<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-1034">
  <Title>Theory Refinement and Natural Language Learning Hervd Ddjean* Seminar fiir S1)rachwissenschaft</Title>
  <Section position="7" start_page="233" end_page="234" type="concl">
    <SectionTitle>
6 Evaluation
</SectionTitle>
    <Paragraph position="0"> We now show some results and give some comparisons with other works (Table 5). The results are, quite sinfilar to other approaches. Two rates are measured: precision an recall.</Paragraph>
    <Paragraph position="1"> ~, ~ Nu~nbcr of correct proposed pattc'rns Number of correct patterns p z Number o.f correct proposed patterns Nu'mber of proposed pattcrns Tile training data. are comt)osed of the sections 15-18 of tile Wall Street Journal Corpus (Marcus el; al., 1993), and we use the section 20 for the test corpus 12. The data is tagged with the Brill tagger. The works generating syinbolic rules like ALLiS are (Rainshaw and Marcus, 1.995) (Transformation-Based learning) and (Cardie and Pierce, 1.998) (error-driven pruning of treebank grammars). ALLiS provides better results than them. (Argamon et al., 1.998) use a Memory-Based Shallow Learning system, (Tjong Kim Sang and Veenstra, 1999) the Memory-Based Learning nmtho(l and (Mufioz el; at., 1999) uses a network of linear functions. The latter work seems to integrate better lexical intbrmation since ALLiS gets better results with POS only.</Paragraph>
    <Paragraph position="2">  sion/recall).</Paragraph>
    <Paragraph position="3"> The main errors done by ALLiS are due to errors of tagging (the corpus is tagged with the Brill tagger) or errors in the bracketing of the training cortms. Then, the second type of errors concerns 12This data set; is avMlable via ftp://ftp, cis. upenn, edu/ pub/chunker/.</Paragraph>
    <Paragraph position="4">  tim (:o()rdin;dx:(1 sl,ru(:tures. 'l'h(;s(~ two tyl)(;s (}l'l'Ol'S correspond to 51% of the, overall errors. We (:an tin(l 1;11(: sam(; l;yl)olop;y in other works (\]{anlshaw :rod Marcus, 1995), (Ca rdi(: and Pierc(:, 1998). \Ve did some tries in order to manually imt)r()v(', th(; final ,grammar: I)ut l;lm only tyt/(; ()f errors whi(:h can 1)e mmnmlly iml)r()v(;(1 (:(m(:(wns tim t)r()t)h;m of the (tuolaI;ion tamks (th(~ inll)rov(mw.nl is al)()ul ()l' 0.2% i~l l)re(:ision mid recall).</Paragraph>
  </Section>
class="xml-element"></Paper>