English

Training Mixed-Objective Pointing Decoders for Block-Level Optimization in Search Recommendation

Information Retrieval 2021-05-24 v1

Abstract

Related or ideal follow-up suggestions to a web query in search engines are often optimized based on several different parameters -- relevance to the original query, diversity, click probability etc. One or many rankers may be trained to score each suggestion from a candidate pool based on these factors. These scorers are usually pairwise classification tasks where each training example consists of a user query and a single suggestion from the list of candidates. We propose an architecture that takes all candidate suggestions associated with a given query and outputs a suggestion block. We discuss the benefits of such an architecture over traditional approaches and experiment with further enforcing each individual metric through mixed-objective training.

Keywords

Cite

@article{arxiv.2105.10152,
  title  = {Training Mixed-Objective Pointing Decoders for Block-Level Optimization in Search Recommendation},
  author = {Harsh Kohli},
  journal= {arXiv preprint arXiv:2105.10152},
  year   = {2021}
}

Comments

4 pages. Accepted at the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval

R2 v1 2026-06-24T02:19:45.241Z