Context Attentive Document Ranking and Query Suggestion

Wasi Ahmad, Kai-Wei Chang, and Hongning Wang, in SIGIR, 2019.


[Full Text]

Abstract

We present a context-aware neural ranking model to exploit users’ on-task search activities and enhance retrieval performance. Inparticular, a two-level hierarchical recurrent neural network isintroduced to learn search context representation of individualqueries, search tasks, and corresponding dependency structure byjointly optimizing two companion retrieval tasks: document rank-ing and query suggestion. To identify variable dependency structurebetween search context and users’ ongoing search activities, at-tention at both levels of recurrent states are introduced. Extensiveexperiment comparisons against a rich set of baseline methods andan in-depth ablation analysis confirm the value of our proposedapproach for modeling search context buried in search tasks.

Bib Entry

@inproceedings{ahmad2019context,
  author = {Ahmad, Wasi and Chang, Kai-Wei and Wang, Hongning},
  title = {Context Attentive Document Ranking and Query Suggestion},
  booktitle = {SIGIR},
  slides_url = {/documents/slides/ahmad2019context_slide.pdf},
  year = {2019}
}

Links