--- title: "Rodrigo Nogueira — author profile and papers" description: "Rodrigo Nogueira, Universidade Estadual de Campinas (UNICAMP): 3 papers on Elamur Research (2019–2020), h-index 27 — affiliations, topics, co-authors and…" canonical: "https://research.elamur.ai/free/en/authors/rodrigo-nogueira/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/rodrigo-nogueira/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Rodrigo Nogueira # Rodrigo Nogueira Rodrigo Nogueira works in information retrieval, studying how pretrained neural language models can improve the ranking of passages and documents for search and question answering. Their papers here, from 2019 and 2020, share one setting. An inexpensive first-stage retriever such as BM25 returns candidates, and a neural model then either reorders them or changes the text that gets indexed. The experiments draw mainly on the MS MARCO collection, with further tests on TREC benchmarks. The most cited of these is [Passage Re-ranking with BERT](https://md.research.elamur.ai/free/en/papers/nogueira-2019-passage-re-ranking-bert/) (2019). It fine-tunes BERT as a binary relevance classifier that reads a query and a candidate passage together. The paper argues that large training sets combined with pretraining let neural rankers surpass classical methods. [Document Expansion by Query Prediction](https://md.research.elamur.ai/free/en/papers/nogueira-2019-document-expansion-query-prediction/) (2019) approaches vocabulary mismatch from the document side rather than by rewriting queries. Its method, Doc2query, trains a sequence-to-sequence transformer to produce questions that a passage could answer. Those predicted questions are added to each passage before ordinary BM25 indexing. The newest work, [Document Ranking with a Pretrained Sequence-to-Sequence Model](https://md.research.elamur.ai/free/en/papers/nogueira-2020-document-ranking-pretrained-sequence-sequence/) (2020), treats reranking as generation instead of classification. T5 models of several sizes are fine-tuned to output "true" or "false" for a query–document pair placed in a simple template. The scores for those two tokens give a relevance probability used to reorder BM25 results. The paper also reports strong results when the model is applied without in-domain training to Robust04, Core17 and Core18. Nogueira is based at the Universidade Estadual de Campinas (UNICAMP) in Campinas, Brazil. Bylines also list the [University of Waterloo](https://md.research.elamur.ai/free/en/universities/university-of-waterloo/) (2020–2023) and [New York University](https://md.research.elamur.ai/free/en/universities/new-york-university/) (2016–2020). Co-authors on these papers include [Kyunghyun Cho](https://md.research.elamur.ai/free/en/authors/kyunghyun-cho/), [Jimmy Lin](https://md.research.elamur.ai/free/en/authors/jimmy-lin/) and [Wei Yang](https://md.research.elamur.ai/free/en/authors/wei-yang/), and the work sits within [Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/). Rodrigo Nogueira has 3 papers in our library, in 2019–2020, most of them on [Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/); often with [Jimmy Lin](https://md.research.elamur.ai/free/en/authors/jimmy-lin/), [Kyunghyun Cho](https://md.research.elamur.ai/free/en/authors/kyunghyun-cho/), [Wei Yang](https://md.research.elamur.ai/free/en/authors/wei-yang/). 3 papers in our library · 2019–2020 [OpenAlex](https://openalex.org/A5030647281) · [ORCID](https://orcid.org/0000-0002-2600-6035) · [Wikidata](https://www.wikidata.org/wiki/Q130842243) · [**h-index 27**](https://openalex.org/authors/A5030647281) · [125 works](https://openalex.org/works?filter=author.id:A5030647281) · [4,492 citations](https://openalex.org/works?filter=author.id:A5030647281&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 3 works in our library](https://md.research.elamur.ai/free/en/authors/rodrigo-nogueira/#papers) · [🔗 745 citations in our library](https://md.research.elamur.ai/free/en/authors/rodrigo-nogueira/cited-by/) · [9 more in our library without a page yet](#also) · [⭐ Paper Star rank #1493](https://md.research.elamur.ai/free/en/paper-stars/page/15/#star-1493) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Rodrigo+Nogueira) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Rodrigo+Nogueira) · [dblp](https://dblp.org/search?q=Rodrigo+Nogueira) · [ACL Anthology](https://aclanthology.org/search/?q=Rodrigo+Nogueira) ## Affiliations [🎓**Universidade Estadual de Campinas (UNICAMP)** Campinas · Brazil 2014–2026 · 40 papers*current*](https://ror.org/04wffgt70) · [🎓**University of Waterloo** Waterloo · Canada 2020–2023 · 36 papers](https://md.research.elamur.ai/free/en/universities/university-of-waterloo/) · [🎓**New York University** New York · United States 2016–2020 · 11 papers](https://md.research.elamur.ai/free/en/universities/new-york-university/) · [🔬**Instituto Federal Catarinense** Blumenau · Brazil 2017–2019 · 2 papers](https://ror.org/02f8h1m78) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed. ## Topics [Information retrieval & search (2)](https://md.research.elamur.ai/free/en/topics/information-retrieval/) ## Works by year ### 2020s [**2020** 1 paper](https://md.research.elamur.ai/free/en/papers/nogueira-2020-document-ranking-pretrained-sequence-sequence/) ### 2010s [**2019** 2 papers](https://md.research.elamur.ai/free/en/authors/rodrigo-nogueira/year/2019/) ## Papers The most cited first (OpenAlex and our library). 1. **[Passage Re-ranking with BERT](https://md.research.elamur.ai/free/en/papers/nogueira-2019-passage-re-ranking-bert/)** *(2019 · 667 citations)* Nogueira and Cho look at the middle step of a typical retrieval-based question-answering pipeline. In that step, a cheap first-stage retriever (BM25) returns about a thousand candidate passages, and a more expensive model must reorder them so the truly relevant ones come first. Neural rankers had not yet clearly… 2. **[Document Ranking with a Pretrained Sequence-to-Sequence Model](https://md.research.elamur.ai/free/en/papers/nogueira-2020-document-ranking-pretrained-sequence-sequence/)** *(2020 · 538 citations)* The paper reframes neural document reranking as a generation task, departing from the usual approach of encoder-only classifiers such as BERT. 3. **[Document Expansion by Query Prediction](https://md.research.elamur.ai/free/en/papers/nogueira-2019-document-expansion-query-prediction/)** *(2019 · 317 citations)* Search engines often miss relevant texts because users phrase queries with different words than the documents use. ## Also in our library 9 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 3 co-authors with a page, the most papers together first. - [Jimmy Lin](https://md.research.elamur.ai/free/en/authors/jimmy-lin/) ×2 - [Kyunghyun Cho](https://md.research.elamur.ai/free/en/authors/kyunghyun-cho/) ×2 - [Wei Yang](https://md.research.elamur.ai/free/en/authors/wei-yang/) ## Cited by Papers of our library cite their works 745 times (of the 140,884 papers whose bibliographies we read); [41 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/rodrigo-nogueira/cited-by/).