Search Results

Documents authored by Grefenstette, Gregory


Document
From Evaluating to Forecasting Performance: How to Turn Information Retrieval, Natural Language Processing and Recommender Systems into Predictive Sciences (Dagstuhl Perspectives Workshop 17442)

Authors: Nicola Ferro, Norbert Fuhr, Gregory Grefenstette, Joseph A. Konstan, Pablo Castells, Elizabeth M. Daly, Thierry Declerck, Michael D. Ekstrand, Werner Geyer, Julio Gonzalo, Tsvi Kuflik, Krister Lindén, Bernardo Magnini, Jian-Yun Nie, Raffaele Perego, Bracha Shapira, Ian Soboroff, Nava Tintarev, Karin Verspoor, Martijn C. Willemsen, and Justin Zobel

Published in: Dagstuhl Manifestos, Volume 7, Issue 1 (2018)


Abstract
We describe the state-of-the-art in performance modeling and prediction for Information Retrieval (IR), Natural Language Processing (NLP) and Recommender Systems (RecSys) along with its shortcomings and strengths. We present a framework for further research, identifying five major problem areas: understanding measures, performance analysis, making underlying assumptions explicit, identifying application features determining performance, and the development of prediction models describing the relationship between assumptions, features and resulting performance.

Cite as

Nicola Ferro, Norbert Fuhr, Gregory Grefenstette, Joseph A. Konstan, Pablo Castells, Elizabeth M. Daly, Thierry Declerck, Michael D. Ekstrand, Werner Geyer, Julio Gonzalo, Tsvi Kuflik, Krister Lindén, Bernardo Magnini, Jian-Yun Nie, Raffaele Perego, Bracha Shapira, Ian Soboroff, Nava Tintarev, Karin Verspoor, Martijn C. Willemsen, and Justin Zobel. From Evaluating to Forecasting Performance: How to Turn Information Retrieval, Natural Language Processing and Recommender Systems into Predictive Sciences (Dagstuhl Perspectives Workshop 17442). In Dagstuhl Manifestos, Volume 7, Issue 1, pp. 96-139, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2018)


Copy BibTex To Clipboard

@Article{ferro_et_al:DagMan.7.1.96,
  author =	{Ferro, Nicola and Fuhr, Norbert and Grefenstette, Gregory and Konstan, Joseph A. and Castells, Pablo and Daly, Elizabeth M. and Declerck, Thierry and Ekstrand, Michael D. and Geyer, Werner and Gonzalo, Julio and Kuflik, Tsvi and Lind\'{e}n, Krister and Magnini, Bernardo and Nie, Jian-Yun and Perego, Raffaele and Shapira, Bracha and Soboroff, Ian and Tintarev, Nava and Verspoor, Karin and Willemsen, Martijn C. and Zobel, Justin},
  title =	{{From Evaluating to Forecasting Performance: How to Turn Information Retrieval, Natural Language Processing and Recommender Systems into Predictive Sciences (Dagstuhl Perspectives Workshop 17442)}},
  pages =	{96--139},
  journal =	{Dagstuhl Manifestos},
  ISSN =	{2193-2433},
  year =	{2018},
  volume =	{7},
  number =	{1},
  editor =	{Ferro, Nicola and Fuhr, Norbert and Grefenstette, Gregory and Konstan, Joseph A. and Castells, Pablo and Daly, Elizabeth M. and Declerck, Thierry and Ekstrand, Michael D. and Geyer, Werner and Gonzalo, Julio and Kuflik, Tsvi and Lind\'{e}n, Krister and Magnini, Bernardo and Nie, Jian-Yun and Perego, Raffaele and Shapira, Bracha and Soboroff, Ian and Tintarev, Nava and Verspoor, Karin and Willemsen, Martijn C. and Zobel, Justin},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagMan.7.1.96},
  URN =		{urn:nbn:de:0030-drops-98987},
  doi =		{10.4230/DagMan.7.1.96},
  annote =	{Keywords: Information Systems, Formal models, Evaluation, Simulation, User Interaction}
}
Document
Towards Performance Modeling and Performance Prediction across IR/RecSys/NLP (Dagstuhl Perspectives Workshop 17442)

Authors: Nicola Ferro, Norbert Fuhr, Gregory Grefenstette, and Joseph A. Konstan

Published in: Dagstuhl Reports, Volume 7, Issue 10 (2018)


Abstract
This reports briefly describes the organization and the plenary talks given during the Dagstuhl Perspectives Workshop 17442. The goal of this workshop was to investigate the state-of-the-art and to delineate a roadmap and research challenges for performance modeling and prediction in three neighbour domains, namely information retrieval (IR), recommender systems (RecSys), and natural language processing (NLP).

