--- title: "Nicholas FitzGerald — author profile and papers" description: "Nicholas FitzGerald: 3 papers on Elamur Research (2018–2020), h-index 14 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/nicholas-fitzgerald/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/nicholas-fitzgerald/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Nicholas FitzGerald # Nicholas FitzGerald Nicholas FitzGerald works in natural language processing, on how text can be turned into structured meaning and how models can capture knowledge about entities. Their papers here cover predicate-argument structure expressed through natural-language questions, relation representations between pairs of entity mentions, and language models that hold facts about entities in their own parameters. The methods combine large crowdsourced annotation, neural parsing pipelines, and Transformer pre-training with entity supervision. The most cited work here is [Matching the Blanks](https://md.research.elamur.ai/free/en/papers/soares-2019-matching-blanks-distributional-similarity-relation/) (2019). Using BERT, it compares ways of marking two target entities and of reading a relation vector off the output, and finds that special marker tokens work best. It then introduces a pre-training objective that learns relation representations from entity-linked text alone, with no need for a predefined relation inventory or an extensive knowledge base. Earlier, [Large-Scale QA-SRL Parsing](https://md.research.elamur.ai/free/en/papers/fitzgerald-2018-large-scale-qa-srl-parsing/) (2018) released a much larger QA-SRL corpus covering Wikipedia, Wikinews and science textbooks. It was gathered through a streamlined crowdsourcing interface with a separate validation step. The paper also trains a parser that first detects answer spans and then generates role questions for them. The newest paper here, [Entities as Experts](https://md.research.elamur.ai/free/en/papers/fevry-2020-entities-as-experts-sparse-memory/) (2020), turns to storing factual knowledge inside a language model rather than in an external knowledge base. It inserts an entity memory layer partway through a Transformer, between its lower and upper stacks. Unlike approaches that plug in embeddings trained separately, it trains the entity embeddings jointly with the whole model. This continues the entity-centred line of the relation-learning work, and the papers here touch on [semantic role labeling](https://md.research.elamur.ai/free/en/topics/semantic-role-labeling/), question answering and [knowledge graphs & ontologies](https://md.research.elamur.ai/free/en/topics/knowledge-graphs/). Bylines on these papers place FitzGerald at [Google](https://md.research.elamur.ai/free/en/companies/google/) from 2018 and, before that, at the [University of Washington](https://md.research.elamur.ai/free/en/universities/university-of-washington/) from 2012 to 2018. Frequent co-authors include [Livio Baldini Soares](https://md.research.elamur.ai/free/en/authors/livio-baldini-soares/) and [Tom Kwiatkowski](https://md.research.elamur.ai/free/en/authors/tom-kwiatkowski/). Other collaborators are Luke Zettlemoyer, Luheng He, Julian Michael, Eunsol Choi and Thibault Févry. Nicholas FitzGerald has 3 papers in our library, in 2018–2020, most of them on [Semantic role labeling](https://md.research.elamur.ai/free/en/topics/semantic-role-labeling/), [Question answering](https://md.research.elamur.ai/free/en/topics/question-answering/), [Knowledge graphs & ontologies](https://md.research.elamur.ai/free/en/topics/knowledge-graphs/); often with [Livio Baldini Soares](https://md.research.elamur.ai/free/en/authors/livio-baldini-soares/), [Tom Kwiatkowski](https://md.research.elamur.ai/free/en/authors/tom-kwiatkowski/), [Eunsol Choi](https://md.research.elamur.ai/free/en/authors/eunsol-choi/). 