dsc / guess-language
Attempts to determine the natural language of a selection of Unicode (utf-8) text (a clone of http://code.google.com/p/guess-language with package metadata)
☆47Updated 14 years ago
Related projects: ⓘ
- Pipeline for distributed Natural Language Processing, made in Python☆64Updated 7 years ago
- common data interchange format for document processing pipelines that apply natural language processing tools to large streams of text☆34Updated 7 years ago
- WebAnnotator is a tool for annotating Web pages. WebAnnotator is implemented as a Firefox extension (https://addons.mozilla.org/en-US/fi…☆48Updated 2 years ago
- Updates to Zope's keyphrase extractor (forked from 1.1.0)☆67Updated 7 years ago
- Lightweight, multilingual natural language processing☆63Updated 11 years ago
- A tool to segment text based on frequencies and the Viterbi algorithm "#TheBoyWhoLived" => ['#', 'The', 'Boy', 'Who', 'Lived']☆82Updated 8 years ago
- clone of https://code.google.com/p/splitta/ so it can be a git submodule☆34Updated 11 years ago
- Discussion Summarization is the process of condensing a text document which is a collection of discussion threads, using CBS (Cluster Bas…☆12Updated 10 years ago
- Python bindings for CLD2.☆17Updated 6 years ago
- Python's missing statistical Swiss Army knife☆15Updated 9 years ago
- Find which links on a web page are pagination links☆29Updated 7 years ago
- rapid nlp prototyping☆72Updated last year
- Plots various graphs for a series of plaintext files in a directory☆19Updated 8 years ago
- Realtime semantic similarity visualization with gensim, d3.js, and hookbox☆40Updated 10 years ago
- Sometimes you just need a lot of text. Plainstream is a small Python app that provides you with a plain text stream directly from Wikiped…☆24Updated 11 months ago
- Character Vomiting☆10Updated 6 years ago
- templatemaker is a Python library that can extract data from files with a similar format, like HTML pages.☆63Updated 3 years ago
- (BROKEN, help wanted)☆15Updated 8 years ago
- ... just because nltk is too heavy☆36Updated 14 years ago
- Memory-based shallow parser for Python☆73Updated 5 years ago
- This is a Python binding to the tokenizer Ucto. Tokenisation is one of the first step in almost any Natural Language Processing task, yet…☆29Updated last week
- Some convenient natural language tools that build on NLTK.☆85Updated 10 years ago
- ☆17Updated 7 years ago
- DEPRECATED - name_tools for Open States and other projects☆19Updated 4 years ago
- C++ Ternary Search Tree implementation with Python bindings☆43Updated 6 years ago
- Entity Linking for the masses☆56Updated 8 years ago
- Readability/Boilerpipe extraction in Python☆55Updated 8 years ago
- [NO LONGER MAINTAINED AS OPEN SOURCE - USE SCALETEXT.COM INSTEAD]☆109Updated 11 years ago
- Automatically exported from code.google.com/p/guess-language☆53Updated 7 months ago
- Wikipedia API wrapper for humans and elk. (en.wikipedia.org/w/api.php, get it?)☆36Updated 10 years ago