aipamenak – Hizkuntza-teknologiak, Ixa Taldearen bloga https://www.unibertsitatea.net/blogak/ixa IXA taldea. Hizkuntzaren prozesamendua Wed, 31 May 2023 21:32:01 +0000 eu hourly 1 https://wordpress.org/?v=4.9.23 https://www.unibertsitatea.net/blogak/ixa/files/2018/10/ixa.jpg aipamenak – Hizkuntza-teknologiak, Ixa Taldearen bloga https://www.unibertsitatea.net/blogak/ixa 32 32 Hitzaldia: Ele anitzetako aipamenen detekzioa koreferentziaren ebazpenerako (O. Uryupina, 2014/02/21) https://www.unibertsitatea.net/blogak/ixa/2014/02/17/hitzaldia-ele-anitzetako-aipamenen-detekzioa-koreferentziaren-ebazpenerako-20140221/ https://www.unibertsitatea.net/blogak/ixa/2014/02/17/hitzaldia-ele-anitzetako-aipamenen-detekzioa-koreferentziaren-ebazpenerako-20140221/#comments Mon, 17 Feb 2014 18:56:33 +0000 https://www.unibertsitatea.net/blogak/ixa/?p=1445 Hizlariak: Olga Uryupina
Trentoko Unibertsitatea
Eguna: Otsailaren 21an, 2014, ostirala
Ordua: Arratsaldeko 12:00retan
Non
: Informatika Fakutatea, 3.2 gela

 

Izenburua:
Ele anitzetako aipamenen detekzioa koreferentziaren ebazpenerako.
/Multilingual Mention Detection for Coreference Resolution

 Edukia:

Accurate mention detection is a vital prerequisite for a variety of
Natural Language Processing tasks, in particular, for Relation
Extraction and Coreference Resolution. If a toolkit cannot extract
mentions reliably, it will obviously be unable to assign them to
relations or entities.

We propose a novel algorithm for multilingual mention detection: we
extract mentions from parse trees via kernel-based SVM learning. Our
approach allows for straightforward mention detection for any language
where (not necessary perfect) parsing resources are available, without
any complex language-specific rule engineering.  We also investigate
possibilities for incorporating automatically acquired mentions into
an end-to-end coreference resolution system. We evaluate our approach
on the Arabic and Chinese portions of the CoNLL-2012 dataset, showing
a significant improvement over the system with the baseline mention
detection.

Lan hau Alessandro Moschitti-ren lankidetzarekin garatu da.

]]>
https://www.unibertsitatea.net/blogak/ixa/2014/02/17/hitzaldia-ele-anitzetako-aipamenen-detekzioa-koreferentziaren-ebazpenerako-20140221/feed/ 1