HunTag3
Sequential tagger
A tool for sequential sentence tagging using Maximum Entropy Learning and Hidden Markov Models.
A sequential tagger for NLP using Maximum Entropy Learning and Hidden Markov Models
8 stars
7 watching
1 forks
Language: Lex
last commit: about 6 years ago
Linked from 1 awesome list
Related projects:
| Repository | Description | Stars |
|---|---|---|
| | An NLP tool that uses Maximum Entropy Learning and Hidden Markov Models to perform sequential tagging | 22 |
| | An integrated Hungarian verb conjugation dictionary repository combining multiple sources and datasets. | 4 |
| | An implementation of a computational model for linguistic analysis based on cognitive inspiration | 1 |
| | A Java-based tool for annotating text with morphological information using a hybrid approach combining statistical models and rule-based components. | 15 |
| | A Python wrapper around a morphological analysis tool to facilitate language processing tasks | 1 |
| | A Python wrapper and lemmatizer for emMorph, a Hungarian morphological analyzer. | 3 |
| | A toolkit for part-of-speech tagging and morphological analysis | 141 |
| | A word generator based on statistical analysis of letter sequences in a given dictionary. | 172 |
| | A Python API for parsing and querying WordNet XML files in Hungarian language format | 5 |
| | Generates names based on statistical patterns from large datasets using a Markov chain algorithm | 449 |
| | Reproduces results from a 2012 EMNLP paper on type-supervised hidden Markov models for part-of-speech tagging with incomplete tag dictionaries. | 1 |
| | Tool to manage and normalize keywords in Plone content management system | 4 |
| | This project provides different types of Hidden Markov Models (HMMs) for incorporating prosody into basic parsing in natural language processing. | 2 |
| | A large-scale dataset for training models to perform multiple tasks and zero-shot learning in natural language processing. | 473 |
| | Generates pseudorandom words by applying Markov chains to existing word sequences | 33 |