Customising Ranking Models for Enterprise Search on Bilingual Click-Through Dataset

TL;DR

This paper details the development of a bilingual enterprise search system, focusing on customizing ranking models to improve search results for technical documents using click-through data and various ranking algorithms.

Contribution

It introduces a comprehensive process for customizing ranking models specifically for bilingual enterprise search using click-through datasets.

Findings

Improved NDCG@k scores with different ranking algorithms

Effective combination of IR methods for bilingual search

Demonstrated system performance on technical enterprise documents

Abstract

In this work, we provide the details about the process of establishing an end-to-end system for enterprise search on bilingual click-through dataset. The first part of the paper will be about the high-level workflow of the system. Then, in the second part we will elaborately mention about the ranking models to improve the search results in the vertical search of the technical documents in enterprise domain. Throughout the paper, we will mention the way which we combine the methods in IR literature. Finally, in the last part of the paper we will report our results using different ranking algorithms with $NDCG@k$ where k is the cut-off value.