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 4 years ago
- NTREX -- News Test References for MT Evaluation☆86Updated 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
- Coursera Corpus Mining and Multistage Fine-Tuning for Improving Lectures Translation☆15Updated last year
- A library for minimum Bayes risk (MBR) decoding☆48Updated 4 months ago
- OpusFilter - Parallel corpus processing toolkit☆110Updated last week
- Improved Sentence Alignment in Linear Time and Space☆181Updated 2 years ago
- ☆49Updated last year
- A tool that locates, downloads, and extracts machine translation corpora☆158Updated 2 weeks ago
- An example usage of JParaCrawl pre-trained Neural Machine Translation (NMT) models.☆104Updated 4 years ago
- Tools for filtering and cleaning parallel and monolingual corpora for machine translation and other natural language processing tasks.☆41Updated last year
- ☆31Updated last year
- SIGMORPHON 2022 Shared Task on Morpheme Segmentation☆28Updated 2 years ago
- A tiny BERT for low-resource monolingual models☆31Updated last week
- Bicleaner fork that uses neural networks☆40Updated 3 months ago
- Complimentary code for our paper Automatic punctuation restoration with BERT models☆50Updated last year
- ☆42Updated 7 years ago
- MT Evaluation in Many Languages via Zero-Shot Paraphrasing☆102Updated last year
- Efficient Low-Memory Aligner☆146Updated 8 months ago
- Bicleaner is a parallel corpus classifier/cleaner that aims at detecting noisy sentence pairs in a parallel corpus.☆158Updated last year
- The Business Scene Dialogue corpus☆70Updated 3 years ago
- Project OCELoT: an Open, Collaborative Evaluation Leaderboard of Translations☆21Updated 3 weeks ago
- ☆15Updated 6 years ago
- A guide to building language technology in new languages.☆59Updated 3 years ago
- Utilities for Processing the Switchboard Dialogue Act Corpus☆70Updated 4 years ago
- cLang-8 is a dataset for grammatical error correction.☆109Updated 3 years ago
- Code and datasets of "Multilingual Extractive Reading Comprehension by Runtime Machine Translation"☆40Updated 6 years ago
- An official implementation of "BPE-Dropout: Simple and Effective Subword Regularization" algorithm.☆52Updated 4 years ago
- Scripts to preprocess training and test data and to run fast_align and giza☆108Updated 3 years ago
- A neural word aligner based on multilingual BERT☆357Updated 3 years ago