GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → lum-ai → odinson

lum-ai / odinson

Licence: Apache-2.0 license
Odinson is a powerful and highly optimized open-source framework for rule-based information extraction. Odinson couples a simple, yet powerful pattern language that can operate over multiple representations of text, with a runtime system that operates in near real time.

Programming Languages

scala
5932 projects

Labels

nlpsyntaxopen-sourcetext-mininginformation-extractionsurfacerule-basedextraction-engineodinson

Projects that are alternatives of or similar to odinson

TabInOut
Framework for information extraction from tables
Stars: ✭ 37 (-37.29%)
Mutual labels:  text-mining, information-extraction, rule-based
neji
Flexible and powerful platform for biomedical information extraction from text
Stars: ✭ 37 (-37.29%)
Mutual labels:  text-mining, information-extraction
Awesome Hungarian Nlp
A curated list of NLP resources for Hungarian
Stars: ✭ 121 (+105.08%)
Mutual labels:  text-mining, information-extraction
slotminer
Tool for slot extraction from text
Stars: ✭ 15 (-74.58%)
Mutual labels:  information-extraction, rule-based
deduce
Deduce: de-identification method for Dutch medical text
Stars: ✭ 40 (-32.2%)
Mutual labels:  text-mining, information-extraction
Chemdataextractor
Automatically extract chemical information from scientific documents
Stars: ✭ 152 (+157.63%)
Mutual labels:  text-mining, information-extraction
palladian
Palladian is a Java-based toolkit with functionality for text processing, classification, information extraction, and data retrieval from the Web.
Stars: ✭ 32 (-45.76%)
Mutual labels:  text-mining, information-extraction
TableDisentangler
Functional and structural analysis of tables in research papers (Table disentangling)
Stars: ✭ 21 (-64.41%)
Mutual labels:  text-mining, information-extraction
news-graph
Key information extraction from text and graph visualization
Stars: ✭ 83 (+40.68%)
Mutual labels:  information-extraction
ninja-ui-syntax
Beautiful Atom syntax theme inspired by a Dribbble shot.
Stars: ✭ 17 (-71.19%)
Mutual labels:  syntax
TypeNet
A Hierarchical Type system for fine grained entity typing
Stars: ✭ 51 (-13.56%)
Mutual labels:  information-extraction
Search
Blue Brain text mining toolbox for semantic search and structured information extraction
Stars: ✭ 26 (-55.93%)
Mutual labels:  text-mining
postcss-styled
PostCSS syntax for parsing styled components
Stars: ✭ 53 (-10.17%)
Mutual labels:  syntax
Linux Dynamic Wallpapers
Dynamic Wallpapers for Linux
Stars: ✭ 305 (+416.95%)
Mutual labels:  surface
evil-textobj-syntax
This package is a port of vim-textobj-syntax for emacs. It provides evil text objects for consecutive items with same syntax highlight.
Stars: ✭ 19 (-67.8%)
Mutual labels:  syntax
fast-tsetlin-machine-with-mnist-demo
A fast Tsetlin Machine implementation employing bit-wise operators, with MNIST demo.
Stars: ✭ 58 (-1.69%)
Mutual labels:  rule-based
CogIE
CogIE: An Information Extraction Toolkit for Bridging Text and CogNet. ACL 2021
Stars: ✭ 47 (-20.34%)
Mutual labels:  information-extraction
PolyDraw
✳️ PTSource PolyDraw is a free 3D polygonal modeller for Windows x86 and x64, for creating or modifying 3D objects using a mesh of 3D points and parametric NURBS Curves .Exports and imports to over 40 formats including WebVR and 3D Printing.
Stars: ✭ 17 (-71.19%)
Mutual labels:  surface
jsdoc-syntax.vim
Standalone JSDoc syntax for vim
Stars: ✭ 17 (-71.19%)
Mutual labels:  syntax
react-cheatsheets
Create and generate cheat sheets using React
Stars: ✭ 21 (-64.41%)
Mutual labels:  syntax
View All Similar Projects ➔

Tests (GitHub Actions) codecov

Odinson

Odinson can be used to rapidly query a natural language knowledge base and extract structured relations. Query patterns can be designed over (a) surface, syntax, or a combination of both. In particular, Odinson has been highly optimized to deliver these results in near real-time, which enables users to dynamically develop queries, receiving immediate feedback on the coverage and precision of the patterns at scale. Please see our LREC 2020 paper for technical details and evaluation.

Documentation

Please see http://gh.lum.ai/odinson/, for documentation, including information about installation, capabilities, and learning how to build queries.

Project overview

Odinson supports a wide range of features, including:

  • Patterns over tokens, including boolean patterns over token features like lemma, POS tags, NER tags, chunk tags, etc
  • Patterns over syntax by matching paths in a dependency graph. Note that this actually agnostic to the tags in the graph edges and it could be repurposed for matching over semantic roles or something else.
  • Named captures for extracting the different entities involved in a relation
  • Support for greedy and lazy quantifiers, lookaround assertions, etc.
  • Support for an internal state to hold intermediate mentions, allowing for the application of patterns in a cascade
  • Support for grammars
  • Filtering results by document metadata (e.g., authors, publication date)
  • and much, much more!

Again, please see our documentation, for more information!

We would also love to hear any questions, requests, or suggestions you may have.

Contributions

If you would like to contribute to this project with code, rule sets, or other repo material, that's awesome! Please do! Some of these materials will help you get started:

  • There is a document covering some of the technical issues related to contributing like the Pull Request Process and Formatting Tips.
  • We do ask you to be nice, and we spell that out in a Covenant Code of Conduct. Of course you can expect the same behavior of us.
  • Please ensure the contributions you propose are yours to give and you are comfortable with the shared rights. There is a Contributor License Agreement (CLA) that you will sign before a pull request is accepted so there are no surprises for any of us. Please take a look at the CLA before you get too far, just in case, as there are legal ramifications.

Thanks for your interest in Odinson!

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].