User Tools

Site Tools


measure_corpus
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<?xml-stylesheet type="text/xsl" href="lexUnit.xsl"?>
<lexUnit xmlns="http://framenet.icsi.berkeley.edu" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" frame="Measure" frameID="652" status="Finished_Initial" POS="N" name="measure.n" ID="8538" totalAnnotated="9" xsi:schemaLocation="../schema/lexUnit.xsd">
    <header>
        <corpus description="BNC2" name="BNC2" ID="111">
            <document description="bncp" name="bncp" ID="421"/>
        </corpus>
        <frame>
            <FE fgColor="FFFFFF" bgColor="FF69B4" type="Core" abbrev="Algorithm" name="ML_Algorithm"/>
            <FE fgColor="FFFFFF" bgColor="004C99" type="Core" abbrev="Measure" name="Measure"/>
            <FE fgColor="FFFFFF" bgColor="0000FF" type="Peripheral" abbrev="Task" name="ML_Task"/>
            <FE fgColor="FFFFFF" bgColor="99004C" type="Peripheral" abbrev="Dataset" name="Dataset"/>
            <FE fgColor="FFFFFF" bgColor="009900" type="Peripheral" abbrev="Value" name="Measure_value"/>
            <FE fgColor="FFFFFF" bgColor="239900" type="Peripheral" abbrev="Method" name="Measure_method"/>
        </frame>
    </header>
    <definition>This frame represents information about specific measure (and its value) used to estimate performance of specific ML algorithm on some dataset. ML algorithm solves ML task.</definition>
    <lexeme POS="N" name="error"/>
 
 
    <subCorpus name="01-unannotated-1">
        <sentence corpID="111" docID="421" sentNo="1" paragNo="181" aPos="0" ID="1215438">
            <text>The resulting optimization problem becomes tractable, but one may wonder if minimizing such a convex proxy still results in a good accuracy.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/s10994-015-5491-2"/>
                    <label cBy="351" end="85" start="76" name="Target"/>
                </layer>
                <layer rank="1" name="FE"><label end="33" start="14" name="ML_Task"/>
                <label end="105" start="76" name="ML_Algorithm"/>
                <label end="138" start="131" name="Measure"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="2" paragNo="181" aPos="0" ID="1215438">
            <text>As such, algorithmic development for classification problems has largely been measured by classification accuracy, precision, or a similar metric on benchmark data sets.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/s10994-013-5422-z"/>
                    <label cBy="351" end="85" start="78" name="Target"/>
                    <label cBy="351" end="112" start="105" name="Target"/>
                    <label cBy="351" end="123" start="115" name="Target"/>
                </layer>
                <layer rank="1" name="FE"><label end="59" start="37" name="ML_Task"/>
                <label end="112" start="90" name="Measure"/>
                <label end="123" start="115" name="Measure"/>
                <label end="144" start="139" name="Measure"/>
                <label end="169" start="149" name="Dataset"/>
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="3" paragNo="181" aPos="0" ID="1215438">
            <text>The area under a precision-recall curve (AUCPR) is a common summary measurement used to report the performance of machine learning algorithms.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/s10994-013-5432-x"/>
                    <label cBy="351" end="32" start="17" name="Target"/>
                    <label cBy="351" end="78" start="68" name="Target"/>
                    <label cBy="351" end="109" start="99" name="Target"/>
                </layer>
                <layer rank="1" name="FE"><label end="140" start="114" name="ML_Algorithm"/>
                <label end="46" start="4" name="Measure"/>
                <label end="66" start="51" name="Measure"/>
 
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="4" paragNo="181" aPos="0" ID="1215438">
            <text>In pattern mining, results are typically selected by some measure of interestingness of which support, the number of selected objects, is the most well-known example.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/s10994-013-5334-y"/>
                    <label cBy="351" end="64" start="58" name="Target"/>
                </layer>
                <layer rank="1" name="FE"><label end="16" start="3" name="ML_Task"/>
                <label end="83" start="69" name="Measure"/>
                <label end="124" start="107" name="Measure"/>
                <label end="100" start="94" name="Measure"/>
 
