Open Hub
Open Hub

Tags : Browse Projects

Select a tag to browse associated projects and drill deeper into the tag cloud.

botfuel-dialog

Compare

  Analyzed about 21 hours ago

Build highly conversational chatbots

8.7K lines of code

5 current contributors

over 5 years since last commit

0 users on Open Hub

Inactive
5.0
 
0 Reviews
I Use This
Mostly written in JavaScript
Licenses: apache_2
Tags agent bot chatbot development framework nlp node nodejs sdk

finner

Compare

  Analyzed about 11 hours ago

financial NER, like apache-opennlp but actually working

79.7K lines of code

0 current contributors

over 3 years since last commit

0 users on Open Hub

Inactive
0.0
 
0 Reviews
I Use This
Mostly written in C
Licenses: BSD-3-Clause
Tags c command-line-interface ner nlp

NLP-Cube

Compare

  Analyzed about 22 hours ago

Natural Language Processing Pipeline - Sentence Splitting, Tokenization, Lemmatization, Part-of-speech Tagging and Dependency Parsing

46.6K lines of code

10 current contributors

over 2 years since last commit

0 users on Open Hub

Inactive
0.0
 
0 Reviews
I Use This
Mostly written in JavaScript
Licenses: apache_2
Tags extraction information language lemma lemmatization machine natural nlp parsing processing sentece splitting 3 more...

mediacloud_backend

Compare

  Analyzed about 6 hours ago

MediaCloud backend repository

23K lines of code

0 current contributors

almost 10 years since last commit

0 users on Open Hub

Inactive
0.0
 
0 Reviews
I Use This
Mostly written in JavaScript
Licenses: No declared licenses
Tags analytics celery datascience media nlp python rss webcrawler

clic/LM_PRU

Compare

  Analyzed about 7 hours ago

The LiverMemories/Portale della Ricerca Umanistica (LM/PRU) pipeline is a multilingual aware web service for processing archaeology texts. Currently, the input are documents in Portable Document Format (PDF) with machine-encoded text, for example, encoded via optical character recognition (OCR) or ... [More] directly from the source applicaton, and the output are tabular formatted multi-column files. [Less]

9.12K lines of code

0 current contributors

about 13 years since last commit

0 users on Open Hub

Inactive
0.0
 
0 Reviews
I Use This
Mostly written in Python
Licenses: No declared licenses
Tags english hlt italian langid namedentityrecognition natural-language-processing natural_language_processing nlp

Mulm

Compare

  Analyzed about 21 hours ago

Mulm is a state-of-the-art Hidden Markov Model toolkit.

12.8K lines of code

0 current contributors

almost 8 years since last commit

0 users on Open Hub

Inactive
0.0
 
0 Reviews
I Use This
Mostly written in Lisp
Licenses: gpl3
Tags hmm languagemodel markov n-gram nlp partofspeech tagging trigram trigrams

Pattern web mining module

Compare

  Analyzed about 2 hours ago

Pattern is a web mining module for Python 2.5+ with functionality for data retrieval (Google + Twitter + Wikipedia, web spider, HTML DOM parser), natural language processing for English, German and Dutch (tagger/chunker, n-gram search, sentiment analysis, WordNet), machine learning (nearest ... [More] neighbor, clustering, Naive Bayes + k-NN + SVM classifiers) and network analysis (graph centrality, graph visualization). [Less]

58.1K lines of code

0 current contributors

over 5 years since last commit

0 users on Open Hub

Inactive
0.0
 
0 Reviews
I Use This
Mostly written in Python
Licenses: bsd
Tags computational_linguistics data-mining graph graphics javascript machine-learning natural-language-processing nlp python visualization

stem-search.vim

Compare

  Analyzed about 20 hours ago

StmSrch is a reverse-stem searching script. It implements the Porter stemming algorithm, by Martin Porter. It also handles irregular verbs and noun pluralizations. This script can be useful for searching or scanning through corpus files. Each word input to the :StmSrch command will be stemmed ... [More] and then formulated in such a way as to match possible conjugations or pluralizations. Without any word given for input, it will attempt to stem the current word under the cursor. The matching is done using word boundaries so not just any substring will match. For example: - :StmSrch searcher will match any of: - search, searching, searches, searchers, searched, ... and a string of words will work as well, matching in order: - :StmSrch thieves are running from bunnies will match strings of word [Less]

308 lines of code

0 current contributors

over 15 years since last commit

0 users on Open Hub

Inactive
0.0
 
0 Reviews
I Use This
Mostly written in Vim Script
Licenses: mit
Tags corpus corpus_linguistics nlp porter search stem vim

trnltk

Compare

  Analyzed about 20 hours ago

Turkish Natural Language Toolkit

15.5K lines of code

0 current contributors

over 7 years since last commit

0 users on Open Hub

Inactive
0.0
 
0 Reviews
I Use This
Mostly written in Python
Licenses: apache_2
Tags nlp python python27 turkish

Zeitcrawler

Compare

  Analyzed about 2 hours ago

A specialized crawler for the German newspaper 'Die Zeit'. Starting from the front page or from a given list of links, the crawler retrieves newspaper articles and gathers new links to explore as it goes, stripping the text of each article out of the HTML formatting and saving it into a raw text ... [More] file. The project includes scripts to convert it into the XML format for further use with natural language processing tools. [Less]

1.64K lines of code

0 current contributors

over 11 years since last commit

0 users on Open Hub

Inactive
0.0
 
0 Reviews
I Use This
Mostly written in Perl
Licenses: gpl3
Tags academic computational_linguistics corpus corpus_linguistics crawler digital_humanities natural_language_processing nlp perl unix webcrawler xml