I'm really excited about the ongoing research in conversational AI.
— Chip Huyen (@chipro) September 18, 2019
Today Amazon released the largest topic-based conversational dataset to date: 10.7k conversations, 235k utterances, 4.7M words. All convos are linked to particular knowledge sources.https://t.co/xW72hRYo9e
Can you predict wait times at major city intersections? Join our latest Playground competition, hosted by Google #BigQuery and compete for thousands of dollars worth of GCP credits! 👀 Read more and get started today: https://t.co/ncPdfcFSUN pic.twitter.com/E6SHemH89O
— Kaggle (@kaggle) September 13, 2019
We are excited to release Taskmaster-1, a new task-oriented dialog dataset. We explore two methods for data collection, two-person and self-dialogs. Surprisingly self-dialogs are an effective way to collect dialog.
— Arvind Neelakantan (@arvind_io) September 13, 2019
Paper accepted to @emnlp2019 : https://t.co/mAhKu5PUL1 pic.twitter.com/gTj5ocfdrS
Attn researchers and academics! We just introduced a new feature to Kaggle Datasets: the Digital Object Identifier, DOI, to Datasets.
— Kaggle (@kaggle) September 12, 2019
📢
Read more about how you can use this feature, and let us know what you think! https://t.co/dxffsahQmx pic.twitter.com/vDsEGRcB8L
Just launched: 3D Object Detection for Autonomous Vehicles challenge by @LyftLevel5 | Read the details and get started today 👉 https://t.co/7jOxoTUPlS #NeurIPS2019 pic.twitter.com/dU5vhvTzkZ
— Kaggle (@kaggle) September 12, 2019
The lack of good benchmark tasks is one of the biggest obstacles to progress in meta-reinforcement learning right now. With meta-world, we hope to change that: 50 manipulation tasks, divided into a meta-training set and a meta-test set. https://t.co/IJCX997pd4
— Sergey Levine (@svlevine) September 12, 2019
Taking face censoring one more step: replace them with randomly generated face at the correct pose.
— Reza Zadeh (@Reza_Zadeh) September 11, 2019
Paper: https://t.co/T2edC4VGXB
Code: https://t.co/F7iUh2lJVt pic.twitter.com/XqxKo041bG
Check out our new diagnostic NLP benchmark, CLUTRR,
— Will Hamilton (@williamleif) September 10, 2019
which tests the logical reasoning and generalization ability of NLP systems: https://t.co/uF1cxZPiGK https://t.co/CHhNuHtBw5 Paper to appear in EMNLP 2019; project led by @koustuvsinha
Second Fashion-Gen challenge at #ICCV2019:
— Negar Rostamzadeh (@negar_rz) September 10, 2019
Fashion-Gen is a dataset of ~300K images paired with item descriptions. The task is image generation conditioned on the given text descriptions.
Deadline: Oct 15
Challenge: https://t.co/45WdOpOIqv
Paper: https://t.co/RUrRx7HHiv pic.twitter.com/q6v1YFnsVc
Google open-sources datasets for AI assistants with human-level understanding - VentureBeat https://t.co/KqNWmiZa3P via @GoogleNews
— Bojan Tunguz (@tunguz) September 8, 2019
Retrospectively reading solutions from the top competing teams is systematically one of the most satisfying learning part of participating in a @kaggle ML competition.
— Alexandre Cadrin (@alexandrecadrin) September 8, 2019
Here are many solutions from the recent @SIIM_Tweets/@RadiologyACR pneumothorax comp:https://t.co/VaEwlrurqG
Excited to announce Quoref, a reading comprehension dataset with 24K span-selection questions requiring coreferential reasoning over English Wikipedia paragraphs. Work with @nelsonfliu, @anamarasovic, @nlpnoah and @nlpmattg. https://t.co/w2Igjq2IPB https://t.co/dNf4Fu2ENH #NLProc
— Pradeep Dasigi (@pdasigi) September 6, 2019