Cite as

Nicola Ferro, Norbert Fuhr, Gregory Grefenstette, and Joseph A. Konstan. Towards Performance Modeling and Performance Prediction across IR/RecSys/NLP (Dagstuhl Perspectives Workshop 17442). In Dagstuhl Reports, Volume 7, Issue 10, pp. 139-146, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2018)


Copy BibTex To Clipboard

@Article{ferro_et_al:DagRep.7.10.139,
  author =	{Ferro, Nicola and Fuhr, Norbert and Grefenstette, Gregory and Konstan, Joseph A.},
  title =	{{Towards Performance Modeling and Performance Prediction across IR/RecSys/NLP (Dagstuhl Perspectives Workshop 17442)}},
  pages =	{139--146},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2018},
  volume =	{7},
  number =	{10},
  editor =	{Ferro, Nicola and Fuhr, Norbert and Grefenstette, Gregory and Konstan, Joseph A.},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.7.10.139},
  URN =		{urn:nbn:de:0030-drops-86667},
  doi =		{10.4230/DagRep.7.10.139},
  annote =	{Keywords: Information Systems, Formal models, Evaluation, Simulation, User Interaction}
}
Document
User-Generated Content in Social Media (Dagstuhl Seminar 17301)

Authors: Tat-Seng Chua, Norbert Fuhr, Gregory Grefenstette, Kalervo Järvelin, and Jaakko Paltonen

Published in: Dagstuhl Reports, Volume 7, Issue 7 (2018)


Abstract
This report documents the program and the outcomes of Dagstuhl Seminar 17301 "User-Generated Content in Social Media". Social media have a profound impact on individuals, businesses, and society. As users post vast amounts of text and multimedia content every minute, the analysis of this user generated content (UGC) can offer insights to individual and societal concerns and could be beneficial to a wide range of applications. In this seminar, we brought together researchers from different subfields of computer science, such as information retrieval, multimedia, natural language processing, machine learning and social media analytics. We discussed the specific properties of UGC, the general research tasks currently operating on this type of content, identifying their limitations, and imagining new types of applications. We formed two working groups, WG1 "Fake News and Credibility", WG2 "Summarizing and Story Telling from UGC". WG1 invented an "Information Nutrition Label" that characterizes a document by different features such as e.g. emotion, opinion, controversy, and topicality; For computing these feature values, available methods and open research issues were identified. WG2 developed a framework for summarizing heterogeneous, multilingual and multimodal data, discussed key challenges and applications of this framework.

Cite as

Tat-Seng Chua, Norbert Fuhr, Gregory Grefenstette, Kalervo Järvelin, and Jaakko Paltonen. User-Generated Content in Social Media (Dagstuhl Seminar 17301). In Dagstuhl Reports, Volume 7, Issue 7, pp. 110-154, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2018)


Copy BibTex To Clipboard

@Article{chua_et_al:DagRep.7.7.110,
  author =	{Chua, Tat-Seng and Fuhr, Norbert and Grefenstette, Gregory and J\"{a}rvelin, Kalervo and Paltonen, Jaakko},
  title =	{{User-Generated Content in Social Media (Dagstuhl Seminar 17301)}},
  pages =	{110--154},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2018},
  volume =	{7},
  number =	{7},
  editor =	{Chua, Tat-Seng and Fuhr, Norbert and Grefenstette, Gregory and J\"{a}rvelin, Kalervo and Paltonen, Jaakko},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.7.7.110},
  URN =		{urn:nbn:de:0030-drops-84260},
  doi =		{10.4230/DagRep.7.7.110},
  annote =	{Keywords: social media, user-generated content, social multimedia, summarisation, storytelling, fake-news, credibility, AI}
}
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail