# mhagiwara/100-nlp-papers

100 Must-Read NLP Papers

Repository: https://github.com/mhagiwara/100-nlp-papers
Canonical: https://ross.abutalabs.com/products/100-nlp-papers
Homepage: http://masatohagiwara.net/100-nlp-papers/
License Family: other
Last push: 2021-07-09T15:21:35+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3529, "days_push": 1881, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3846, forks 558 (observed 2026-08-28T04:08:24.077173+00:00)

## What it is
A curated list of 100 must-read natural language processing papers compiled by Masato Hagiwara, covering machine learning, neural models, embeddings, and other core NLP topics. It is a reading guide for students and researchers rather than software.

## Use cases
- find essential NLP papers to read
- build a self-study curriculum for natural language processing
- get reading recommendations for NLP research
- learn the history of NLP through landmark papers
- find survey and tutorial papers on NLP topics

## When to choose
- you are a student or researcher starting out in NLP and want a structured reading list
- you want curated pointers to foundational and modern NLP papers including tutorials and blog posts

## When to avoid
- you need runnable code, a library, or a tool rather than a paper list
- you need an exhaustive or fully up-to-date bibliography, since the list is opinionated and evolving

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: nlp, documentation
- domain: machine-learning, tutorials, awesome-lists
- platform: -
- tags: reading-list, papers, curated-list, education, natural-language-processing

## Member repositories
- mhagiwara/100-nlp-papers (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:24.077173+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:26:00.970387+00:00, confidence not recorded.
  - readme: https://github.com/mhagiwara/100-nlp-papers (fetched 2026-08-28T04:08:24.077173+00:00, sha 8dbb7f17e336)
  - homepage: http://masatohagiwara.net/100-nlp-papers/ (fetched 2026-08-29T09:21:08.757569+00:00, sha 2e1b4eb84191)
- Data as of 2026-08-30T08:39:29.467469+00:00.