moses-smt / mgiza
A word alignment tool based on famous GIZA++, extended to support multi-threading, resume training and incremental training.
☆161Updated 3 years ago
Alternatives and similar repositories for mgiza:
Users that are interested in mgiza are comparing it to the libraries listed below
- GIZA++ is a statistical machine translation toolkit that is used to train IBM Models 1-5 and an HMM word alignment model. This package al…☆264Updated last year
- scripts and configuration files for Edinburgh neural MT submission to WMT 16 shared translation task☆138Updated 4 years ago
- Examples, tutorials and use cases for Marian, including our WMT-2017/18 baselines.☆76Updated last year
- Corpus preprocessing☆95Updated 10 months ago
- Easy Bootstrap Resampling and Approximate Randomization for BLEU, METEOR, and TER using Multiple Optimizer Runs. This implements "Better …☆202Updated last year
- Translation Error Rate (TER)☆43Updated 6 years ago
- Tool for comparison and evaluation of machine translation.☆56Updated 2 years ago
- ☆54Updated 9 years ago
- Collection of Evaluation Metrics and Algorithms for Machine Translation☆76Updated 6 years 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
- Efficient Markov Chain word alignment☆53Updated 3 years ago
- Efficient Low-Memory Aligner☆140Updated 2 weeks ago
- eXtensible Neural Machine Translation☆185Updated 4 years ago
- Recurrent neural network grammars☆186Updated 6 years ago
- ☆42Updated 6 years ago
- Appraise evaluation system for manual evaluation of machine translation output☆74Updated 3 years ago
- Pipelined quality estimation.☆50Updated 5 years ago
- TED parallel Corpora is growing collection of Bilingual parallel corpora, Multilingual parallel corpora and Monolingual corpora extracted…☆245Updated 9 years ago
- SemCor and Masc documents annotated with NOAD word senses.☆182Updated 4 years ago
- Neural macine translation soft alignment visualisations for web and command line☆72Updated 3 years ago
- Tools for extracting parallel corpora from article titles across languages in Wikipedia☆72Updated 9 years ago
- Scripts to preprocess training and test data and to run fast_align and giza☆108Updated 3 years ago
- Supplementary material for "When and Why Are Pre-trained Word Embeddings Useful for Neural Machine Translation?" at NAACL 2018☆121Updated 4 years ago
- Decoder, aligner, and model optimizer for statistical machine translation and other structured prediction models based on (mostly) contex…☆183Updated 4 years ago
- TER-plus Machine Translation metric.☆31Updated 2 years ago
- Bicleaner is a parallel corpus classifier/cleaner that aims at detecting noisy sentence pairs in a parallel corpus.☆152Updated 7 months ago
- ☆34Updated 8 years ago
- Attention-based NMT with Coverage, Context Gate, and Reconstruction☆95Updated 3 years ago
- ☆18Updated 6 years ago
- JFLEG (JHU FLuency-Extended GUG) corpus for Grammatical Error Correction Evaluation☆112Updated last year