<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-1051">
  <Title>Automatic learning of textual entailments with cross-pair similarities</Title>
  <Section position="4" start_page="401" end_page="401" type="intro">
    <SectionTitle>
2 Related work
</SectionTitle>
    <Paragraph position="0"> Although the textual entailment recognition problem is not new, most of the automatic approaches have been proposed only recently. This has been mainly due to the RTE challenge events (Dagan et al., 2005; Bar Haim et al., 2006). In the following we report some of such researches.</Paragraph>
    <Paragraph position="1"> A first class of methods defines measures of the distance or similarity between T and H either assuming the independence between words (Corley and Mihalcea, 2005; Glickman et al., 2005) in a bag-of-word fashion or exploiting syntactic interpretations (Kouylekov and Magnini, 2005). A pair (T,H) is then in entailment when sim(T,H) &gt; a. These approaches can hardly determine whether the entailment holds in the examples of the previous section. From the point of view of bag-of-word methods, the pairs (T1,H1) and (T1,H2) have both the same intra-pair similarity since the sentences of T1 and H1 as well as those of T1 and H2 differ by a noun, insurance and cash, respectively. At syntactic level, also, we cannot capture the required information as such nouns are both noun modifiers: insurance modifies companies and cash modifies dividends.</Paragraph>
    <Paragraph position="2"> A second class of methods can give a solution to the previous problem. These methods generally combine a similarity measure with a set of possible transformations T applied over syntactic and semantic interpretations. The entailment between T and H is detected when there is a transformation r [?] T so that sim(r(T),H) &gt; a. These transformations are logical rules in (Bos and Markert, 2005) or sequences of allowed rewrite rules in (de Salvo Braz et al., 2005). The disadvantage is that such rules have to be manually designed. Moreover, they generally model better positive implications than negative ones and they do not consider errors in syntactic parsing and semantic analysis.</Paragraph>
  </Section>
class="xml-element"></Paper>