PubTag: Generating Research Tag-Clouds with Keyphrase Extraction and Learning-to-Rank
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
cstagclouds
data
.gitignore
README.md
requirements.txt
tagcloud.py

README.md

PubTag

PubTag: Generating Research Tag-Clouds with Keyphrase Extraction and Learning-to-Rank

Data

  • A labelled dataset of 1,126 author-scored keyphrases extracted from the text of papers coauthored by 12 Computer Science professors, which can be found in data/scored_keyphrases.
  • An evaluation of four learning-to-rank frameworks using the above dataset, and a comparison of their results with an unsupervised keyphrase extraction framework, which can be found in data/evaluation
  • Raw text data used for evaluation in data/txt