papers AI Learner
The Github is limit! Click to go to the new site.

Investigating the Successes and Failures of BERT for Passage Re-Ranking

2019-05-05
Harshith Padigela, Hamed Zamani, W. Bruce Croft

Abstract

The bidirectional encoder representations from transformers (BERT) model has recently advanced the state-of-the-art in passage re-ranking. In this paper, we analyze the results produced by a fine-tuned BERT model to better understand the reasons behind such substantial improvements. To this aim, we focus on the MS MARCO passage re-ranking dataset and provide potential reasons for the successes and failures of BERT for retrieval. In more detail, we empirically study a set of hypotheses and provide additional analysis to explain the successful performance of BERT.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.01758

PDF

http://arxiv.org/pdf/1905.01758


Comments