Natural Language Processing

Curated Resources (31)

Tools (5)

• spaCy spacy.iofree

  An open-source software library for advanced Natural Language Processing written in Python and Cython.

• NLTK nltk.orgfree

  A leading Python platform for building computational programs to process and analyze human language data.

• Gensim radimrehurek.comfree

  An open-source Python library designed for unsupervised topic modeling, document indexing, and similarity retrieval.

• Stanza stanfordnlp.github.iofree

  A Python natural language analysis package developed by the Stanford NLP Group featuring accurate neural pipelines.

• Hugging Face Transformers huggingface.cofree

  Documentation for the open-source Transformers library, which provides pretrained text, vision and audio models and APIs for inference and fine-tuning.

Databases (4)

• WordNet wordnet.princeton.edufree

  A large lexical database of English nouns, verbs, adjectives, and adverbs grouped into sets of cognitive synonyms.

• ACL Anthology aclanthology.orgfree

  A comprehensive digital archive hosting open-access scientific papers published across all major NLP and computational linguistics venues.

• Universal Dependencies universaldependencies.orgfree

  A cross-linguistically consistent treebank annotation database spanning more than one hundred human languages.

• Hugging Face Hub huggingface.cofree

  A repository of open-access pre-trained natural language processing models, embeddings, and tokenizers.

Learn (9)

• Stanford CS224N: Natural Language Processing with Deep Learning web.stanford.edufree

  Lecture notes, assignments, and slides covering neural network architectures for natural language processing from Stanford University.

• Speech and Language Processing (Jurafsky & Martin) web.stanford.edufree

  The authoritative textbook draft on computational linguistics, speech processing, and natural language understanding.

• Hugging Face NLP Course huggingface.cofree

  A hands-on, open-access course teaching practical transformer workflows, fine-tuning, and model deployment.

• The Illustrated Transformer jalammar.github.iofree

  Heavily illustrated walkthrough of the transformer architecture, explaining attention, encoders and decoders visually for students new to modern language models.

• Transformer: A Novel Neural Network Architecture for Language Understanding research.googlefree

  Google Research blog post introducing the transformer model and explaining in accessible terms why self-attention improved machine translation.

• GPT in 60 Lines of NumPy jaykmody.comfree

  Hands-on tutorial that implements the forward pass of a GPT language model in a short NumPy program, aimed at programmers learning how GPT works.

• The Annotated Transformer nlp.seas.harvard.edufree

  Line-by-line annotated PyTorch implementation of the original transformer paper, pairing the text of the paper with working code for students and researchers.

• LLM University docs.cohere.comfree

  Free self-paced course on large language models covering embeddings, text generation, retrieval-augmented generation and deployment for developers building language applications.

• Prompt Engineering Roadmap (roadmap.sh) roadmap.shfree

  Interactive roadmap on prompting language models: topics laid out in a suggested study order, each linking to further reading.

Publications (6)

• Computational Linguistics direct.mit.edufree

  The diamond open-access flagship academic journal published by MIT Press on behalf of the Association for Computational Linguistics.

• Transactions of the Association for Computational Linguistics (TACL) transacl.orgfree

  An open-access journal publishing high-impact peer-reviewed research in all areas of computational linguistics and NLP.

• Natural Language Engineering cambridge.orgpaid

  A peer-reviewed journal from Cambridge University Press focusing on practical and engineering aspects of language processing.

• Language Models are Few-Shot Learners arxiv.orgfree

  Research paper introducing GPT-3 and showing how a large language model performs new tasks from a few examples given in its prompt.

• Improving Language Understanding by Generative Pre-Training cdn.openai.comfree

  The 2018 paper describing the first GPT model, which combined unsupervised pre-training of a transformer with supervised fine-tuning on language tasks.

• Language Models are Unsupervised Multitask Learners cdn.openai.comfree

  The 2019 paper introducing GPT-2 and showing that a large language model trained on web text can perform many tasks without task-specific training.

Blogs and sites (3)

• Stanford NLP Group Blog nlp.stanford.edufree

  Technical articles, perspectives, and research releases by the Stanford Natural Language Processing Group.

• Sebastian Ruder's Blog ruder.iofree

  Technical essays and comprehensive newsletters detailing developments in NLP, representation learning, and multilinguality.

• Explosion Blog explosion.aifree

  Insights and practical tutorials on production natural language processing, data annotation, and developer tooling.

Events and conferences (4)

• ACL (Annual Meeting of the Association for Computational Linguistics) aclweb.orgpaid

  The flagship international conference presenting leading research across all areas of natural language processing.

• EMNLP (Empirical Methods in Natural Language Processing) aclanthology.orgpaid

  A premier annual gathering focused on empirical and data-driven methods in computational linguistics.

• NAACL (North American Chapter of the ACL) aclanthology.orgpaid

  An annual major conference focusing on natural language processing research organized by the North American ACL chapter.

• COLING (International Conference on Computational Linguistics) aclanthology.orgpaid

  A major recurring international conference dedicated to computational linguistics and language resources.

Other subcategories

Artificial Intelligence · Machine Learning · Big Data · Computer Information Systems · Computer Science · Computer Vision · Cyber Security · Data Science · Databases · Distributed Computing · Hardware · Human-Computer Interaction · IT Certification · Networking · Operating Systems · Robotics · Software Engineering

Part of Computing