{"work":{"id":"562fbfab-d6fe-48e1-a06d-e5d078c70945","openalex_id":null,"doi":null,"arxiv_id":"1901.04085","raw_key":null,"title":"Passage Re-ranking with BERT","authors":null,"authors_text":"Rodrigo Nogueira, Kyunghyun Cho","year":2019,"venue":"cs.IR","abstract":"Recently, neural models pretrained on a language modeling task, such as ELMo (Peters et al., 2017), OpenAI GPT (Radford et al., 2018), and BERT (Devlin et al., 2018), have achieved impressive results on various natural language processing tasks such as question-answering and natural language inference. In this paper, we describe a simple re-implementation of BERT for query-based passage re-ranking. Our system is the state of the art on the TREC-CAR dataset and the top entry in the leaderboard of the MS MARCO passage retrieval task, outperforming the previous state of the art by 27% (relative) in MRR@10. The code to reproduce our results is available at https://github.com/nyu-dl/dl4marco-bert","external_url":"https://arxiv.org/abs/1901.04085","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-16T16:48:06.337181+00:00","pith_arxiv_id":"1901.04085","created_at":"2026-05-10T00:24:46.872260+00:00","updated_at":"2026-05-16T16:48:06.337181+00:00","title_quality_ok":false,"display_title":"Passage Re-ranking with BERT","render_title":"Passage Re-ranking with BERT"},"hub":{"state":{"work_id":"562fbfab-d6fe-48e1-a06d-e5d078c70945","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":45,"external_cited_by_count":null,"distinct_field_count":8,"first_pith_cited_at":"2020-04-10T04:53:17+00:00","last_pith_cited_at":"2026-05-14T07:47:44+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-05-16T17:48:56.996246+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":3}],"polarity_counts":[{"context_polarity":"background","n":3}],"runs":{"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-14T18:09:32.437956+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","work_id":"c5f7f027-ac36-4b07-b824-0eca2f310641","shared_citers":8},{"title":"arXiv preprint arXiv:2312.02724 , year=","work_id":"0d9b3ad1-b405-412f-81ee-fd6f941d2367","shared_citers":7},{"title":"Retrieval-Augmented Generation for Large Language Models: A Survey","work_id":"b80d2790-6cd9-4c87-b3c4-de404f99a80e","shared_citers":7},{"title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","work_id":"27adfcc9-2a67-43d6-a844-78309012411f","shared_citers":7},{"title":"arXiv preprint arXiv:2309.15088 , year=","work_id":"6196b66d-d87d-460e-bd36-fa58f800ca9b","shared_citers":5},{"title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","work_id":"588618d7-fd41-4053-b34d-a981f8793039","shared_citers":5},{"title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","work_id":"789cc674-467e-4f23-bb50-05c79fe8c4c2","shared_citers":5},{"title":"CoRRabs/2003.07820(2020), https://arxiv.org/ abs/2003.07820","work_id":"083b288a-95a1-4846-959c-e69b87d8885c","shared_citers":4},{"title":"doi: 10.18653/v1/ 2024.findings-acl.586","work_id":"8d675bdd-79ca-48d6-9163-fc17ce0e8ece","shared_citers":4},{"title":"Is C hat GPT Good at Search? Investigating Large Language Models as Re-Ranking Agents","work_id":"7dd0e789-8a59-408d-8f34-4fe23b7490ce","shared_citers":4},{"title":"M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation","work_id":"a9435752-4e49-42bd-95b4-0fec975633c8","shared_citers":4},{"title":"arXiv preprint arXiv:2004.04906 , year=","work_id":"3d6f2008-b001-4542-ba3f-192f6880c74b","shared_citers":3},{"title":"ColBERT: Efficient and effective passage search via con- textualized late interaction over bert","work_id":"a0aa64b7-2891-458f-a5ef-35ff6fa77f18","shared_citers":3},{"title":"C-Pack: Packed Resources For General Chinese Embeddings","work_id":"5d8d3efd-bb5b-4a30-8457-28f190c026e9","shared_citers":3},{"title":"Dense passage retrieval for open-domain question answering","work_id":"083391f8-812d-430f-8d08-89a03031ce6c","shared_citers":3},{"title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","work_id":"9ff0ede5-1ff9-4694-80ea-fd9845a497f9","shared_citers":3},{"title":"FEVER: a large-scale dataset for Fact Extraction and VERification","work_id":"b696f75f-e5ad-4555-9c12-e292e77c388f","shared_citers":3},{"title":"LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory","work_id":"9074870f-aee7-4103-b167-ac6473a8a9b3","shared_citers":3},{"title":"Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory","work_id":"a5aed26c-a248-48b6-a59e-f7693fcb180a","shared_citers":3},{"title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","work_id":"78d498ce-11db-4f88-8eb0-40e0f86af615","shared_citers":3},{"title":"Overview of the trec 2020 deep learning track","work_id":"08c56b45-a87e-4374-9a23-6404c928b6ea","shared_citers":3},{"title":"Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models","work_id":"bab684a8-d933-426c-a19e-2c855a0d1f59","shared_citers":3},{"title":"REALM: retrieval-augmented language model pre-training","work_id":"a397ddf8-b0b7-4e32-9d59-fb6ea67ac287","shared_citers":3},{"title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","work_id":"6246e99b-7b4e-4424-be78-3e1983932cdc","shared_citers":3}],"time_series":[{"n":1,"year":2020},{"n":2,"year":2021},{"n":31,"year":2026}],"dependency_candidates":[]},"error":null,"updated_at":"2026-05-14T18:09:19.762391+00:00"},"identity_refresh":{"job_type":"identity_refresh","status":"succeeded","result":{"items":[{"title":"Qwen3 