moses-smt / giza-pp
GIZA++ is a statistical machine translation toolkit that is used to train IBM Models 1-5 and an HMM word alignment model. This package also contains the source for the mkcls tool which generates the word classes necessary for training some of the alignment models.
☆264Updated last year
Related projects ⓘ
Alternatives and complementary repositories for giza-pp
- A word alignment tool based on famous GIZA++, extended to support multi-threading, resume training and incremental training.☆161Updated 3 years ago
- Easy Bootstrap Resampling and Approximate Randomization for BLEU, METEOR, and TER using Multiple Optimizer Runs. This implements "Better …☆202Updated last year
- Simple, fast unsupervised word aligner☆738Updated 2 years ago
- scripts and configuration files for Edinburgh neural MT submission to WMT 16 shared translation task☆138Updated 4 years ago
- Python scripts preprocessing Penn Treebank and Chinese Treebank☆162Updated 4 years ago
- SemCor and Masc documents annotated with NOAD word senses.☆183Updated 4 years ago
- eXtensible Neural Machine Translation☆185Updated 4 years ago
- Neural macine translation soft alignment visualisations for web and command line☆72Updated 3 years ago
- ☆146Updated 7 years ago
- Examples, tutorials and use cases for Marian, including our WMT-2017/18 baselines.☆78Updated last year
- Code and model files for the paper: "A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction" (AAAI-18…☆185Updated 5 years ago
- Efficient Low-Memory Aligner☆139Updated 2 months ago
- Baseline models, training scripts, and instructions on how to reproduce our results for our state-of-art grammar correction system from M…☆69Updated 5 years ago
- TED parallel Corpora is growing collection of Bilingual parallel corpora, Multilingual parallel corpora and Monolingual corpora extracted…☆242Updated 8 years ago
- An open-source neural machine translation system developed by Natural Language Processing Group, Nanjing University.☆99Updated 6 years ago
- This is a CoNLL formatted version of the OntoNotes 5.0 release.☆190Updated 9 years ago
- ☆42Updated 6 years ago
- Efficient Markov Chain word alignment☆54Updated 3 years ago
- JFLEG (JHU FLuency-Extended GUG) corpus for Grammatical Error Correction Evaluation☆112Updated last year
- A neural word aligner based on multilingual BERT☆328Updated 2 years ago
- Scripts to preprocess training and test data and to run fast_align and giza☆109Updated 3 years ago
- ☆270Updated 4 years ago
- Neural network sequence labeling model☆252Updated 6 years ago
- Attention-based NMT with Coverage, Context Gate, and Reconstruction☆95Updated 3 years ago
- Python wrapper for evaluating summarization quality by ROUGE package☆166Updated 4 years ago
- An implementation of RNNsearch using TensorFlow☆68Updated 6 years ago
- machine translation and quality estimation☆34Updated 5 years ago
- Attention-based NMT with a coverage mechanism to indicate whether a source word is translated or not☆110Updated 4 years ago
- Collection of Evaluation Metrics and Algorithms for Machine Translation☆76Updated 6 years ago
- ☆262Updated 2 years ago