Mao-KU / JASS
JASS: Japanese-specific Sequence to Sequence Pre-training for Neural Machine Translation (LREC2020) & Linguistically Driven Multi-Task Pre-Training for Low-Resource Neural Machine Translation (ACM TALLIP)
☆16Updated 3 years ago
Alternatives and similar repositories for JASS
Users that are interested in JASS are comparing it to the libraries listed below
Sorting:
- ☆28Updated 11 months ago
- A Supervised Word Alignment Method based on Cross-Language Span Prediction using Multilingual BERT☆27Updated 4 years ago
- ☆33Updated 3 years ago
- A large parallel corpus of English and Japanese☆84Updated 7 years ago
- FairseqでGECをモデルを動かす.☆7Updated 3 years ago
- The Business Scene Dialogue corpus☆68Updated 3 years ago
- ☆23Updated last year
- ☆24Updated 2 years ago
- Stronger Baselines for Grammatical Error Correction Using a Pretrained Encoder-Decoder Model.☆37Updated 2 years ago
- ☆20Updated 2 years ago
- ☆119Updated 4 years ago
- ☆21Updated 2 years ago
- ☆42Updated 6 years ago
- Tools for filtering and cleaning parallel and monolingual corpora for machine translation and other natural language processing tasks.☆41Updated last year
- Code for AAAI 2021 paper "Lexically Constrained Neural Machine Translation with Explicit Alignment Guidance"☆25Updated 2 years ago
- An example usage of JParaCrawl pre-trained Neural Machine Translation (NMT) models.☆104Updated 4 years ago
- Scripts to preprocess training and test data and to run fast_align and giza☆108Updated 3 years ago
- ☆17Updated 4 years ago
- Multi-modal Neural Machine Translation in PyTorch☆44Updated 7 years ago
- YiSi: A Semantic Machine Translation Evaluation Metric for Evaluating Languages with Different Levels of Available Resources☆25Updated 5 years ago
- My implementation of LASER architecture in Fairseq☆12Updated 4 years ago
- A library for minimum Bayes risk (MBR) decoding☆37Updated last month
- Lexically Constrained Neural Machine Translation with Levenshtein Transformer☆39Updated 4 years ago
- Repository of "An Empirical Study of Incorporating Pseudo Data into Grammatical Error Correction" (EMNLP-IJCNLP 2019)☆68Updated 5 years ago
- The baseline model code for WMT 2021 Triangular MT☆13Updated 4 years ago
- DSTC10 Track 2 - Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations☆61Updated last year
- ☆23Updated 9 months ago
- ☆33Updated 4 years ago
- Terminology Dataset☆23Updated 5 years ago
- Unsupervised parallel sentence extraction from comparable corpora☆16Updated 5 years ago