--- title: "Marco Pennacchiotti — author profile and papers" description: "Marco Pennacchiotti: 5 papers on Elamur Research (2006–2010), h-index 28 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/marco-pennacchiotti/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/marco-pennacchiotti/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Marco Pennacchiotti # Marco Pennacchiotti Marco Pennacchiotti works in computational semantics, and the papers here, dated 2006 to 2010, follow two connected lines. One is the automatic discovery of semantic relations between words in large text collections, with as little hand-labelled supervision as possible. The other is frame semantics as encoded in FrameNet: how to widen the resource's lexical coverage and how far frame and role information helps in textual entailment and question answering. The methods mix lexical surface patterns, corpus co-occurrence statistics, distributional vector spaces and WordNet hierarchies, and several papers sit under [semantic role labeling](https://md.research.elamur.ai/free/en/topics/semantic-role-labeling/). The most cited paper here is [Espresso](https://md.research.elamur.ai/free/en/papers/pantel-2006-espresso-leveraging-generic-patterns-automatically/) (2006). Starting from a handful of seed pairs, it bootstraps surface patterns and ranks them by a PMI-based reliability score instead of raw frequency. It keeps broad but noisy patterns by checking their output against precise ones in a very large corpus. [SemEval-2010 Task 8](https://md.research.elamur.ai/free/en/papers/hendrickx-2010-semeval-2010-task-8-multi/) set up a shared evaluation in which systems label the relation between two marked nouns, choosing among nine relation types plus a residual class and also deciding argument direction. Its 10,717 examples were gathered from the Web and annotated independently by two people. [FATE](https://md.research.elamur.ai/free/en/papers/burchardt-2008-fate-framenet-annotated-corpus-textual/) (2008) is a manually built corpus that adds frames and semantic roles to the 800 pairs of the RTE-2 test set. The newer papers concentrate on FrameNet's limited vocabulary. [Automatic induction of FrameNet lexical units](https://md.research.elamur.ai/free/en/papers/pennacchiotti-2008-automatic-induction-framenet-lexical-units/) (2008) assigns words missing from the resource to suitable frames out of roughly 800 candidates. [Combining Word Sense and Usage](https://md.research.elamur.ai/free/en/papers/cao-2008-combining-word-sense-usage-modeling/) (2008) represents frames both through WordNet sub-hierarchies and as corpus-derived vectors, so that similarity between frames and lexical units can be measured. The 2010 shared task then returns to relation classification. Bylines place the earlier work at the [University of Rome Tor Vergata](https://md.research.elamur.ai/free/en/universities/university-of-rome-tor-vergata/) (2004–2007) and [Saarland University](https://md.research.elamur.ai/free/en/universities/saarland-university/) (2007–2009), with later papers listing [Yahoo](https://md.research.elamur.ai/free/en/companies/yahoo/) (2009–2021) and eBay (2012–2017). Frequent co-authors include [Roberto Basili](https://md.research.elamur.ai/free/en/authors/roberto-basili/), [Danilo Croce](https://md.research.elamur.ai/free/en/authors/danilo-croce/) and [Diego De Cao](https://md.research.elamur.ai/free/en/authors/diego-de-cao/). Other collaborators are [Patrick Pantel](https://md.research.elamur.ai/free/en/authors/patrick-pantel/) and [Aljoscha Burchardt](https://md.research.elamur.ai/free/en/authors/aljoscha-burchardt/). Marco Pennacchiotti has 5 papers in our library, in 2006–2010, most of them on [Semantic role labeling](https://md.research.elamur.ai/free/en/topics/semantic-role-labeling/), [Word sense disambiguation](https://md.research.elamur.ai/free/en/topics/word-sense-disambiguation/), [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/); often with [Danilo Croce](https://md.research.elamur.ai/free/en/authors/danilo-croce/), [Diego De Cao](https://md.research.elamur.ai/free/en/authors/diego-de-cao/), [Roberto Basili](https://md.research.elamur.ai/free/en/authors/roberto-basili/). 