<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="oai2.xsl"?>
<OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd">
  <responseDate><![CDATA[2026-08-12T12:27:36Z]]></responseDate>
  <request verb="GetRecord" metadataPrefix="oai_dc" identifier="oai:it.cnr:prodotti:287038"><![CDATA[http://www.cnr.it/oai-pmh/oai2.php]]></request>
  <GetRecord>
    <record>
      <header>
        <identifier><![CDATA[oai:it.cnr:prodotti:oai:it.cnr:prodotti:287038]]></identifier>
        <datestamp><![CDATA[2015-02-20T17:23:21Z]]></datestamp>
        <setSpec><![CDATA[openaire]]></setSpec>
        <setSpec><![CDATA[CDS048]]></setSpec>
      </header>
      <metadata>
        <oai_dc:dc xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
          <dc:type><![CDATA[info:eu-repo/semantics/conferenceObject]]></dc:type>
          <dc:type><![CDATA[Contributo in atti di convegno]]></dc:type>
          <dc:title><![CDATA[Flexible Acquisition  of Subcategorization Frames in Italian]]></dc:title>
          <dc:creator><![CDATA[Caselli, Tommaso]]></dc:creator>
          <dc:creator><![CDATA[Frontini, Francesca]]></dc:creator>
          <dc:creator><![CDATA[Quochi, Valeria]]></dc:creator>
          <dc:creator><![CDATA[Rubino, Francesco]]></dc:creator>
          <dc:creator><![CDATA[Russo, Irene]]></dc:creator>
          <dc:language><![CDATA[eng]]></dc:language>
          <dc:description><![CDATA[Lexica of predicate-argument structures constitute a useful tool for several tasks in NLP. This paper describes a web-service system for automatic acquisition of verb subcategorization frames (SCFs) from parsed data in Italian. The system acquires SCFs in an unsupervised manner. We created two gold standards for the evaluation of the system, the first by mixing together information from two lexica (one manually created and the second automatically acquired) and manual exploration of corpus data and the other annotating data extracted from a specialized corpus (environmental domain). Data filtering is accomplished by means of the maximum likelihood estimate (MLE). The evaluation phase has allowed us to identify the best empirical MLE threshold for the creation of a lexicon (P=0.653, R=0.557, F1=0.601). In addition to this, we assigned to the extracted entries of the lexicon a confidence score based on the relative frequency and evaluated the extractor on domain specific data. The confidence score will allow the final user to easily select the entries of the lexicon in terms of their reliability: one of the most interesting feature of this work is the possibility the final users have to customize the results of the SCF extractor, obtaining different SCF lexica in terms of size and accuracy.]]></dc:description>
          <dc:source><![CDATA[Eight International Conference on Language Resources and Evaluation (LREC'12), pp. 2842–2848, Istanbul, Turkey, 23-25 Maggio 2012]]></dc:source>
          <dc:source><![CDATA[info:cnr-pdr/source/autori:Caselli, Tommaso; Frontini, Francesca; Quochi, Valeria; Rubino, Francesco and Russo, Irene/congresso_nome:Eight International Conference on Language Resources and Evaluation (LREC'12)/congresso_luogo:Istanbul, Turkey/congresso_data:23-25 Maggio 2012/anno:2012/pagina_da:2842/pagina_a:2848/intervallo_pagine:2842–2848]]></dc:source>
          <dc:publisher><![CDATA[European Language Resources Association ELRA, Paris, FRA]]></dc:publisher>
          <dc:date><![CDATA[2012]]></dc:date>
          <dc:identifier><![CDATA[http://www.cnr.it/prodotto/i/287038]]></dc:identifier>
          <dc:identifier><![CDATA[https://publications.cnr.it/doc/287038]]></dc:identifier>
          <dc:identifier><![CDATA[http://www.lrec-conf.org/proceedings/lrec2012/summaries/390.html]]></dc:identifier>
          <dc:identifier><![CDATA[urn:isbn:9782951740877]]></dc:identifier>
          <dc:relation><![CDATA[info:eu-repo/grantAgreement/EC/FP7/248064//Platform for Automatic, Normalized Annotation and Cost-Effective Acquisition of Language Resources for Human Language Technologies/PANACEA]]></dc:relation>
          <dc:relation><![CDATA[info:cnr-pdr/author/idpersonaleesterno:6898/CASELLI/TOMMASO]]></dc:relation>
          <dc:relation><![CDATA[info:cnr-pdr/author/idpersonaleesterno:15422/RUSSO/IRENE]]></dc:relation>
          <dc:relation><![CDATA[info:cnr-pdr/author/idpersonaleesterno:17591/FRONTINI/FRANCESCA]]></dc:relation>
          <dc:relation><![CDATA[info:cnr-pdr/author/idpersonaleesterno:17594/RUBINO/FRANCESCO]]></dc:relation>
          <dc:relation><![CDATA[info:cnr-pdr/author/matricola:11893/QUOCHI/VALERIA]]></dc:relation>
          <dc:subject><![CDATA[lexicon]]></dc:subject>
          <dc:subject><![CDATA[automatic acquisition]]></dc:subject>
          <dc:subject><![CDATA[subcategorisation frames]]></dc:subject>
        </oai_dc:dc>
      </metadata>
    </record>
  </GetRecord>
</OAI-PMH>
