Skip to content

Morpho-semantic Components (MSC) for Word Sense Induction and Disambiguation (WSI\WSD)

License

Notifications You must be signed in to change notification settings

fabiobif/MSC-patterns

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

20 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MSC+ patterns

Identifying the correct meaning of words in context or discovering new word senses is particularly useful for several tasks such as question answering, information extraction, information retrieval, and text summarization. We propose an approach to induce and disambiguate word senses of some target words in collections of short texts, such as tweets, through the use of fuzzy lexico-semantic patterns that we define as sequences of Morpho-semantic Components (MSC).

Getting Started

  • miningMSCpatterns.php is an algorithm to find the most frequent MSC+ patterns in a set of documents.
  • msc-microposts2016test.txt is the document previously annotated with PoS tagging and some word senses.
  • patterns folder has the resulting of the mining MSC+ patterns algorithm.

Citing

If you use any code or sources from MSC patterns in your research work, you are kindly asked to acknowledge the use of the tool in your publications.

Goularte, F.B., Sorato, D., Nassar, S.M., Fileto, R., Saggion, H. "MSC+: Morpho-semantic Components for Word Sense Induction and Disambiguation." 2019.

About

Morpho-semantic Components (MSC) for Word Sense Induction and Disambiguation (WSI\WSD)

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages