• Benmark:

  https://paperswithcode.com/sota

• ACL anthology for NLP papers:

  http://www.aclweb.org/anthology/

• Online proceedings of major ML conferences:

  • NeurIPS
  • ICML, ICLR, CVPR, EMNLP, NAACL

• Online preprint servers:

  http://arxiv.org/

• Top paper menioned on Twitter:

  http://www.arxiv-sanity.com/

• Others:

  • http://scholar.google.com
  • http://dl.acm.org/
  • http://aclasb.dfki.de

• Huggingface Datasets:

  https://huggingface.co/datasets

• Kaggle has many datasets, though some of them are too small for Deep Learning:

  https://www.kaggle.com/datasets

• SOTA NLP:

  https://paperswithcode.com/sota

  https://nlpprogress.com/

  https://gluebenchmark.com/leaderboard

  https://www.conll.org/previous-tasks

• A small list of well-known standard datasets for common NLP tasks: https://machinelearningmastery.com/datasets-natural-language-processing/

• An alphabetical list of free or public domain text datasets:

  https://github.com/niderhoff/nlp-datasets

• Wikipedia has a list of machine learning text datasets, tabulated with useful information such as dataset size: https://en.wikipedia.org/wiki/List_of_datasets_for_machine-learning_research#Text_data

• Datahub has lots of datasets, though not all of it is Machine Learning focused:

  https://datahub.io/collections

• Microsoft Research has a collection of datasets (look under the ‘Dataset directory’ tab): https://www.microsoft.com/en-us/research/academic-program/data-science-microsoft-research/?from=http%3A%2F%2Fresearch.microsoft.com%2Fen-us%2Fprojects%2Fdata-science-initiative%2F%20datasets.aspx#!dataset-directory

• A script to search arXiv papers for a keyword, and extract important information such as performance metrics on a task:

  https://huyenchip.com/2018/10/04/sotawhat.html

• Datasets for machine translation:

  http://statmt.org

• Syntactic corpora for many languages:

  https://universaldependencies.org

• StanfordNLP: a Python library providing tokenization, tagging, parsing, and other capabilities:

  https://stanfordnlp.github.io/stanfordnlp/

• Other software from the Stanford NLP group: http://nlp.stanford.edu/software/index.shtml

• NLTK, a lightweight Natural Language Toolkit package in Python: http://nltk.org/

• spaCy, another Python package that can do preprocessing, but also includes neural models (e.g. Language Models):

  https://spacy.io/

• Site

  • ML

    • NeurIPS
    • ICML
    • ICLR
    • AISTATS

  • CV

    • CVPR
    • ICCV
    • ECCV

  • NLP

    • ACL
    • NAACL
    • EMNLP

  • Data

    • KDD
    • CIKM
    • ICDM
    • SDM
    • PAKDD
    • PKDD/ECML
    • RECSYS
    • SIGIR
    • WWW
    • WSDM

  • AI

    • AAAI
    • ICANN
    • IJCAI
    • UAI

• NeurIPS: Neural Information Processing Systems (formerly abbreviated NIPS). NeurIPS has gotten huge over the past few years as AI has become so important. Has a focus on neural networks, but not exclusively.

   https://nips.cc

• ICML: International Conference on Machine Learning. Has a general machine learning focus.

  https://icml.cc

• ICLR: International Conference on Learning Representations. ICLR was really the first conference focused on deep learning. It’s called “learning representations” because the motivation behind deep learning is to automatically learn higher-level features, or representations, that summarize data in useful ways. Deep Learning describes the structure of our current best solution to the problem of learning these representations.

   https://iclr.cc

• AAAI: Association for the Advancement of Artificial Intelligence. AAAI is a little more applications focused, and a little less theoretical than some of the other AI conferences.

  http://www.aaai.org

• CVPR: Computer Vision and Pattern Recognition.

  https://www.thecvf.com

• ICCV: International Conference on Computer Vision.

  https://www.thecvf.com

Practical Tips for Final Projects Notes

List of great ML/AI conferences