3 papers in our library · 2018–2020 [OpenAlex](https://openalex.org/A5073439637) · [**h-index 14**](https://openalex.org/authors/A5073439637) · [25 works](https://openalex.org/works?filter=author.id:A5073439637) · [2 631 citations](https://openalex.org/works?filter=author.id:A5073439637&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [3 works in our library](https://md.research.elamur.ai/free/en/authors/nicholas-fitzgerald/#papers) · [3 778 citations in our library](https://md.research.elamur.ai/free/en/authors/nicholas-fitzgerald/cited-by/) · [⭐ Paper Star rank #2613](https://md.research.elamur.ai/free/en/paper-stars/page/27/#star-2613) 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=Nicholas+FitzGerald) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Nicholas+FitzGerald) · [dblp](https://dblp.org/search?q=Nicholas+FitzGerald) · [ACL Anthology](https://aclanthology.org/search/?q=Nicholas+FitzGerald) ## Affiliations - [Google (United States)](https://md.research.elamur.ai/free/en/companies/google/) · Mountain View, United States —2018–2023 on 12 papers - [University of Southern California](https://md.research.elamur.ai/free/en/universities/university-of-southern-california/) · Los Angeles, United States —2021–2023 on 2 papers - [University of Washington](https://md.research.elamur.ai/free/en/universities/university-of-washington/) · Seattle, United States —2012–2018 on 8 papers - [University of British Columbia](https://md.research.elamur.ai/free/en/universities/university-of-british-columbia/) · Vancouver, Canada —2011 on 2 papers From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 more institutions on single bylines are not listed. ## Topics [Semantic role labeling 1](https://md.research.elamur.ai/free/en/topics/semantic-role-labeling/) · [Question answering 1](https://md.research.elamur.ai/free/en/topics/question-answering/) · [Knowledge graphs & ontologies 1](https://md.research.elamur.ai/free/en/topics/knowledge-graphs/) ## Works by year ### 2020s [**2020** 1 paper](https://md.research.elamur.ai/free/en/papers/fevry-2020-entities-as-experts-sparse-memory/) ### 2010s [**2019** 1 paper](https://md.research.elamur.ai/free/en/papers/soares-2019-matching-blanks-distributional-similarity-relation/) · [**2018** 1 paper](https://md.research.elamur.ai/free/en/papers/fitzgerald-2018-large-scale-qa-srl-parsing/) ## Papers The most cited first (OpenAlex and our library). 1. **[Matching the Blanks: Distributional Similarity for Relation Learning](https://md.research.elamur.ai/free/en/papers/soares-2019-matching-blanks-distributional-similarity-relation/)** *(2019 · 294 citations)* The paper addresses the task of extracting relations between entities in text. The authors aim to obtain general-purpose relation representations that do not depend on a fixed schema or a large knowledge graph. First, using BERT LARGE, they compare ways to mark the two target entities in the input and to obtain a… 2. **[Entities as Experts: Sparse Memory Access with Entity Supervision](https://md.research.elamur.ai/free/en/papers/fevry-2020-entities-as-experts-sparse-memory/)** *(2020 · 205 citations)* The paper asks how a language model can store factual knowledge about real-world entities inside its own parameters, rather than relying on external knowledge bases. 3. **[Large-Scale QA-SRL Parsing](https://md.research.elamur.ai/free/en/papers/fitzgerald-2018-large-scale-qa-srl-parsing/)** *(2018 · 141 citations)* The paper releases QA-SRL Bank 2.0, which has 265,140 valid question-answer pairs for 64,018 sentences and 133,479 verbs across Wikipedia, Wikinews and science textbooks. ## Co-authors here 7 co-authors with a page, the most papers together first. - [Livio Baldini Soares](https://md.research.elamur.ai/free/en/authors/livio-baldini-soares/) ×2 - [Tom Kwiatkowski](https://md.research.elamur.ai/free/en/authors/tom-kwiatkowski/) ×2 - [Eunsol Choi](https://md.research.elamur.ai/free/en/authors/eunsol-choi/) - [Julian Michael](https://md.research.elamur.ai/free/en/authors/julian-michael/) - [Luheng He](https://md.research.elamur.ai/free/en/authors/luheng-he/) - [Luke Zettlemoyer](https://md.research.elamur.ai/free/en/authors/luke-zettlemoyer/) - [Thibault Févry](https://md.research.elamur.ai/free/en/authors/thibault-fevry/) ## Cited by Papers of our library cite their works 3 778 times (of the 140 884 papers whose bibliographies we read); [203 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/nicholas-fitzgerald/cited-by/).