but a lot is still missing (numpy and pandas are huge libraries).

https://github.com/predictive-analytics-lab/data-science-types

Remote online PyDoma meetup for russian-speaking community.

#PyData — worldwide events about anything related to storage, processing or visualization data with #python.

Link: https://pydata.timepad.ru/event/1318959/

P.S. We are happy to promote any national online activities, which are valuable and open to public.

​​Automatic product tagging on photoes on Facebook Pages

#FacebookAI released an improvement aiming at enhancing shopping platform.

Post: https://ai.facebook.com/blog/powered-by-ai-advancing-product-understanding-and-building-new-shopping-experiences
Paper: https://scontent-arn2-1.xx.fbcdn.net/v/t39.8562-6/99353320_565175057533429_3886205100842024960_n.pdf

#GrokNet #DL #segmentation #PyTorch

​​Learning to Simulate Dynamic Environments with GameGAN

#Nvidia designed a GAN that able to recreate games without any game engine. To train it, authors of the model use experience collected by reinforcement learning and other techniques.

GameGAN successfully reconstructed all mechanics of #Pacman game. Moreover, the trained model can generate new mazes that have never appeared in the original game. It can even replace background (static objects) and foreground (dynamic objects) with different images!

As the authors say, applying reinforcement learning algorithms to real world tasks requires accurate simulation of that task. Currently designing such simulations is expensive and time-consuming. Using neural networks instead of hand-written simulations may help to solve these problems.

Paper: https://cdn.arstechnica.net/wp-content/uploads/2020/05/Nvidia_GameGAN_Research.pdf
Blog: https://blogs.nvidia.com/blog/2020/05/22/gamegan-research-pacman-anniversary/
Github Page: https://nv-tlabs.github.io/gameGAN/

#GAN #RL

​​SpERT: Span-based Joint Entity and Relation Extraction with Transformer Pre-training

Authors introduce SpERT, an attention model for span-based joint entity and relation extraction.

This work investigates the use of Transformer networks for relation extraction: given a pre-defined set of target relations and a sentence such as “Leonardo DiCaprio starred in Christopher Nolan’s thriller Inception”, the goal is to extract triplets such as (“Leonardo DiCaprio”, Plays-In, “Inception”) or (“Inception”, Director, “Christopher Nolan”).

The main contributions of the paper are:
– a novel approach towards span-based joint entity and relation extraction
– ablation study showing that negative samples from the same sentence yield efficient training, a localized context representation is beneficial, finetuning a pre-trained model yields a strong performance increase over training from scratch.

This approach improves the SOTA score on CoNLL04 dataset by 2.6% (micro) F1.


Paper: https://arxiv.org/abs/1909.07755
Code: https://github.com/markus-eberts/spert

#nlp #deeplearning #transformer #bert #ner #relationextraction