--- title: "Richárd Farkas — author profile and papers" description: "Richárd Farkas, University of Primorska: 5 papers on Elamur Research (2008–2018), h-index 21 — affiliations, topics, co-authors and who cites them in our…" canonical: "https://research.elamur.ai/free/en/authors/richard-farkas/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/richard-farkas/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Richárd Farkas # Richárd Farkas Richárd Farkas works in natural language processing. Their papers here address three connected problems: recognising when a statement is hedged, negated or speculative rather than factual; parsing languages whose grammar is largely expressed inside words; and resolving coreference, that is, working out which expressions refer to the same entity. A recurring approach is building annotated corpora and organising shared tasks so that different systems can be compared on common data. The work pays particular attention to biomedical text and to Hungarian and other morphologically complex languages. The most cited of the papers here is [The CoNLL-2010 Shared Task](https://md.research.elamur.ai/free/en/papers/farkas-2010-conll-2010-shared-task-learning/) (2010). It turned uncertainty detection into a competition, asking systems to label sentences from biology articles and Wikipedia as certain or uncertain, and to locate hedge cues and their scope. It built on [the BioScope corpus](https://md.research.elamur.ai/free/en/papers/szarvas-2008-bioscope-corpus-annotation-negation-uncertainty/) (2008), a collection of biomedical texts annotated for negation and speculation cues along with the stretch of each sentence that every cue governs. The [SPMRL 2013 overview](https://md.research.elamur.ai/free/en/papers/seddah-2013-overview-spmrl-2013-shared-task/) (2013) reported a cross-framework evaluation of parsing morphologically rich languages. It compared settings with gold, predicted and raw morphology and used a fixed small training set for every language. Later papers turn toward coreference. A system for the CoNLL 2012 task handled Arabic, Chinese and English by stacking resolvers, offsetting the weakness of judging mention pairs one at a time. [SzegedKoref](https://md.research.elamur.ai/free/en/papers/vincze-2018-szegedkoref-hungarian-coreference-corpus/) (2018) added coreference annotation to documents of the Szeged Treebank, giving Hungarian a larger resource for training resolvers, with links classified by type, such as pronominal or nominal. Farkas has been at the [University of Szeged](https://md.research.elamur.ai/free/en/universities/university-of-szeged/) since 2007, with earlier bylines at the MTA-SZTE Research Group on Artificial Intelligence, the [Hungarian Academy of Sciences](https://md.research.elamur.ai/free/en/government/hungarian-academy-of-sciences/) and, between 2011 and 2014, the [University of Stuttgart](https://md.research.elamur.ai/free/en/universities/university-of-stuttgart/). Papers from 2026 also list the University of Primorska and InnoRenew CoE in Slovenia. Co-authors here include [Veronika Vincze](https://md.research.elamur.ai/free/en/authors/veronika-vincze/), [György Szarvas](https://md.research.elamur.ai/free/en/authors/gyorgy-szarvas/) and János Csirik. The topics span [coreference resolution](https://md.research.elamur.ai/free/en/topics/coreference-resolution/), morphology, syntax, and evaluation and benchmarks. Richárd Farkas has 5 papers in our library, in 2008–2018, 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/), [Morphology](https://md.research.elamur.ai/free/en/topics/morphology/); often with [Veronika Vincze](https://md.research.elamur.ai/free/en/authors/veronika-vincze/), [György Szarvas](https://md.research.elamur.ai/free/en/authors/gyorgy-szarvas/), [János Csirik](https://md.research.elamur.ai/free/en/authors/janos-csirik/). 5 papers in our library · 2008–2018 current affiliation [University of Primorska](https://ror.org/05xefg082), Koper, Slovenia; [University of Szeged](https://md.research.elamur.ai/free/en/universities/university-of-szeged/), Szeged, Hungary; [InnoRenew CoE](https://ror.org/0538nf417), Izola, Slovenia [OpenAlex](https://openalex.org/A5076395593) · [ORCID](https://orcid.org/0000-0001-7019-2632) · [**h-index 21**](https://openalex.org/authors/A5076395593) · [93 works](https://openalex.org/works?filter=author.id:A5076395593) · [2 533 citations](https://openalex.org/works?filter=author.id:A5076395593&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [5 works in our library](https://md.research.elamur.ai/free/en/authors/richard-farkas/#papers) · [370 citations in our library](https://md.research.elamur.ai/free/en/authors/richard-farkas/cited-by/) · 3 more works in our library · [⭐ Paper Star rank #2096](https://md.research.elamur.ai/free/en/paper-stars/page/21/#star-2096) 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=Rich%C3%A1rd+Farkas) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Rich%C3%A1rd+Farkas) · [dblp](https://dblp.org/search?q=Rich%C3%A1rd+Farkas) · [ACL Anthology](https://aclanthology.org/search/?q=Rich%C3%A1rd+Farkas) ## Affiliations - [University of Szeged](https://md.research.elamur.ai/free/en/universities/university-of-szeged/) · Szeged, Hungary —current · 2007–2026 on 50 papers - [InnoRenew CoE](https://ror.org/0538nf417) · Izola, Slovenia —current · 2026 on 1 paper - [University of Primorska](https://ror.org/05xefg082) · Koper, Slovenia —current · 2026 on 1 paper - [MTA-SZTE Research Group on Artificial Intelligence](https://ror.org/0507fk326) · Szeged, Hungary —2006–2023 on 15 papers - [University of Stuttgart](https://md.research.elamur.ai/free/en/universities/university-of-stuttgart/) · Stuttgart, Germany —2011–2014 on 14 papers - [Hungarian Academy of Sciences](https://md.research.elamur.ai/free/en/government/hungarian-academy-of-sciences/) · Budapest, Hungary —2006–2011 on 19 papers - [Friedrich-Alexander-Universität Erlangen-Nürnberg](https://md.research.elamur.ai/free/en/universities/friedrich-alexander-universitat-erlangen-nurnberg/) · Erlangen, Germany —2004 on 2 papers From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. ## Topics [Coreference resolution 2](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/) · [Morphology 1](https://md.research.elamur.ai/free/en/topics/morphology/) · [Evaluation & benchmarks 1](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · [Semitic languages 1](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · [Syntax & grammar formalisms 1](https://md.research.elamur.ai/free/en/topics/syntax-grammar/) ## Works by year ### 2010s [**2018** 1 paper](https://md.research.elamur.ai/free/en/papers/vincze-2018-szegedkoref-hungarian-coreference-corpus/) · [**2013** 1 paper](https://md.research.elamur.ai/free/en/papers/seddah-2013-overview-spmrl-2013-shared-task/) · [**2012** 1 paper](https://md.research.elamur.ai/free/en/papers/bjorkelund-2012-data-driven-multilingual-coreference-resolution/) · [**2010** 1 paper](https://md.research.elamur.ai/free/en/papers/farkas-2010-conll-2010-shared-task-learning/) ### 2000s [**2008** 1 paper](https://md.research.elamur.ai/free/en/papers/szarvas-2008-bioscope-corpus-annotation-negation-uncertainty/) ## Papers The most cited first (OpenAlex and our library). 1. **[The CoNLL-2010 Shared Task: Learning to Detect Hedges and their Scope in Natural Language Text](https://md.research.elamur.ai/free/en/papers/farkas-2010-conll-2010-shared-task-learning/)** *(2010 · 370 citations)* The CoNLL-2010 Shared Task introduced uncertainty detection as a competition problem. The goal is to separate factual statements from hedged or speculative ones, which matters for information extraction, for example when mining protein-protein interactions. The organizers defined two tasks. Task1 asks for a binary… 2. **[Overview of the SPMRL 2013 Shared Task: A Cross-Framework Evaluation of Parsing Morphologically Rich Languages](https://md.research.elamur.ai/free/en/papers/seddah-2013-overview-spmrl-2013-shared-task/)** *(2013 · 244 citations)* The paper presents the inaugural shared task devoted to statistically parsing morphologically rich languages (MRLs), organized alongside the 4th SPMRL workshop at EMNLP 2013. 3. **[The BioScope corpus: annotation for negation, uncertainty and their scope in biomedical texts](https://md.research.elamur.ai/free/en/papers/szarvas-2008-bioscope-corpus-annotation-negation-uncertainty/)** *(2008 · 240 citations)* The authors tackle a gap in biomedical text mining: systems must tell factual statements apart from negated or speculative ones, but no sizeable public corpus existed for training and evaluating negation and hedge detection or for resolving the scope of those cues. 4. **[Data-driven Multilingual Coreference Resolution using Resolver Stacking](https://md.research.elamur.ai/free/en/papers/bjorkelund-2012-data-driven-multilingual-coreference-resolution/)** *(2012 · 61 citations)* This CoNLL 2012 Shared Task system performs coreference resolution for Arabic, Chinese and English. Its goal is to reduce a known weakness of pair-wise resolvers, which judge each mention pair in isolation. The pipeline begins with a deliberately over-generating mention extractor built on parse trees and, for… 5. **[SzegedKoref: A Hungarian Coreference Corpus](https://md.research.elamur.ai/free/en/papers/vincze-2018-szegedkoref-hungarian-coreference-corpus/)** *(2018 · 14 citations)* Hungarian had only a small manually annotated coreference dataset (Miháltz, 2012), which was not enough to build machine-learning coreference resolvers. ## 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 14 co-authors with a page, the most papers together first. - [Veronika Vincze](https://md.research.elamur.ai/free/en/authors/veronika-vincze/) ×3 - [György Szarvas](https://md.research.elamur.ai/free/en/authors/gyorgy-szarvas/) ×2 - [János Csirik](https://md.research.elamur.ai/free/en/authors/janos-csirik/) ×2 - [Anders Björkelund](https://md.research.elamur.ai/free/en/authors/anders-bjorkelund/) - [Djamé Seddah](https://md.research.elamur.ai/free/en/authors/djame-seddah/) - [György Móra](https://md.research.elamur.ai/free/en/authors/gyorgy-mora/) - [Jennifer Foster](https://md.research.elamur.ai/free/en/authors/jennifer-foster/) - [Jinho D. Choi](https://md.research.elamur.ai/free/en/authors/jinho-d-choi/) - [Marie Candito](https://md.research.elamur.ai/free/en/authors/marie-candito/) - [Nizar Habash](https://md.research.elamur.ai/free/en/authors/nizar-habash/) - [Reut Tsarfaty](https://md.research.elamur.ai/free/en/authors/reut-tsarfaty/) - [Sandra Kübler](https://md.research.elamur.ai/free/en/authors/sandra-kubler/) ## Cited by Papers of our library cite their works 370 times (of the 140 884 papers whose bibliographies we read); [47 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/richard-farkas/cited-by/).