# NiuTrans/MTBook

《机器翻译：基础与模型》肖桐 朱靖波 著 - Machine Translation: Foundations and Models

Repository: https://github.com/NiuTrans/MTBook
Canonical: https://ross.abutalabs.com/products/mtbook
Homepage: https://opensource.niutrans.com/mtbook/index.html
Language: TeX
License Family: other
Topics: machine-translation, deep-learning, natural-language-processing, neural-machine-translation, statistical-machine-translation, machine-learning, tex
Last push: 2024-09-14T11:26:32+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2315, "days_push": 718, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2793, forks 750 (observed 2026-08-28T04:07:22.236985+00:00)

## What it is
An open-source Chinese-language textbook, 'Machine Translation: Foundations and Models' by Tong Xiao and Jingbo Zhu of NEU NLP Lab / NiuTrans, covering machine translation from statistical foundations to modern neural and deep-learning approaches. The full book is written in TeX with all source openly available, and is published as a complete PDF plus a free web version.

## Use cases
- learn machine translation from scratch
- understand how statistical machine translation works
- study neural machine translation models and transformers
- find a free machine translation textbook in Chinese
- prepare for NLP research focused on translation
- get course material for teaching machine translation
- review n-gram language modeling and parsing basics for MT

## When to choose
- you want a systematic, textbook-depth treatment of machine translation history, statistical methods, and neural models
- you prefer Chinese-language instruction or want the TeX source to adapt the material
- you need free access via web chapters or a complete PDF for self-study or coursework

## When to avoid
- you need runnable software or a library to build a translation system rather than a book
- you want an English-language textbook
- you need hands-on training code, datasets, or benchmark tooling, which this resource does not provide

## Facets
- artifact type: learning-resource
- maturity: stable
- function: nlp, machine-learning, deep-learning
- domain: machine-learning, deep-learning, tutorials, education
- platform: browser
- tags: machine-translation, neural-machine-translation, statistical-machine-translation, textbook, open-textbook, tex, chinese-language, nlp-tutorial, natural-language-processing

## Member repositories
- NiuTrans/MTBook (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:22.236985+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 2026-08-30T08:14:50.008972+00:00, confidence not recorded.
  - readme: https://github.com/NiuTrans/MTBook (fetched 2026-08-28T04:07:22.236985+00:00, sha 67a870da2497)
  - homepage: https://opensource.niutrans.com/mtbook/index.html (fetched 2026-08-29T09:55:00.360336+00:00, sha 44136fa355b3)
- Data as of 2026-08-30T08:39:29.467469+00:00.