Wikipedia - Scientific articles - Cronologia

Christian: Harvard Business School, dicembre 2006

2009-03-24T11:16:06Z

Harvard Business School, dicembre 2006

Christian: Biblioteche oggi, gennaio-febbraio 2009

2009-03-09T14:57:44Z

Biblioteche oggi, gennaio-febbraio 2009

Christian: /* 2007 */ :HP Laboratories, febbraio 2007

2009-03-09T14:50:17Z

‎2007: :HP Laboratories, febbraio 2007

Christian: Evaluating authoritative sources using social networks: an insight from Wikipedia

2009-02-24T22:26:59Z

Evaluating authoritative sources using social networks: an insight from Wikipedia

Christian: Episteme, feb. 2009

2009-02-23T22:12:36Z

Episteme, feb. 2009

Andrea: Annullata la modifica 4910 di Andrea (discussione)

2009-02-19T13:21:47Z

Annullata la modifica 4910 di Andrea (discussione)

Mostra modifiche

Andrea il 13:21, 19 feb 2009

2009-02-19T13:21:08Z

Mostra modifiche

Christian: title

2009-02-19T13:15:11Z

title

Mostra modifiche

Christian: da Web of Science

2009-02-19T13:08:01Z

da Web of Science

Mostra modifiche

@@ Riga 7: / Riga 7: @@
 ==2004==
 * {{cite journal |author=Nikolaos Th. Korfiatis; Marios Poulos and George Bokos|title=Evaluating authoritative sources using social networks: an insight from Wikipedia|publisher=OIR|date=March 2006|year=|month=|volume=30|issue=3|page=252|pages=11}}
 ==2007==

@@ Riga 114: / Riga 114: @@
 * {{cite journal |author=Giampiccolo, Danilo; Forner, Pamela; Herrera, Jesus; Penas, Anselmo; Ayache, Christelle; Forascu, Corina; Jijkoun, Valentin; Osenova, Petya; Rocha, Paulo; Sacaleanu, Bogdan; Sutcliffe, Richard|title=Overview of the CLEF 2007 Multilingual Question Answering Track|publisher=ADVANCES IN MULTILINGUAL AND MULTIMODAL INFORMATION RETRIEVAL|date=SEP 19-21, 2007|year=2008|month=0|volume=5152|issue=0|page=200|pages=37}}
 :The fifth QA campaign at CLEF [1], having its first edition in 2003, offered not only a main task but an Answer Validation Exercise (AVE) [2], which continued last year's pilot, and a new pilot: the Question Answering on Speech Transcripts (QAST) [3, 15]. The main task was characterized by the focus on cross-linguality, while covering as many European languages as possible. As novelty, some QA pairs were grouped in clusters. Every cluster was characterized by a topic (not given to participants). The questions from a cluster possibly contain co-references between one of them and the others. Finally, the need for searching answers in web formats was satisfied by introducing Wikipedia(1) as document corpus. The results and the analyses reported by the participants suggest that the introduction of Wikipedia and the topic related questions led to a drop in systems' performance.
 ===[http://www.eupjournals.com/toc/epi/6/1?cookieSet=1# Episteme, feb. 2009]===

@@ Riga 7: / Riga 7: @@
 ==2004==
 * {{cite journal |author=Nikolaos Th. Korfiatis; Marios Poulos and George Bokos|title=Evaluating authoritative sources using social networks: an insight from Wikipedia|publisher=OIR|date=March 2006|year=|month=|volume=30|issue=3|page=252|pages=11}}
 ==2008==

@@ Riga 4: / Riga 4: @@
 {{TOCright}}
 * {{cite journal |author=Zhang, Congle; Xue, Gui-Rong; Yu, Yong|title=Knowledge Supervised Text Classification with No Labeled Documents|publisher=PRICAI 2008: TRENDS IN ARTIFICIAL INTELLIGENCE|date=DEC 15-19, 2008|year=2008|month=0|volume=5351|issue=0|page=509|pages=12}}
 :In traditional text classification approaches, the semantic meanings of the classes are described by the labeled documents. Since labeling documents is often time consuming and expensive, it; is a promising idea that asking users to provide some keywords to depict the classes, instead of labeling any documents. However, short pieces of keywords may not contain enough information and therefore may lead to unreliable classifier. Fortunately, there are large amount of public data easily available in web directories, such as ODP, Wikipedia, etc. We are interested in exploring the enormous crowd intelligence contained in such public data to enhance text classification. In this paper, we propose a novel text; classification framework called "Knowledge Supervised Learning" (KSL), which utilizes the knowledge in keywords and the crowd intelligence to learn the classifier without any labeled documents. We design a two-stage risk minimization (TSRM) approach for the KSL problem. It can optimize the expected prediction risk and build the high quality classifier. Empirical results verify our claim: our algorithm can achieve above 0.9 on Micro-F1 on average, which is much better than baselines and even comparable against SVM classifier supervised by labeled documents.

@@ Riga 3: / Riga 3: @@
 * {{cite journal |author=Zhang, Congle; Xue, Gui-Rong; Yu, Yong|title=Knowledge Supervised Text Classification with No Labeled Documents|publisher=PRICAI 2008: TRENDS IN ARTIFICIAL INTELLIGENCE|date=DEC 15-19, 2008|year=2008|month=0|volume=5351|issue=0|page=509|pages=12}}
 :In traditional text classification approaches, the semantic meanings of the classes are described by the labeled documents. Since labeling documents is often time consuming and expensive, it; is a promising idea that asking users to provide some keywords to depict the classes, instead of labeling any documents. However, short pieces of keywords may not contain enough information and therefore may lead to unreliable classifier. Fortunately, there are large amount of public data easily available in web directories, such as ODP, Wikipedia, etc. We are interested in exploring the enormous crowd intelligence contained in such public data to enhance text classification. In this paper, we propose a novel text; classification framework called "Knowledge Supervised Learning" (KSL), which utilizes the knowledge in keywords and the crowd intelligence to learn the classifier without any labeled documents. We design a two-stage risk minimization (TSRM) approach for the KSL problem. It can optimize the expected prediction risk and build the high quality classifier. Empirical results verify our claim: our algorithm can achieve above 0.9 on Micro-F1 on average, which is much better than baselines and even comparable against SVM classifier supervised by labeled documents.
@@ Riga 103: / Riga 104: @@
 * {{cite journal |author=Giampiccolo, Danilo; Forner, Pamela; Herrera, Jesus; Penas, Anselmo; Ayache, Christelle; Forascu, Corina; Jijkoun, Valentin; Osenova, Petya; Rocha, Paulo; Sacaleanu, Bogdan; Sutcliffe, Richard|title=Overview of the CLEF 2007 Multilingual Question Answering Track|publisher=ADVANCES IN MULTILINGUAL AND MULTIMODAL INFORMATION RETRIEVAL|date=SEP 19-21, 2007|year=2008|month=0|volume=5152|issue=0|page=200|pages=37}}
 :The fifth QA campaign at CLEF [1], having its first edition in 2003, offered not only a main task but an Answer Validation Exercise (AVE) [2], which continued last year's pilot, and a new pilot: the Question Answering on Speech Transcripts (QAST) [3, 15]. The main task was characterized by the focus on cross-linguality, while covering as many European languages as possible. As novelty, some QA pairs were grouped in clusters. Every cluster was characterized by a topic (not given to participants). The questions from a cluster possibly contain co-references between one of them and the others. Finally, the need for searching answers in web formats was satisfied by introducing Wikipedia(1) as document corpus. The results and the analyses reported by the participants suggest that the introduction of Wikipedia and the topic related questions led to a drop in systems' performance.