clab / fast_align
Simple, fast unsupervised word aligner
☆738Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for fast_align
- Fast BPE☆656Updated 5 months ago
- A tool for holistic analysis of language generations systems☆467Updated 2 years ago
- A neural word aligner based on multilingual BERT☆328Updated 2 years ago
- ☆360Updated last year
- Open-Source Neural Machine Translation in Tensorflow☆797Updated last year
- 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
- A framework to learn cross-lingual word embedding mappings☆645Updated last year
- Python port of Moses tokenizer, truecaser and normalizer☆488Updated 5 months ago
- Unsupervised Statistical Machine Translation☆228Updated 4 years ago
- Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons☆1,068Updated 3 months ago
- scripts and configuration files for Edinburgh neural MT submission to WMT 16 shared translation task☆138Updated 4 years ago
- Open-Source Machine Translation Quality Estimation in PyTorch☆228Updated 2 years ago
- Evaluating Cross-lingual Sentence Representations☆442Updated 3 years ago
- Source code for paper: Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data☆246Updated 4 years ago
- Obtain Word Alignments using Pretrained Language Models (e.g., mBERT)☆351Updated last year
- BERT for Coreference Resolution☆445Updated last year
- End-to-end Neural Coreference Resolution☆524Updated 2 years ago
- A word alignment tool based on famous GIZA++, extended to support multi-threading, resume training and incremental training.☆161Updated 3 years ago
- A list of Neural MT implementations☆359Updated 2 years ago
- Moses, the machine translation system☆1,583Updated 5 months ago
- MASS: Masked Sequence to Sequence Pre-training for Language Generation☆1,118Updated last year
- eXtensible Neural Machine Translation☆185Updated 4 years ago
- Bicleaner is a parallel corpus classifier/cleaner that aims at detecting noisy sentence pairs in a parallel corpus.☆150Updated 5 months ago
- ERRor ANnotation Toolkit: Automatically extract and classify grammatical errors in parallel original and corrected sentences.☆440Updated 7 months ago
- Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)☆1,187Updated last month
- Easy Bootstrap Resampling and Approximate Randomization for BLEU, METEOR, and TER using Multiple Optimizer Runs. This implements "Better …☆202Updated last year
- Fast + Non-Autoregressive Grammatical Error Correction using BERT. Code and Pre-trained models for paper "Parallel Iterative Edit Models …☆228Updated last year
- Bitextor generates translation memories from multilingual websites☆291Updated last week
- An open-source neural machine translation toolkit developed by Tsinghua Natural Language Processing Group☆705Updated 2 years ago
- Efficient Low-Memory Aligner☆139Updated 2 months ago