Pith. sign in

REVIEW 3 cited by

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

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1905.01758 v1 pith:2FOQQFGH submitted 2019-05-05 cs.IR cs.CL

Harshith Padigela , Hamed Zamani , W. Bruce Croft This is my paper · ORCID
classification cs.IRcs.CL
keywords bertpassagere-rankingfailuresmodelreasonssuccessesadditional
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. On Identifiability in Transformers

    cs.CL 2019-08 conditional novelty 7.0 of 10

    Self-attention weights in Transformers are non-identifiable for long sequences, and the paper offers effective attention and Hidden Token Attribution as diagnostic tools.

  2. DynRank: Improving Passage Retrieval with Dynamic Zero-Shot Prompting Based on Question Classification

    cs.CL 2024-11 conditional novelty 4.0 of 10

    DynRank conditions UPR-style passage reranking on an automatically inferred fine-grained question type and reports small gains over static prompting on NQ, TriviaQA, WebQuestions, and BEIR.

  3. A Study of BERT for Non-Factoid Question-Answering under Passage Length Constraints

    cs.IR 2019-08 conditional novelty 4.0 of 10

    BERT fine-tuning substantially improves non-factoid passage re-ranking over prior baselines, with a 256-token input window performing best and chunking providing a workaround for longer passages.

Pith tools