nttcslab-nlp / spanalignLinks
SpanAlign: Sentence Alignment Method based on Cross-Language Span Prediction and ILP
☆14Updated 4 years ago
Alternatives and similar repositories for spanalign
Users that are interested in spanalign are comparing it to the libraries listed below
Sorting:
- A Supervised Word Alignment Method based on Cross-Language Span Prediction using Multilingual BERT☆27Updated 5 years ago
- NTREX -- News Test References for MT Evaluation☆88Updated last year
- This repo contains a set of neural transducer, e.g. sequence-to-sequence model, focusing on character-level tasks.☆76Updated 2 years ago
- A library for minimum Bayes risk (MBR) decoding☆51Updated 3 months ago
- OpusFilter - Parallel corpus processing toolkit☆115Updated this week
- A tool that locates, downloads, and extracts machine translation corpora☆162Updated 4 months ago
- Improved Sentence Alignment in Linear Time and Space☆188Updated 2 years ago
- Complimentary code for our paper Automatic punctuation restoration with BERT models☆50Updated 2 years ago
- MT Evaluation in Many Languages via Zero-Shot Paraphrasing☆102Updated last year
- SIGMORPHON 2022 Shared Task on Morpheme Segmentation☆31Updated 2 years ago
- ☆50Updated last year
- ☆15Updated 6 years ago
- Coursera Corpus Mining and Multistage Fine-Tuning for Improving Lectures Translation☆15Updated last year
- Bicleaner is a parallel corpus classifier/cleaner that aims at detecting noisy sentence pairs in a parallel corpus.☆160Updated last year
- Fairseq tutorial☆17Updated 3 years ago
- An official implementation of "BPE-Dropout: Simple and Effective Subword Regularization" algorithm.☆53Updated 4 years ago
- Library for experimenting with state-of-the-art evaluation metrics like UScore☆12Updated 2 years ago
- Bicleaner fork that uses neural networks☆40Updated last week
- A tiny BERT for low-resource monolingual models☆31Updated last month
- Project OCELoT: an Open, Collaborative Evaluation Leaderboard of Translations☆23Updated 3 months ago
- Tools for filtering and cleaning parallel and monolingual corpora for machine translation and other natural language processing tasks.☆41Updated 2 years ago
- Corpus preprocessing☆99Updated last year
- Efficient Low-Memory Aligner☆146Updated last year
- ☆94Updated last year
- ☆34Updated 2 years ago
- Obtain Word Alignments using Pretrained Language Models (e.g., mBERT)☆386Updated 2 years ago
- Universal Romanizer that can convert any unicode script to roman (latin) script☆237Updated last year
- ☆42Updated 7 years ago
- ☆34Updated 4 years ago
- An adaptation of Fairseq to (End-to-end) speech translation.☆22Updated 3 years ago