Cerca
Ara es mostren els items 1-10 de 43
Language technology challenges of a "small" language (Catalan)
(2010-05)
Text en actes de congrés.
Accés restringit per política de l'editorial
Text en actes de congrés.
Accés restringit per política de l'editorial
In this paper, we present a brief snapshot of the state of affairs in computational processing of Catalan and the initiatives that are starting to take place in an effort to bring the field a step forward, by making a ...
KnowNet: building a large net of knowledge from the web
(2008)
Text en actes de congrés.
Accés obert
Text en actes de congrés.
Accés obert
This paper presents a new fully automatic
method for building highly dense and accurate knowledge bases from existing
semantic resources. Basically, the method uses a wide-coverage and accurate knowledge-based Word Sense ...
Comparing non-parametric ensemble methods for document clustering
(Springer Verlag, 2008)
Text en actes de congrés.
Accés restringit per política de l'editorial
Text en actes de congrés.
Accés restringit per política de l'editorial
The biases of individual algorithms for non-parametric document clustering can lead to non-optimal solutions. Ensemble clustering
methods may overcome this limitation, but have not been applied to document collections. ...
FEMsum at DUC 2007
(2007)
Text en actes de congrés.
Accés obert
Text en actes de congrés.
Accés obert
This paper describes and analyzes how the FEMsum system deals with DUC 2007 tasks of providing summary-length answers to complex questions, both background and just-the-news summaries. We participated in producing background ...
The TALP participation at TAC-KBP 2013
(2013)
Text en actes de congrés.
Accés obert
Text en actes de congrés.
Accés obert
This document describes the work performed by the Universitat Politècnica de Catalunya (UPC) in its second participation at TAC-KBP 2013 in both the Entity Linking and the Slot Filling tasks.
English language learning activity using spoken language and intelligent computer-assisted technologies
(2011)
Comunicació de congrés.
Accés obert
Comunicació de congrés.
Accés obert
This paper presents work in progress on language technologies applied to secondary school education. The application presented integrates several state-of-the-art technologies related to spoken language and intelligent ...
IARG-AnCora: Annotating the AnCora corpus with implicit arguments
(2012)
Text en actes de congrés.
Accés restringit per política de l'editorial
Text en actes de congrés.
Accés restringit per política de l'editorial
IARG-AnCora is an ongoing project which aim is to annotate the implicit arguments of deverbal nominalizations in AnCora corpus. This corpus will be the basis for systems of automatic semantic role labeling based on machine ...
Semantic annotation of deverbal nominalizations in the Spanish corpus AnCora
(North European Association for Language Technology, 2010)
Text en actes de congrés.
Accés obert
Text en actes de congrés.
Accés obert
This paper presents the methodology and the linguistic criteria followed to enrich the AnCora-Es corpus with the semantic annotation of deverbal nominalizations. The first step was to run two independent automated processes: ...
Cultural configuration of Wikipedia: measuring autoreferentiality in different languages
(2011)
Text en actes de congrés.
Accés obert
Text en actes de congrés.
Accés obert
Among the motivations to write in Wikipedia
given by the current literature there is often coincidence, but none of the studies presents the hypothesis of contributing for the visibility of the own national or language ...
Using Wikipedia for domain terms extraction
(2012)
Text en actes de congrés.
Accés restringit per política de l'editorial
Text en actes de congrés.
Accés restringit per política de l'editorial
Domain terms are a useful resource for tuning both resources and NLP processors to domain specific tasks. This paper proposes a method for obtaining terms from potentially any domain using Wikipedia.