--- title: "Aron Culotta — author profile and papers" description: "Aron Culotta, Tulane University: 2 papers on Elamur Research (2004–2007), h-index 36 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/aron-culotta/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/aron-culotta/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Aron Culotta # Aron Culotta Aron Culotta's papers here deal with [information extraction](https://md.research.elamur.ai/free/en/topics/information-extraction/): pulling structured facts about entities out of ordinary sentences. Two problems recur. One is relation extraction, deciding whether and how two mentioned entities are related. The other is [coreference resolution](https://md.research.elamur.ai/free/en/topics/coreference-resolution/), grouping mentions that refer to the same entity. The methods are statistical learning over linguistic structure: kernel functions inside support vector machines, and probabilistic models that score whole groups of mentions. The relation work draws on the ACE newswire corpus. The most cited of these papers is [Dependency Tree Kernels for Relation Extraction](https://md.research.elamur.ai/free/en/papers/culotta-2004-dependency-tree-kernels-relation-extraction/) (2004). It reduces each candidate entity pair to the smallest dependency subtree connecting the two mentions. Every node is annotated with features such as the word, part of speech, entity type and WordNet hypernyms. A tree kernel that extends earlier work by Zelenko and colleagues then compares these subtrees within an SVM. Structured kernels outperformed a plain bag-of-words kernel, and adding the two kernels together gave the strongest results. The second paper, [First-Order Probabilistic Models for Coreference Resolution](https://md.research.elamur.ai/free/en/papers/culotta-2007-first-order-probabilistic-models-coreference/) (2007), moves away from judging mentions one pair at a time. A maximum-entropy model instead evaluates entire candidate clusters. This lets features describe a cluster as a whole, for example ruling out clusters made only of pronouns. Because the number of possible clusters explodes, the paper also introduces practical approximations. Across 2004 to 2007, the papers move from local relations inside a single sentence toward reasoning at the level of whole entities. The coreference work was written with [Michael Wick](https://md.research.elamur.ai/free/en/authors/michael-wick/) and [Andrew McCallum](https://md.research.elamur.ai/free/en/authors/andrew-mccallum/), and [Jeffrey Sorensen](https://md.research.elamur.ai/free/en/authors/jeffrey-sorensen/) also appears among the co-authors. Culotta is currently at Tulane University in New Orleans. Earlier bylines list the Illinois Institute of Technology in Chicago and, from 2004 to 2009, the University of Massachusetts Amherst, the period when these papers appeared. 2 papers on this site · 2004–2007 current affiliation [Tulane University](https://ror.org/04vmvtb21), New Orleans, United States Aron Culotta has 2 papers on this site, in 2004–2007, most of them on [Coreference resolution](https://md.research.elamur.ai/free/en/topics/coreference-resolution/), [Information extraction](https://md.research.elamur.ai/free/en/topics/information-extraction/); often with [Andrew McCallum](https://md.research.elamur.ai/free/en/authors/andrew-mccallum/), [Jeffrey Sorensen](https://md.research.elamur.ai/free/en/authors/jeffrey-sorensen/), [Michael Wick](https://md.research.elamur.ai/free/en/authors/michael-wick/). [OpenAlex](https://openalex.org/A5011178134) · [ORCID](https://orcid.org/0000-0003-2660-7575) · [**h-index 36**](https://openalex.org/authors/A5011178134) · [129 works](https://openalex.org/works?filter=author.id:A5011178134) · [5 546 citations](https://openalex.org/works?filter=author.id:A5011178134&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [2 works on this site](https://md.research.elamur.ai/free/en/authors/aron-culotta/#papers) · [244 citations in our library](https://md.research.elamur.ai/free/en/authors/aron-culotta/cited-by/) 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=Aron+Culotta) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Aron+Culotta) · [dblp](https://dblp.org/search?q=Aron+Culotta) · [ACL Anthology](https://aclanthology.org/search/?q=Aron+Culotta) ## Affiliations - [Tulane University](https://ror.org/04vmvtb21) · New Orleans, United States —current · 2020–2026 on 25 papers - [Northeastern Illinois University](https://ror.org/04edns687) · Chicago, United States —2014–2021 on 2 papers - [Illinois Institute of Technology](https://md.research.elamur.ai/free/en/universities/illinois-institute-of-technology/) · Chicago, United States —2013–2020 on 35 papers - [Southeastern Louisiana University](https://ror.org/0531xck41) · Hammond, United States —2010–2012 on 5 papers - [University of Massachusetts Amherst](https://md.research.elamur.ai/free/en/universities/university-of-massachusetts-amherst/) · Amherst Center, United States —2004–2009 on 18 papers From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 6 more institutions on single bylines are not listed. ## Topics [Coreference resolution 1](https://md.research.elamur.ai/free/en/topics/coreference-resolution/) · [Information extraction 1](https://md.research.elamur.ai/free/en/topics/information-extraction/) ## Works by year ### 2000s [**2007** 1 paper](https://md.research.elamur.ai/free/en/papers/culotta-2007-first-order-probabilistic-models-coreference/) · [**2004** 1 paper](https://md.research.elamur.ai/free/en/papers/culotta-2004-dependency-tree-kernels-relation-extraction/) ## Papers The most cited first (OpenAlex and our library). 1. **[Dependency Tree Kernels for Relation Extraction](https://md.research.elamur.ai/free/en/papers/culotta-2004-dependency-tree-kernels-relation-extraction/)** *(2004 · 998 citations)* The paper addresses relation extraction: deciding whether two already-tagged entity mentions in one sentence are linked by a relation, and which relation it is. 2. **[First-Order Probabilistic Models for Coreference Resolution](https://md.research.elamur.ai/free/en/papers/culotta-2007-first-order-probabilistic-models-coreference/)** *(2007 · 212 citations)* Most machine-learned coreference systems judge noun phrase mentions two at a time. This means they cannot use evidence about a whole entity cluster, such as a ban on clusters made only of pronouns. Culotta, Wick and McCallum let a maximum-entropy model score entire sets of mentions. This gives a first-order… ## Co-authors here 3 co-authors with a page, the most papers together first. - [Andrew McCallum](https://md.research.elamur.ai/free/en/authors/andrew-mccallum/) - [Jeffrey Sorensen](https://md.research.elamur.ai/free/en/authors/jeffrey-sorensen/) - [Michael Wick](https://md.research.elamur.ai/free/en/authors/michael-wick/) ## Cited by Papers of our library cite their works 244 times (of the 140 884 papers whose bibliographies we read); [49 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/aron-culotta/cited-by/).