Wasi Ahmad, Kai-Wei Chang, Hongning Wang

ICLR 2018

Links

We propose a multi-task learning framework to jointly learn document ranking and query suggestion for web search. It consists of two major components, a document ranker and a query recommender. Document ranker combines current query and session information and compares the combined representation with document representation to rank the documents. Query recommender tracks users�� query reformulation sequence considering all previous in-session queries using a sequence to sequence approach. As both tasks are driven by the users�� underlying search intent, we perform joint learning of these two components through session recurrence, which encodes search context and intent. Extensive comparisons against state-of-the-art document ranking and query suggestion algorithms are performed on the public AOL search log, and the promising results endorse the effectiveness of the joint learning framework.

Bib entry

@inproceedings{ACW18,
author = {Wasi Ahmad and Kai-Wei Chang and Hongning Wang},
title = {Multi-Task Learning for Document Ranking and Query Suggestion},
booktitle = {ICLR},
year = {2018},
}