windsuzu / Joint-Semantic-Phonetic-EmbeddingLinks
We use phonetics as a feature to create a joint semantic-phonetic embedding and improve the neural machine translation between Chinese and Japanese. 🥳
☆12Updated 4 years ago
Alternatives and similar repositories for Joint-Semantic-Phonetic-Embedding
Users that are interested in Joint-Semantic-Phonetic-Embedding are comparing it to the libraries listed below
Sorting:
- The baseline model code for WMT 2021 Triangular MT☆13Updated 4 years ago
- ☆42Updated 7 years ago
- ☆120Updated 5 years ago
- MaxMatch (M^2) Scorer - Evaluation program for grammatical error correction systems.☆155Updated 3 years ago
- A PyTorch implementation of "Reaching Human-level Performance in Automatic Grammatical Error Correction: An Empirical Study"☆50Updated 6 years ago
- Data Augmentation for Neural Machine Translation☆32Updated 8 years ago
- TVsub: DCU-Tencent Chinese-English Dialogue Corpus☆46Updated 7 years ago
- machine translation and quality estimation☆34Updated 6 years ago
- Models, system configurations and outputs of our winning GEC systems in the BEA 2019 shared task described in R. Grundkiewicz, M. Junczys…☆51Updated 6 years ago
- Scripts to preprocess training and test data and to run fast_align and giza☆107Updated 4 years ago
- ☆31Updated 3 years ago
- Repository of "An Empirical Study of Incorporating Pseudo Data into Grammatical Error Correction" (EMNLP-IJCNLP 2019)☆68Updated 5 years ago
- Code for cross-sentence grammatical error correction using multilayer convolutional seq2seq models (ACL 2019)☆50Updated 5 years ago
- Code for Synchronous Bidirectional Neural Machine Translation (SB-NMT)☆67Updated 6 years ago
- Neural quality estimation toolkit for grammatical error correction and other language generation applications.☆49Updated 6 years ago
- Team Kakao&Brain's Grammatical Error Correction System for the ACL 2019 BEA Shared Task☆92Updated 6 years ago
- Source code for paper: Improving Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data☆251Updated 5 years ago
- My implementation of LASER architecture in Fairseq☆12Updated 5 years ago
- The implementation of "Learning Deep Transformer Models for Machine Translation"☆116Updated last year
- Code for the paper "Multi-Task Learning for Domain-General Spoken Disfluency Detection in Dialogue Systems" (Igor Shalyminov, Arash Eshgh…☆23Updated 3 years ago
- Supplementary material for "When and Why Are Pre-trained Word Embeddings Useful for Neural Machine Translation?" at NAACL 2018☆123Updated 2 months ago
- Fast + Non-Autoregressive Grammatical Error Correction using BERT. Code and Pre-trained models for paper "Parallel Iterative Edit Models …☆231Updated 2 years ago
- Neural models and instructions on how to reproduce our results for our neural grammatical error correction systems from M. Junczys-Dowmun…☆88Updated 6 years ago
- Framework for neural-based Quality Estimation☆42Updated 5 years ago
- code of our EMNLP-19 Paper, CM-Net: A Novel Collaborative Memory Network for Spoken Language Understanding☆28Updated 6 years ago
- MAsked Sequence to Sequence (MASS) pre-training for language generation☆21Updated 6 years ago
- A simple TensorFlow implementation of the Transformer☆25Updated 6 years ago
- ☆15Updated 7 years ago
- We release a dataset based on Wikipedia sentences and the corresponding translations in 6 different languages along with the scores (scal…☆81Updated 4 years ago
- BERT-DST: Scalable End-to-End Dialogue State Tracking with Bidirectional Encoder Representations from Transformer☆100Updated 4 years ago