IRCLMay 5, 2019

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

arXiv:1905.01758v147 citations
Originality Synthesis-oriented
AI Analysis

It provides insights into BERT's performance for retrieval, which is incremental as it explains existing results rather than introducing new methods.

The paper analyzes why BERT improves passage re-ranking on the MS MARCO dataset, identifying reasons for its successes and failures through empirical study.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes