AdolfVonKleist / SimpleLM
Simple, standalone python classes for training statistical language models using several popular smoothing methods.
☆25Updated 12 years ago
Related projects ⓘ
Alternatives and complementary repositories for SimpleLM
- Code for EMNLP 2016 paper: Morphological Priors for Probabilistic Word Embeddings☆52Updated 7 years ago
- Code for morphological transformations☆29Updated 7 years ago
- ☆21Updated 9 years ago
- Read-only unofficial mirror of Pynini☆16Updated 5 years ago
- Python bindings for libwapiti☆66Updated 4 years ago
- Fast Word Clustering Software☆74Updated 2 months ago
- bin files☆13Updated 2 months ago
- Context Aware Language Models☆28Updated 6 years ago
- Generalized Language Modeling toolkit☆51Updated 2 years ago
- OxLM: Oxford Neural Language Modelling Toolkit☆39Updated 9 years ago
- A Combinatory Categorial Grammar library.☆22Updated 10 years ago
- Generic Environment for Context-Aware Correction of Orthography☆22Updated 2 years ago
- Fast structured perceptron sequential labeler☆15Updated 8 years ago
- Support library for NLP and machine learning.☆26Updated 7 years ago
- Helsinki Neural Machine Translation system☆29Updated 4 years ago
- C++ implementation of Generalised Brown clustering and python scripts for feature generation☆41Updated 8 years ago
- A simple Python wrapper for the ClearNLP constituents-to-dependencies converter☆10Updated 9 years ago
- A small utility for converting Stanford GloVe vectors to HDF5 / NumPy☆12Updated 7 years ago
- A tool for detecting sentence fragments.☆7Updated 8 years ago
- Yet another regression toolkit☆12Updated 11 years ago
- A Continuous Space Neural Network Language Model based on Theano☆9Updated 8 years ago
- Utility scripts in Python☆37Updated 2 months ago
- TheanoLM is a recurrent neural network language modeling tool implemented using Theano☆81Updated 4 months ago
- An extremely simple Python wrapper for the SRI Language Modeling toolkit☆70Updated 10 years ago
- Symmetrized word alignment models, based on mgizapp and GIZA++☆15Updated 10 years ago
- Normalizes lexically ill-formed text to its most likely clean text, e.g. "c u thr 2nite!" -> "see you there tonight!".☆63Updated 9 years ago
- ☆21Updated 7 years ago
- finite-state toolkit, EM and Bayesian (Gibbs sampling) training for FST and context-free derivation forests☆41Updated 2 years ago
- Hierarchical phrase-based machine translation system☆32Updated 9 years ago
- Torch implementation of the Collobert's SENNA system for NER.☆14Updated 8 years ago