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="5" paragNo="181" aPos="0" ID="1215438">
            <text>While the conference paper derived active performance estimation techniques for the ranking performance measures ERR and DCG, only results for the ERR measure were included in the empirical study.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/s10994-013-5372-5"/>
                    <label cBy="351" end="52" start="42" name="Target"/>
                    <label cBy="351" end="102" start="92" name="Target"/>
                    <label cBy="351" end="157" start="151" name="Target"/>
                </layer>
                <layer rank="1" name="FE"><label end="115" start="84" name="Measure"/>
                <label end="123" start="121" name="Measure"/>
                <label end="149" start="147" name="Measure"/>
 
 
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="6" paragNo="181" aPos="0" ID="1215438">
            <text>We show that they are calibrated with performance measures like the Discounted Cumulative Gain (DCG), but also that they are not calibrated with respect to the widely used Mean Average Precision and Expected Reciprocal Rank.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/s10994-013-5382-3"/>
                    <label cBy="351" end="57" start="50" name="Target"/>
                    <label cBy="351" end="193" start="185" name="Target"/>
                </layer>
                <layer rank="1" name="FE"><label end="57" start="38" name="Measure"/>
                <label end="105" start="68" name="Measure"/>
                <label end="193" start="172" name="Measure"/>
                <label end="222" start="199" name="Measure"/>
 
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="7" paragNo="181" aPos="0" ID="1215438">
            <text>Collaborative filtering algorithms are generally evaluated according to regression criteria (measuring accuracy in ratings) rather than ranking criteria, and is thus designed for a completely different type of learning framework.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/s10994-013-5356-5"/>
                    <label cBy="351" end="57" start="50" name="Target"/>
                    <label cBy="351" end="193" start="185" name="Target"/>
                </layer>
                <layer rank="1" name="FE"><label end="57" start="38" name="Measure"/>
                <label end="105" start="68" name="Measure"/>
                <label end="193" start="172" name="Measure"/>
                <label end="222" start="199" name="Measure"/>
 
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="8" paragNo="181" aPos="0" ID="1215438">
            <text>In De Bie (2011) a framework for data mining was introduced, aiming to quantify the subjective interestingness of patterns.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/s10994-013-5333-z"/>
                </layer>
                <layer rank="1" name="FE">
                    <label end="109" start="84" name="Measure"/>
                    <label end="121" start="114" name="ML_Algorithm"/>
 
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
        <sentence corpID="111" docID="421" sentNo="9" paragNo="181" aPos="0" ID="1215438">
            <text>The Hamming ranking performance is measured with three widely used metrics in information retrieval: mean average precision (MAP), precision-recall curves and precision curves.</text>
            <annotationSet cDate="05/02/2003 04:00:38 PDT Fri" status="MANUAL" ID="1877967">
                <layer rank="1" name="Target">
                    <label end="0" start="0" name="10.1007/s10994-015-5513-0"/>
                    <label cBy="351" end="30" start="20" name="Target"/>
                    <label cBy="351" end="42" start="35" name="Target"/>
                    <label cBy="351" end="122" start="114" name="Target"/>
                    <label cBy="351" end="146" start="131" name="Target"/>
                </layer>
                <layer rank="1" name="FE">
                    <label end="174" start="67" name="Measure"/>
                    <label end="18" start="4" name="ML_Algorithm"/>
 
            </layer>
                <layer rank="1" name="GF"/>
                <layer rank="1" name="PT"/>
                <layer rank="1" name="Other"/>
                <layer rank="1" name="Sent"/>
                <layer rank="1" name="Verb"/>
            </annotationSet>
        </sentence>
 
    </subCorpus>
</lexUnit>
measure_corpus.txt · Last modified: 2016/03/16 13:21 by pj