5 papers in our library · 2006–2010 [OpenAlex](https://openalex.org/A5024339113) · [**h-index 28**](https://openalex.org/authors/A5024339113) · [89 works](https://openalex.org/works?filter=author.id:A5024339113) · [4,654 citations](https://openalex.org/works?filter=author.id:A5024339113&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 5 works in our library](https://md.research.elamur.ai/free/en/authors/marco-pennacchiotti/#papers) · [🔗 495 citations in our library](https://md.research.elamur.ai/free/en/authors/marco-pennacchiotti/cited-by/) · [1 more in our library without a page yet](#also) · [⭐ Paper Star rank #1807](https://md.research.elamur.ai/free/en/paper-stars/page/19/#star-1807) 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=Marco+Pennacchiotti) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Marco+Pennacchiotti) · [dblp](https://dblp.org/search?q=Marco+Pennacchiotti) · [ACL Anthology](https://aclanthology.org/search/?q=Marco+Pennacchiotti) ## Affiliations [🏢**Yahoo** Sunnyvale · United States 2009–2021 · 17 papers](https://md.research.elamur.ai/free/en/companies/yahoo/) · [🎓**Saarland University** Saarbrücken · Germany 2007–2009 · 15 papers](https://md.research.elamur.ai/free/en/universities/saarland-university/) · [🎓**University of Rome Tor Vergata** Rome · Italy 2004–2007 · 15 papers](https://md.research.elamur.ai/free/en/universities/university-of-rome-tor-vergata/) · [🏢**eBay** San Jose · United States 2012–2017 · 9 papers](https://ror.org/05cnabr44) 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 [Semantic role labeling (3)](https://md.research.elamur.ai/free/en/topics/semantic-role-labeling/) · [Word sense disambiguation (1)](https://md.research.elamur.ai/free/en/topics/word-sense-disambiguation/) · [Reasoning (1)](https://md.research.elamur.ai/free/en/topics/reasoning/) ## Works by year ### 2010s [**2010** 1 paper](https://md.research.elamur.ai/free/en/papers/hendrickx-2010-semeval-2010-task-8-multi/) ### 2000s [**2008** 3 papers](https://md.research.elamur.ai/free/en/authors/marco-pennacchiotti/year/2008/) · [**2006** 1 paper](https://md.research.elamur.ai/free/en/papers/pantel-2006-espresso-leveraging-generic-patterns-automatically/) ## Papers The most cited first (OpenAlex and our library). 1. **[Espresso: Leveraging Generic Patterns for Automatically Harvesting Semantic Relations](https://md.research.elamur.ai/free/en/papers/pantel-2006-espresso-leveraging-generic-patterns-automatically/)** *(2006 · 680 citations)* Espresso extracts binary semantic relations from raw text with very little supervision: it needs only a handful of seed pairs. 2. **[SemEval-2010 Task 8: Multi-Way Classification of Semantic Relations between Pairs of Nominals](https://md.research.elamur.ai/free/en/papers/hendrickx-2010-semeval-2010-task-8-multi/)** *(2010 · 283 citations)* This paper presents a shared evaluation for identifying which semantic relation links two marked nouns in a sentence. 3. **[Automatic induction of FrameNet lexical units](https://md.research.elamur.ai/free/en/papers/pennacchiotti-2008-automatic-induction-framenet-lexical-units/)** *(2008 · 88 citations)* FrameNet has limited coverage, with only about 10,000 lexical units (LUs). This has repeatedly undermined its use in QA and RTE systems. The authors address LU induction: automatically assigning words absent from FrameNet to the correct frame(s) among roughly 800 candidates. 4. **[Combining Word Sense and Usage for Modeling Frame Semantics](https://md.research.elamur.ai/free/en/papers/cao-2008-combining-word-sense-usage-modeling/)** *(2008 · 50 citations)* FrameNet's limited lexical coverage and weak multilingual support constrain its use in tasks such as question answering and textual entailment. 5. **[FATE: a FrameNet-Annotated Corpus for Textual Entailment](https://md.research.elamur.ai/free/en/papers/burchardt-2008-fate-framenet-annotated-corpus-textual/)** *(2008 · 35 citations)* Earlier studies suggested that predicate-argument structure captures many phenomena in textual entailment data, such as paraphrases and argument alternations. ## Also in our library 1 more work of theirs is in our library without a page here yet; it will appear as we publish them. ## Co-authors here 12 co-authors with a page, the most papers together first. - [Danilo Croce](https://md.research.elamur.ai/free/en/authors/danilo-croce/) ×2 - [Diego De Cao](https://md.research.elamur.ai/free/en/authors/diego-de-cao/) ×2 - [Roberto Basili](https://md.research.elamur.ai/free/en/authors/roberto-basili/) ×2 - [Aljoscha Burchardt](https://md.research.elamur.ai/free/en/authors/aljoscha-burchardt/) - [Iris Hendrickx](https://md.research.elamur.ai/free/en/authors/iris-hendrickx/) - [Lorenza Romano](https://md.research.elamur.ai/free/en/authors/lorenza-romano/) - [Michael Roth](https://md.research.elamur.ai/free/en/authors/michael-roth/) - [Patrick Pantel](https://md.research.elamur.ai/free/en/authors/patrick-pantel/) - [Preslav Nakov](https://md.research.elamur.ai/free/en/authors/preslav-nakov/) - [Sebastian Padó](https://md.research.elamur.ai/free/en/authors/sebastian-pado/) - [Su Nam Kim](https://md.research.elamur.ai/free/en/authors/su-nam-kim/) - [Zornitsa Kozareva](https://md.research.elamur.ai/free/en/authors/zornitsa-kozareva/) ## Cited by Papers of our library cite their works 495 times (of the 140,884 papers whose bibliographies we read); [42 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/marco-pennacchiotti/cited-by/).