k-NN for question answering (QA) and information retrieval (IR)
This is a learning-to-rank pipeline, which is a part of the project where we study applicability of k-nearest neighbor search methods to IR and QA applications. This project is supported primarily by the NSF grant #1618159 : "Matching and Ranking via Proximity Graphs: Applications to Question Answering and Beyond".
It currently has two branches:
bigger_rerunsbranch 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..
cikm2016branch 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.
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