Skip to content

Latest commit

 

History

History
13 lines (9 loc) · 1.82 KB

knn4qa.md

File metadata and controls

13 lines (9 loc) · 1.82 KB
Raw

Former life (as a knn4qa package)

This project grew out of a knn4qa project. It aimed to study applicability of k-nearest neighbor search methods to IR and QA applications. This project was supported primarily by the NSF grant #1618159 : "Matching and Ranking via Proximity Graphs: Applications to Question Answering and Beyond".

Previous work can be found in the following branches branches:

  1. The bigger_reruns branch includes software used in the dissertation of Leonid Boytsov: "Efficient and Accurate Non-Metric k-NN Search with Applications to Text Matching". A summary of this work is given in the following blog post..
  2. The cikm2016 branch includes software for the paper L. Boytsov, D. Novak, Y. Malkov, E. Nyberg (2016). Off the Beaten Path: Let’s Replace Term-Based Retrieval with k-NN Search, CIKM'16. This work is covered in a blog post as well. For more details on this branch software, please, check the Wiki page.

NB: Our cikm2016 branch can be also used to partially reproduce results from the paper: M Surdeanu, M Ciaramita, H Zaragoza. Learning to rank answers to non-factoid questions from web collections Computational Linguistics, 2011