REVIEW 5 cited by
Understanding the Behaviors of BERT in Ranking
Not yet reviewed by Pith; the record is open.
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
Signed reviews
read the original abstract
This paper studies the performances and behaviors of BERT in ranking tasks. We explore several different ways to leverage the pre-trained BERT and fine-tune it on two ranking tasks: MS MARCO passage reranking and TREC Web Track ad hoc document ranking. Experimental results on MS MARCO demonstrate the strong effectiveness of BERT in question-answering focused passage ranking tasks, as well as the fact that BERT is a strong interaction-based seq2seq matching model. Experimental results on TREC show the gaps between the BERT pre-trained on surrounding contexts and the needs of ad hoc document ranking. Analyses illustrate how BERT allocates its attentions between query-document tokens in its Transformer layers, how it prefers semantic matches between paraphrase tokens, and how that differs with the soft match patterns learned by a click-trained neural ranker.
Forward citations
Cited by 5 Pith papers
-
Learning an Effective Premise Retrieval Model for Efficient Mathematical Formalization
A compact BERT retriever for Lean premises, trained with a Lean-specific tokenizer and fine-grained similarity plus re-ranking, outperforms prior retrievers on most splits and lifts MiniF2F pass@1.
-
Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey
A survey organizes current research on trustworthy RAG into six pillars, reliability, privacy, safety, fairness, explainability, and accountability, and maps methods, metrics, and open problems for each.
-
HNCSE: Advancing Sentence Embeddings via Hybrid Contrastive Learning with Hard Negatives
HNCSE reports 2-point average STS gains over SimCSE using positive mixing and hard-negative mixing, but the method is under-specified and unverified.
-
Revisiting Semantic Representation and Tree Search for Similar Question Retrieval
Similar-question retrieval using BERT embeddings can be accelerated by a k-means tree with beam search, at a cost of about 0.04 MAP on a Quora Question Pairs ranking task.
-
A Study of BERT for Non-Factoid Question-Answering under Passage Length Constraints
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.
Discussion (0). Continue with ORCID to comment.