graehl / carmelLinks
finite-state toolkit, EM and Bayesian (Gibbs sampling) training for FST and context-free derivation forests
☆41Updated 2 years ago
Alternatives and similar repositories for carmel
Users that are interested in carmel are comparing it to the libraries listed below
Sorting:
- Fast Word Clustering Software☆78Updated 7 months ago
- A Combinatory Categorial Grammar library.☆22Updated 11 years ago
- Open-source tools for morphological tagging, segmentation and stemming.☆40Updated 6 years ago
- Code for morphological transformations☆29Updated 8 years ago
- Utilities for manipulating finite state transducers with the OpenFst library.☆32Updated 7 years ago
- Expected edit distance implementation using OpenFst tools☆11Updated 10 years ago
- ☆43Updated 10 years ago
- C++ implementation of Generalised Brown clustering and python scripts for feature generation☆41Updated 9 years ago
- UniParse: A universal graph-based parsing toolkit☆10Updated 5 years ago
- pronunciation LEXicons for Any Low-resource Language☆21Updated 5 years ago
- ☆21Updated 10 years ago
- Corpus preprocessing☆98Updated last year
- bin files☆13Updated 7 months ago
- Simple, standalone python classes for training statistical language models using several popular smoothing methods.☆24Updated 12 years ago
- Support library for NLP and machine learning.☆27Updated 8 years ago
- Zurich Morphological Lexicon for German: a tool to extract a morphological lexicon from Wiktionary☆11Updated 2 years ago
- Search back-end for dependency tree search. See the docs at https://fginter.github.io/dep_search/☆17Updated 7 years ago
- Thot toolkit for statistical machine translation☆53Updated 2 years ago
- A tool for text normalisation via character-level machine translation☆13Updated 5 years ago
- ☆21Updated 8 years ago
- A Python interface to OpenFst☆88Updated 6 years ago
- Parsito: Fast non-projective transition-based dependency parser☆14Updated 2 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
- The repository for the paper "When Do You Need Billions of Words of Pretraining Data?"☆21Updated 4 years ago
- English web corpus with 4M tokens and several annotation types☆26Updated 2 years ago
- ☆28Updated 4 years ago
- Deep learning model of machine translation using attentional and structural biases☆13Updated 8 years ago
- Read-only unofficial mirror of Pynini☆17Updated 6 years ago
- A web demo for visualizing Semafor parses☆29Updated 7 years ago
- Discontinuous Data-Oriented Parsing☆46Updated last year