---
title: "Marta Recasens — author profile and papers"
description: "Marta Recasens, Ajuntament de Barcelona: 9 papers on Elamur Research (2009–2018), h-index 19 — affiliations, topics, co-authors and who cites them in our…"
canonical: "https://research.elamur.ai/free/en/authors/marta-recasens/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/marta-recasens/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Marta Recasens

# Marta Recasens

Marta Recasens works mainly on [coreference resolution](https://md.research.elamur.ai/free/en/topics/coreference-resolution/), the task of deciding which expressions in a text point to the same entity or event. Their papers here return to a few linked questions: what should count as coreference in the first place, how annotation schemes differ across corpora, and how far a reported score reflects the system rather than the dataset or the metric. The usual method is to build and annotate corpora, then use them to test systems. Recasens has also studied near-identity relations, cases that fall between "same" and "different" referent, and has worked across Catalan, English and Spanish.

Among the most cited works, [Linguistic Models for Analyzing and Detecting Biased Language](https://md.research.elamur.ai/free/en/papers/recasens-2013-linguistic-models-analyzing-detecting-biased/) (2013) moves outside coreference. It mines small Wikipedia edits made in neutral-point-of-view disputes and separates framing bias from epistemological bias. [Joint Entity and Event Coreference Resolution across Documents](https://md.research.elamur.ai/free/en/papers/lee-2012-joint-entity-event-coreference-resolution/) (2012) links mentions of events as well as entities across multiple news articles. Earlier, the SemEval-2010 shared task (2009) set up a coreference benchmark in three languages. It asked how well systems transfer between languages and whether the choice of metric changes how systems are ranked.

The later papers turn to evaluation and to harder pronoun cases. [Scoring Coreference Partitions of Predicted Mentions](https://md.research.elamur.ai/free/en/papers/pradhan-2014-scoring-coreference-partitions-predicted-mentions/) (2014) gives a single reference implementation of the standard metrics for system-detected mentions. [Sense Anaphoric Pronouns: Am I One?](https://md.research.elamur.ai/free/en/papers/recasens-2016-sense-anaphoric-pronouns-am-i/) (2016) annotates forms such as "one", "those" and "another" in part of OntoNotes. It also trains a classifier to tell anaphoric uses apart from other uses. [Mind the GAP](https://md.research.elamur.ai/free/en/papers/webster-2018-mind-gap-balanced-corpus-gendered/) (2018) is a Wikipedia corpus of ambiguous pronouns, balanced for gender, on which existing resolvers perform poorly.

The current affiliation is the Ajuntament de Barcelona. Most earlier papers come from the [Universitat de Barcelona](https://md.research.elamur.ai/free/en/universities/universitat-de-barcelona/), where work spans 2008 to 2021, and from [Google](https://md.research.elamur.ai/free/en/companies/google/) between 2013 and 2018, with a stretch at [Stanford University](https://md.research.elamur.ai/free/en/universities/stanford-university/). Frequent co-authors include [Eduard Hovy](https://md.research.elamur.ai/free/en/authors/eduard-hovy/), [Dan Jurafsky](https://md.research.elamur.ai/free/en/authors/dan-jurafsky/) and [Maria Antònia Martí](https://md.research.elamur.ai/free/en/authors/maria-antonia-marti/).

9 papers on this site · 2009–2018

current affiliation [Ajuntament de Barcelona](https://ror.org/00zg6q231), Barcelona, Spain

Marta Recasens has 9 papers on this site, in 2009–2018, most of them on [Coreference resolution](https://md.research.elamur.ai/free/en/topics/coreference-resolution/), [Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/); often with [Eduard Hovy](https://md.research.elamur.ai/free/en/authors/eduard-hovy/), [Dan Jurafsky](https://md.research.elamur.ai/free/en/authors/dan-jurafsky/), [Maria Antònia Martí](https://md.research.elamur.ai/free/en/authors/maria-antonia-marti/). 3 of them are among the papers [Mova](https://md.research.elamur.ai/free/en/projects/mova/) reads.

