thompsonb / vecalign
Improved Sentence Alignment in Linear Time and Space
☆167Updated 2 years ago
Alternatives and similar repositories for vecalign:
Users that are interested in vecalign are comparing it to the libraries listed below
- A neural word aligner based on multilingual BERT☆339Updated 3 years ago
- Efficient Low-Memory Aligner☆142Updated last month
- OpusFilter - Parallel corpus processing toolkit☆104Updated 2 weeks ago
- Bicleaner is a parallel corpus classifier/cleaner that aims at detecting noisy sentence pairs in a parallel corpus.☆155Updated 8 months ago
- Sentence aligner☆110Updated 3 years ago
- A tool that locates, downloads, and extracts machine translation corpora☆151Updated this week
- Scripts to preprocess training and test data and to run fast_align and giza☆108Updated 3 years ago
- Obtain Word Alignments using Pretrained Language Models (e.g., mBERT)☆359Updated last year
- Repository to collect and categorize Grammatical Error Correction papers.☆116Updated 4 months ago
- Bitextor generates translation memories from multilingual websites☆291Updated 4 months ago
- Multilingual sentence alignment using sentence embeddings☆110Updated 4 months ago
- Transformer based translation quality estimation☆110Updated last year
- Machine-Translation-based sentence alignment tool for parallel text☆307Updated 3 years ago
- ☆42Updated 6 years ago
- MT Evaluation in Many Languages via Zero-Shot Paraphrasing☆101Updated 7 months ago
- A Supervised Word Alignment Method based on Cross-Language Span Prediction using Multilingual BERT☆26Updated 4 years ago
- Easier Automatic Sentence Simplification Evaluation☆160Updated last year
- Machine Translation (MT) Preparation Scripts☆31Updated 2 weeks ago
- cLang-8 is a dataset for grammatical error correction.☆103Updated 2 years ago
- NTREX -- News Test References for MT Evaluation☆81Updated 9 months ago
- MorphyNet: a Large Multilingual Database of Derivational and Inflectional Morphology (+morpheme segmentation)☆41Updated last year
- Efficient Markov Chain word alignment☆53Updated 3 years ago
- JFLEG (JHU FLuency-Extended GUG) corpus for Grammatical Error Correction Evaluation☆113Updated last year
- Tools for filtering and cleaning parallel and monolingual corpora for machine translation and other natural language processing tasks.☆41Updated last year
- ☆36Updated 3 years ago
- Bicleaner fork that uses neural networks☆39Updated 7 months ago
- A single model that parses Universal Dependencies across 75 languages. Given a sentence, jointly predicts part-of-speech tags, morphology…☆221Updated 2 years ago
- ☆119Updated 4 years ago
- This is a repository with the data and code for the ACL 2019 paper "When a Good Translation is Wrong in Context: ..." and the EMNLP 2019 …☆97Updated 4 years ago
- Code for our paper "Mask-Align: Self-Supervised Neural Word Alignment" in ACL 2021☆60Updated 3 years ago