Tsinghua University Publishes Comprehensive Machine Translation Reading List

Tsinghua Natural Language Processing Group (THUNLP) has published a great reading list on GitHub for any budding AI researchers whose New Year’s resolution is to study machine translation. The list compiles the most influential machine translation papers from the past 30 years, spotlighting the 10 most important contributions to the development of machine translation.

The reading list is smartly organized, with detailed categorizations including statistical machine translation, neural machine translation, multilingual language translation, low-resource language translation and others. The prominence of neural machine translation papers is due NMT dominance in the field during the years surveyed.

Below is the full THUNLP Machine Translation Reading List:


Statistical Machine Translation


Word-based Models

Phrase-based Models

Syntax-based Models

Discriminative Training

System Combination


Neural Machine Translation


Model Architecture

Attention Mechanism

Open Vocabulary and Character-based NMT

Training Objectives and Frameworks


Low-resource Language Translation

Semi-supervised Methods

Unsupervised Methods

Pivot-based Methods

Data Augmentation Methods

Data Selection Methods

Transfer Learning & Multi-Task Learning Methods

Meta Learning Methods

Multilingual Language Translation

Prior Knowledge Integration

Word/Phrase Constraints

Syntactic/Semantic Constraints

Coverage Constraints

Document-level Translation


Visualization and Interpretability

Linguistic Interpretation

Fairness and Diversity



Speech Translation and Simultaneous Translation


Domain Adaptation

Quality Estimation

Automatic Post-Editing

Word Translation and Bilingual Lexicon Induction

Poetry Translation

To view other papers and resources, please visit THUNLP on GitHub.

Author: Jessie Geng | Editor: Michael Sarazen

2018 Fortune Global 500 Public Company AI Adaptivity Report is out!
Purchase a Kindle-formatted report on Amazon.
Apply for Insight Partner Program to get a complimentary full PDF report.

Follow us on Twitter @Synced_Global for daily AI news!

We know you don’t want to miss any stories. Subscribe to our popular Synced Global AI Weekly to get weekly AI updates.