[OpenAlex](https://openalex.org/A5103978745) · [**h-index 19**](https://openalex.org/authors/A5103978745) · [72 works](https://openalex.org/works?filter=author.id:A5103978745) · [2 086 citations](https://openalex.org/works?filter=author.id:A5103978745&sort=cited_by_count:desc) OpenAlex, 2026-10-14

[9 works on this site](https://md.research.elamur.ai/free/en/authors/marta-recasens/#papers) · [676 citations in our library](https://md.research.elamur.ai/free/en/authors/marta-recasens/cited-by/) · 3 more works in our library · [⭐ Paper Star rank #1469](https://md.research.elamur.ai/free/en/paper-stars/page/15/#star-1469)

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=Marta+Recasens) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Marta+Recasens) · [dblp](https://dblp.org/search?q=Marta+Recasens) · [ACL Anthology](https://aclanthology.org/search/?q=Marta+Recasens)

## Affiliations

- [Ajuntament de Barcelona](https://ror.org/00zg6q231) · Barcelona, Spain —current · 2024 on 1 paper
- [Universitat de Barcelona](https://md.research.elamur.ai/free/en/universities/universitat-de-barcelona/) · Barcelona, Spain —2008–2021 on 16 papers
- [Google (United States)](https://md.research.elamur.ai/free/en/companies/google/) · Mountain View, United States —2013–2018 on 12 papers
- [Stanford University](https://md.research.elamur.ai/free/en/universities/stanford-university/) · Stanford, United States —2012–2016 on 3 papers

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

[Coreference resolution 7](https://md.research.elamur.ai/free/en/topics/coreference-resolution/) · [Multilingual & cross-lingual NLP 1](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/)

## Works by year

### 2010s

[**2018** 1 paper](https://md.research.elamur.ai/free/en/papers/webster-2018-mind-gap-balanced-corpus-gendered/) · [**2016** 1 paper](https://md.research.elamur.ai/free/en/papers/recasens-2016-sense-anaphoric-pronouns-am-i/) · [**2014** 1 paper](https://md.research.elamur.ai/free/en/papers/pradhan-2014-scoring-coreference-partitions-predicted-mentions/) · [**2013** 1 paper](https://md.research.elamur.ai/free/en/papers/recasens-2013-linguistic-models-analyzing-detecting-biased/) · [**2012** 2 papers](https://md.research.elamur.ai/free/en/authors/marta-recasens/year/2012/) · [**2010** 2 papers](https://md.research.elamur.ai/free/en/authors/marta-recasens/year/2010/)

### 2000s

[**2009** 1 paper](https://md.research.elamur.ai/free/en/papers/recasens-2009-semeval-2010-task-1-coreference/)

## Papers

The most cited first (OpenAlex and our library).

