DeText: A Deep Text Ranking Framework with BERT
Abstract
Ranking is the most important component in a search system. Mostsearch systems deal with large amounts of natural language data,hence an effective ranking system requires a deep understandingof text semantics. Recently, deep learning based natural languageprocessing (deep NLP) models have generated promising results onranking systems. BERT is one of the most successful models thatlearn contextual embedding, which has been applied to capturecomplex query-document relations for search ranking. However,this is generally done by exhaustively interacting each query wordwith each document word, which is inefficient for online servingin search product systems. In this paper, we investigate how tobuild an efficient BERT-based ranking model for industry use cases.The solution is further extended to a general ranking framework,DeText, that is open sourced and can be applied to various rankingproductions. Offline and online experiments of DeText on threereal-world search systems present significant improvement overstate-of-the-art approaches.
Keywords
Cite
@article{arxiv.2008.02460,
title = {DeText: A Deep Text Ranking Framework with BERT},
author = {Weiwei Guo and Xiaowei Liu and Sida Wang and Huiji Gao and Ananth Sankar and Zimeng Yang and Qi Guo and Liang Zhang and Bo Long and Bee-Chung Chen and Deepak Agarwal},
journal= {arXiv preprint arXiv:2008.02460},
year = {2020}
}
Comments
Ranking, Deep Language Models, Natural Language Processing