[Forum SIS] Seminario Dott. Panchenko

[Dip. Scienze Statistiche - Mi]

Il Dipartimento di Filosofia e il CIRCSE dell'Università Cattolica del Sacro Cuore organizzano il seguente seminario di semantica, presentato dal Dott.  Alexander Panchenko, dell'Université catholique de Louvain (Belgium) & Digital Society Laboratory (Russia)

Similarity Measures for Semantic Relation Extraction
Lunedì 21 Luglio 2014, 15:00
Aula G. 051

Introduce Marco Passarotti.
Per informazioni: marco.passarotti at unicatt.it<mailto:marco.passarotti at unicatt.it>

Bio:Alexander Panchenko earned his PhD in Natural Language Processing from Université catholique de Louvain (Belgium) in co-tutelle with Moscow State Technical University on  "Similarity Measures for Semantic Relation Extraction"<http://panchenko.me/thesis.pdf> . Now Alexander works as a Research Engineer for Digital Society Laboratory (Moscow) and is an Associated Researcher at Université catholique de Louvain. Currently, he is active in three following domains: short text classification for social media analysis (sentiment analysis, topic categorization, gender detection, etc.), computational lexical semantics (lexical similarity measures, semantic relation extraction, etc.) and skill extraction from text. Alexander is authored and co-authored more than 20 papers in peer-reviewed conferences in computational linguistics and informatics. He served as a reviewer and program committee member of several conferences in natural language processing. Recently, he co-organized a data mining conference AIST'2014 ( http://aistconf.org/). Further information about the speaker can be found at  http://cental.fltr.ucl.ac.be/team/~panchenko/ .

Description: Semantic relations, such as synonyms, hypernyms and co-hyponyms proved to be useful for text processing applications, including text similarity, query expansion, question answering and word sense disambiguation. Such relations are practical because of the gap between lexical surface of the text and its meaning. Indeed, the same concept is often represented by different terms. However, existing resources often do not cover a vocabulary required by a given system. Manual resource construction is prohibitively expensive for many projects.
On the other hand, precision of the existing extractors still do not meet quality of the handcrafted resources. All these factors motivate the development of novel extraction methods. In this work we developed several similarity measures for semantic relation extraction. The main research question we address, is how to improve precision and coverage of such measures. First, we perform a large-scale study the baseline techniques. Second, we propose four novel measures. One of them significantly outperforms the baselines, the others perform comparably to the state-of-the-art techniques. Finally, we successfully apply one of the novel measures in two text processing systems.

Slides (draft):  http://www.slideshare.net/alexanderpanchenko/semantic-similarity-measures-for-semantic-relation-extraction

Demo:  http://serelex.cental.be/

Related papers:  http://link.springer.com/chapter/10.1007/978-3-642-36973-5_97  ,  http://www.oegai.at/konvens2012/proceedings/23_panchenko12p/

Homepage:  http://cental.fltr.ucl.ac.be/team/~panchenko/


Dipartimento di Scienze statistiche
Università Cattolica del Sacro Cuore
Largo A. Gemelli, 1
20123   Milano
http://docenti.unicatt.it/ita/Gabriele_Cantaluppi
http://docenti.unicatt.it/eng/Gabriele_Cantaluppi
tel +39 0272342492
fax +39 0272343064


________________________________

Messaggio istituzionale

Ricerca, Formazione, Assistenza, Cooperazione e Sviluppo: 5 ragioni per metterci la firma.
Grazie a un gesto semplice puoi sostenere le iniziative dell'Ateneo dei cattolici italiani e del Policlinico "A. Gemelli".
Sottoscrivi il 5 per mille a favore dell'Università Cattolica.
Info: www.unicatt.it/5permille<http://www.unicatt.it/5permille/>
________________________________
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.stat.unipg.it/pipermail/sis/attachments/20140703/9a3ae373/attachment-0001.html>