What makes a good conversation?
How controllable attributes affect human judgments

A great post on conversation scoring.

Link:
http://www.abigailsee.com/2019/08/13/what-makes-a-good-conversation.html
Paper:
https://www.aclweb.org/anthology/N19-1170

#NLP #NLU #DL

❇️ @ai_python_en

🔹 Python examples of popular machine learning algorithms with interactive Jupyter demos and math being explained👌

📌 https://github.com/trekhleb/homemade-machine-learning

❇️ @AI_Python

NVIDIA Announces TensorRT 6; Breaks 10 millisecond barrier for BERT-Large

https://news.developer.nvidia.com/tensorrt6-breaks-bert-record/

🔍 DeepPavlov: An open-source library for end-to-end dialogue systems and chatbots

article: https://medium.com/tensorflow/deeppavlov-an-open-source-library-for-end-to-end-dialog-systems-and-chatbots-31cf26849e37

research: https://colab.research.google.com/github/deepmipt/dp_notebooks/blob/master/DP_tf.ipynb

code: https://github.com/deepmipt/DeepPavlov

⭐️Fine-Tuning GPT-2 from Human Preferences

#OpenAI team fine-tuned 774M parameters model to achieve better scores in #summarization and stylistic text continuation in terms of human understanding.

Article definately worths reading (approx 15 min.) with Challenges and lessons learned section and examples.

Link: https://openai.com/blog/fine-tuning-gpt-2/
Paper: https://arxiv.org/abs/1909.08593
Code: https://github.com/openai/lm-human-preferences

#NLP #NLU #finetuning

🗣 Using AI-generated questions to train NLP systems

https://ai.facebook.com/blog/research-in-brief-unsupervised-question-answering-by-cloze-translation/

code:
https://github.com/facebookresearch/UnsupervisedQA

paper:
https://research.fb.com/publications/unsupervised-question-answering-by-cloze-translation/

Neural networks in NLP are vulnerable to adversarially crafted inputs.

We show that they can be trained to become certifiably robust against input perturbations such as typos and synonym substitution in text classification:

https://arxiv.org/abs/1909.01492

Depth Hints are complementary depth suggestions which improve monocular depth estimation algorithms trained from stereo pairs

code:
https://github.com/nianticlabs/depth-hints

paper:
https://arxiv.org/abs/1909.09051

dataset :
https://lmb.informatik.uni-freiburg.de/resources/datasets/SceneFlowDatasets.en.html

​​Light regression analysis of some Microsoft employees salary distrubution

How basic knowledge of regression and couple of graphs can make an information look much better and clear.

Link: https://onezero.medium.com/leak-of-microsoft-salaries-shows-fight-for-higher-compensation-3010c589b41e

#regression #simple #salary #infographic

100,000 FACES GENERATED BY AI FREE FOR ANY USE

https://generated.photos/

https://drive.google.com/drive/folders/1wSy4TVjSvtXeRQ6Zr8W98YbSuZXrZrgY

​​FSGAN: Subject Agnostic Face Swapping and Reenactment

New paper on #DeepFakes creation

YouTube demo:
https://www.youtube.com/watch?v=duo-tHbSdMk
Link:
https://nirkin.com/fsgan/
ArXiV:
https://arxiv.org/pdf/1908.05932.pdf

#FaceSwap #DL #Video #CV

Torchdata is PyTorch oriented library focused on data processing and input pipelines in general

https://github.com/szymonmaszke/torchdata

Sarbazi, M., Sadeghzadeh, M., & Mir Abedini, S. J. (2019). Improving resource allocation in software-defined networks using clustering. Cluster Computing.
doi:10.1007/s10586-019-02985-3

❇️ @AI_Python_EN

If you just published a paper let us inform other members.
@ai_python_en

Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis
pdf: https://arxiv.org/pdf/1909.12224.pdf
abs: https://arxiv.org/abs/1909.12224
project page: https://svip-lab.github.io/project/impersonator.html
github: https://github.com/svip-lab/imper

#AI for Mammography and Digital Breast Tomosynthesis: Current Concepts and Future Perspectives​. Krzysztof et al explain in the newest Radiology article below.
http://bit.ly/2kULbDz

PyTorch implementations of deep reinforcement learning algorithms and environments

GitHub, by Petros Christodoulou : https://lnkd.in/eRZCQ-d

#pytorch #reinforcementlearning #deeplearning

Google researchers just released #ALBERT , that has beaten all models across various benchmarks.

Also, did you know that most NLP models achieves performance that outpaces average human performance?
——————————————————
ALBERT uses parameter reduction techniques to lower memory consumption and increase the training speed of BERT

1. They topped GLUE ( https://lnkd.in/dkWNRVk ) — 92.2%

2. SQuAD (https://lnkd.in/d_Xrba8 ) leaderboards. — 89.4%

3. RACE - they came third with their ensemble model (https://lnkd.in/d2yWbtC ) — 89.4%
——————————————————
Paper at openreview: https://lnkd.in/dzRvWYS
#deeplearning #machinelearning #NLU #NLG #artificiallintelligence #ai