1. **[Linguistic Models for Analyzing and Detecting Biased Language](https://md.research.elamur.ai/free/en/papers/recasens-2013-linguistic-models-analyzing-detecting-biased/)** *(2013 · 394 citations)* The paper asks how bias appears in text that is meant to be neutral, such as encyclopedia articles, and whether a system can find the exact word responsible for it.
2. **[Mind the GAP: A Balanced Corpus of Gendered Ambiguous Pronouns](https://md.research.elamur.ai/free/en/papers/webster-2018-mind-gap-balanced-corpus-gendered/)** *(2018 · 358 citations)* GAP is 8,908 pronoun–name pairs (4,454 contexts) from Wikipedia, each with a gendered pronoun and two names of the same gender, either of which (or neither) could be the referent, with no other compatible mention in between.
3. **[Scoring Coreference Partitions of Predicted Mentions: A Reference Implementation](https://md.research.elamur.ai/free/en/papers/pradhan-2014-scoring-coreference-partitions-predicted-mentions/)** *(2014 · 284 citations)* Coreference metrics such as MUC, B-cubed and CEAF were originally defined for gold mentions, and different research groups adapted them to predicted mentions in incompatible ways, often by adding or removing mentions artificially so that the key and response partitions line up.
4. **[Joint Entity and Event Coreference Resolution across Documents](https://md.research.elamur.ai/free/en/papers/lee-2012-joint-entity-event-coreference-resolution/)** *(2012 · 273 citations)* Most coreference systems link only noun phrases that refer to entities. They miss links between events, such as a verb and a noun naming the same happening. Lee et al. address entities and events together, across multiple news documents.
5. **[SemEval-2010 Task 1: Coreference Resolution in Multiple Languages](https://md.research.elamur.ai/free/en/papers/recasens-2009-semeval-2010-task-1-coreference/)** *(2009 · 92 citations)* This paper proposes a SemEval-2010 shared task that benchmarks automatic coreference resolution in Catalan, English and Spanish.
6. **[A Typology of Near-Identity Relations for Coreference (NIDENT)](https://md.research.elamur.ai/free/en/papers/recasens-2010-typology-near-identity-relations-coreference/)** *(2010 · 67 citations)* Coreference corpora such as ACE and OntoNotes sometimes annotate the same kind of example differently. The authors attribute this to a strict binary choice between identity and non-identity, which fails when two mentions denote almost the same discourse entity. Examples include a town before and after demographic…
7. **[Coreference Resolution across Corpora: Languages, Coding Schemes, and Preprocessing Information](https://md.research.elamur.ai/free/en/papers/recasens-2010-coreference-resolution-across-corpora-languages/)** *(2010 · 40 citations)* The paper shows that a coreference score says as much about the corpus as about the system. The same entity-based system, CISTELL, is trained and tested under three corpus choices: language (English against Spanish, using OntoNotes and AnCora, both news), coding scheme (ACE against OntoNotes on the same 100,000-word…
8. **[Annotating Near-Identity from Coreference Disagreements](https://md.research.elamur.ai/free/en/papers/recasens-2012-annotating-near-identity-coreference-disagreements/)** *(2012 · 36 citations)* Standard coreference corpora treat coreference as a yes/no relation. Borderline cases, where two mentions refer to "almost" the same entity, therefore cause annotator disagreement and add noise for resolution systems. The authors extend two existing coreference resources, the English NP4E and the Catalan AnCora-CA…
9. **[Sense Anaphoric Pronouns: Am I One?](https://md.research.elamur.ai/free/en/papers/recasens-2016-sense-anaphoric-pronouns-am-i/)** *(2016 · 14 citations)* The paper addresses sense anaphora, in which a pronoun takes its meaning from an earlier expression but refers to a different entity, as in "existing ones" pointing back to "loans".

## Also in our library

3 more works of theirs are in our library without a page here yet; they will appear as we publish them.

## Co-authors here

12 of 17 co-authors with a page, the most papers together first.

- [Eduard Hovy](https://md.research.elamur.ai/free/en/authors/eduard-hovy/) ×3
- [Dan Jurafsky](https://md.research.elamur.ai/free/en/authors/dan-jurafsky/) ×2
- [Maria Antònia Martí](https://md.research.elamur.ai/free/en/authors/maria-antonia-marti/) ×2
- [Angel Chang](https://md.research.elamur.ai/free/en/authors/angel-chang/)
- [Constantin Orasan](https://md.research.elamur.ai/free/en/authors/constantin-orasan/)
- [Cristian Danescu-Niculescu-Mizil](https://md.research.elamur.ai/free/en/authors/cristian-danescu-niculescu-mizil/)
- [Emili Sapena](https://md.research.elamur.ai/free/en/authors/emili-sapena/)
- [Heeyoung Lee](https://md.research.elamur.ai/free/en/authors/heeyoung-lee/)
- [Jason Baldridge](https://md.research.elamur.ai/free/en/authors/jason-baldridge/)
- [Kellie Webster](https://md.research.elamur.ai/free/en/authors/kellie-webster/)
- [Lluís Màrquez](https://md.research.elamur.ai/free/en/authors/lluis-marquez/)
- [Michael Strube](https://md.research.elamur.ai/free/en/authors/michael-strube/)

## Cited by

Papers of our library cite their works 676 times (of the 140 884 papers whose bibliographies we read); [174 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/marta-recasens/cited-by/).