Technical Report","outcome":"unchanged","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","resolver":"local_arxiv","confidence":0.98,"old_work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e"}],"counts":{"fixed":0,"merged":0,"unchanged":1,"quarantined":0,"needs_external_resolution":0},"errors":[],"attempted":1},"error":null,"updated_at":"2026-05-14T18:09:36.893596+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"Passage Re-ranking with BERT","claims":[{"claim_text":"Recently, neural models pretrained on a language modeling task, such as ELMo (Peters et al., 2017), OpenAI GPT (Radford et al., 2018), and BERT (Devlin et al., 2018), have achieved impressive results on various natural language processing tasks such as question-answering and natural language inference. In this paper, we describe a simple re-implementation of BERT for query-based passage re-ranking. Our system is the state of the art on the TREC-CAR dataset and the top entry in the leaderboard of the MS MARCO passage retrieval task, outperforming the previous state of the art by 27% (relative) ","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Passage Re-ranking with BERT because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-14T18:09:44.982190+00:00"}},"summary":{"title":"Passage Re-ranking with BERT","claims":[{"claim_text":"Recently, neural models pretrained on a language modeling task, such as ELMo (Peters et al., 2017), OpenAI GPT (Radford et al., 2018), and BERT (Devlin et al., 2018), have achieved impressive results on various natural language processing tasks such as question-answering and natural language inference. In this paper, we describe a simple re-implementation of BERT for query-based passage re-ranking. Our system is the state of the art on the TREC-CAR dataset and the top entry in the leaderboard of the MS MARCO passage retrieval task, outperforming the previous state of the art by 27% (relative) ","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Passage Re-ranking with BERT because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","work_id":"c5f7f027-ac36-4b07-b824-0eca2f310641","shared_citers":8},{"title":"arXiv preprint arXiv:2312.02724 , year=","work_id":"0d9b3ad1-b405-412f-81ee-fd6f941d2367","shared_citers":7},{"title":"Retrieval-Augmented Generation for Large Language Models: A Survey","work_id":"b80d2790-6cd9-4c87-b3c4-de404f99a80e","shared_citers":7},{"title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","work_id":"27adfcc9-2a67-43d6-a844-78309012411f","shared_citers":7},{"title":"arXiv preprint arXiv:2309.15088 , year=","work_id":"6196b66d-d87d-460e-bd36-fa58f800ca9b","shared_citers":5},{"title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","work_id":"588618d7-fd41-4053-b34d-a981f8793039","shared_citers":5},{"title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","work_id":"789cc674-467e-4f23-bb50-05c79fe8c4c2","shared_citers":5},{"title":"CoRRabs/2003.07820(2020), https://arxiv.org/ abs/2003.07820","work_id":"083b288a-95a1-4846-959c-e69b87d8885c","shared_citers":4},{"title":"doi: 10.18653/v1/ 2024.findings-acl.586","work_id":"8d675bdd-79ca-48d6-9163-fc17ce0e8ece","shared_citers":4},{"title":"Is C hat GPT Good at Search? Investigating Large Language Models as Re-Ranking Agents","work_id":"7dd0e789-8a59-408d-8f34-4fe23b7490ce","shared_citers":4},{"title":"M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation","work_id":"a9435752-4e49-42bd-95b4-0fec975633c8","shared_citers":4},{"title":"arXiv preprint arXiv:2004.04906 , year=","work_id":"3d6f2008-b001-4542-ba3f-192f6880c74b","shared_citers":3},{"title":"ColBERT: Efficient and effective passage search via con- textualized late interaction over bert","work_id":"a0aa64b7-2891-458f-a5ef-35ff6fa77f18","shared_citers":3},{"title":"C-Pack: Packed Resources For General Chinese Embeddings","work_id":"5d8d3efd-bb5b-4a30-8457-28f190c026e9","shared_citers":3},{"title":"Dense passage retrieval for open-domain question answering","work_id":"083391f8-812d-430f-8d08-89a03031ce6c","shared_citers":3},{"title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","work_id":"9ff0ede5-1ff9-4694-80ea-fd9845a497f9","shared_citers":3},{"title":"FEVER: a large-scale dataset for Fact Extraction and VERification","work_id":"b696f75f-e5ad-4555-9c12-e292e77c388f","shared_citers":3},{"title":"LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory","work_id":"9074870f-aee7-4103-b167-ac6473a8a9b3","shared_citers":3},{"title":"Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory","work_id":"a5aed26c-a248-48b6-a59e-f7693fcb180a","shared_citers":3},{"title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","work_id":"78d498ce-11db-4f88-8eb0-40e0f86af615","shared_citers":3},{"title":"Overview of the trec 2020 deep learning track","work_id":"08c56b45-a87e-4374-9a23-6404c928b6ea","shared_citers":3},{"title":"Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models","work_id":"bab684a8-d933-426c-a19e-2c855a0d1f59","shared_citers":3},{"title":"REALM: retrieval-augmented language model pre-training","work_id":"a397ddf8-b0b7-4e32-9d59-fb6ea67ac287","shared_citers":3},{"title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","work_id":"6246e99b-7b4e-4424-be78-3e1983932cdc","shared_citers":3}],"time_series":[{"n":1,"year":2020},{"n":2,"year":2021},{"n":31,"year":2026}],"dependency_candidates":[]},"authors":[]}}