YerevaNN / translit-rnn
Automatic transliteration with LSTM
☆92Updated 5 years ago
Related projects ⓘ
Alternatives and complementary repositories for translit-rnn
- Language Identification and transliteration tool for Indian language code mixed data.☆23Updated 8 years ago
- ☆68Updated last year
- TheanoLM is a recurrent neural network language modeling tool implemented using Theano☆81Updated 5 months ago
- Morfessor is a tool for unsupervised and semi-supervised morphological segmentation☆185Updated 4 years ago
- Fast supervised sentence boundary detection using the averaged perceptron☆90Updated 5 years ago
- ☆34Updated 7 years ago
- Fast Word Clustering Software☆74Updated 3 months ago
- Easy to use scripts for evaluating word vectors on a variety of tasks.☆120Updated 3 years ago
- Large corpus of uncompressed and compressed sentences from news articles.☆123Updated 7 years ago
- Bidirectional Long-Short Term Memory tagger (bi-LSTM) (in DyNet) -- hierarchical (with word and character embeddings)☆123Updated last year
- LSTM Language Model with Subword Units Input Representations☆43Updated 3 years ago
- General-Purpose Neural Networks for Sentence Boundary Detection☆73Updated last year
- A Multilingual and Multilevel Representation Learning Toolkit for NLP☆117Updated 6 years ago
- Links to data used in Sproat & Jaitly (https://arxiv.org/abs/1611.00068) experiments.☆76Updated 3 years ago
- Python interface for converting Penn Treebank trees to Stanford Dependencies and Universal Depenencies☆68Updated 5 years ago
- Python library for converting UTF to WX and vice-versa for Indian languages.☆48Updated 2 years ago
- Appraise evaluation system for manual evaluation of machine translation output☆74Updated 3 years ago
- ☆29Updated 6 years ago
- Deep neural network based model for sequence to sequence classification☆77Updated 7 years ago
- Code for EMNLP 2016 paper: Morphological Priors for Probabilistic Word Embeddings☆52Updated 7 years ago
- a pytorch implementation of auto-punctuation learned character by character☆141Updated 4 years ago
- Making sense embedding out of word embeddings using graph-based word sense induction☆212Updated 3 years ago
- An extremely simple Python wrapper for the SRI Language Modeling toolkit☆70Updated 10 years ago
- Demonstration of the results in "Text Normalization using Memory Augmented Neural Networks", Authors: Subhojeet Pramanik, Aman Hussain☆60Updated 5 years ago
- A series of scripts to download and parse the OpenSubtitles corpus.☆86Updated 8 years ago
- Automatic extraction of edited sentences from text edition histories.☆81Updated 2 years ago
- Can neural networks order a scramble of words correctly?☆73Updated 7 years ago
- Subjectivity and sentiment classification using polarity lexicons☆88Updated 3 years ago
- Code to train and use models from "Charagram: Embedding Words and Sentences via Character n-grams".☆125Updated 8 years ago