Skip to content

Implementation and Evaluation of "A Deep Relevance Matching Model for Ad-hoc Retrieval"

License

Notifications You must be signed in to change notification settings

sebastian-hofstaetter/neural-ranking-drmm

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

24 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Hello,

this repository contains an implementation of the DRMM model.

Original paper: A Deep Relevance Matching Model for Ad-hoc Retrieval (Guo et al.) https://dl.acm.org/citation.cfm?id=2983769

Some code is taken from MatchZoo (referenced in the respective files).

Table of Contents

  • Preprocessing: Contains all preprocessing code (starting from raw TREC data) to create all input files for the neural ranking model (this includes generating the histogram, idf informations). See the peprocessing Readme for more.

  • Neural Ranking: Contains the neural ranking model

  • Results: Contains a description of experiments & their raw and trec_eval evaluated results.

Dependencies

  • TREC 8 corpus data (not preprocessed: fbis,fr94,ft,latimes)
  • Python 3: Latest Keras and Tensorflow

About

Implementation and Evaluation of "A Deep Relevance Matching Model for Ad-hoc Retrieval"

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published