<?xml version="1.0" standalone="yes"?>
<Paper uid="P91-1017">
  <Title>Two Languages Are More Informative Than One *</Title>
  <Section position="7" start_page="134" end_page="135" type="evalu">
    <SectionTitle>
6 Failures and Possible Im-
</SectionTitle>
    <Paragraph position="0"> provements A detailed analysis of the failures of the method is most important, as it both suggests possible improvements for the model and indicates its limitations. As described above, these failures include either the cases for which the method was not applicable (no selection) or the cases in which it made an incorrect selection. The following paragraphs list the various reasons for both types.</Paragraph>
    <Section position="1" start_page="134" end_page="135" type="sub_section">
      <SectionTitle>
6.1 Inapplicability
</SectionTitle>
      <Paragraph position="0"> Insufficient data. This was the reason for nearly all the cases of inapplicability. For instance, none of the alternative relations 'an investigator of corruption' (the correct one) or 'researcher of corruption' (the incorrect one) was observed in the parsed corpus. In this case it is possible to perform the correct selection if we used only statistics about the cooccurrences of 'corruption' with either 'investigator' or 'researcher', without looking for any syntactic relation (as in Church and Hanks (1990)). The use of this statistic is a subject for further research, but our initial data suggests that it can substantially increase the applicability of the statistical method with just a little decrease in its precision.</Paragraph>
      <Paragraph position="1"> Another way to deal with the lack of statistical data for the specific words in question is to use statistics about similar words. This is the basis for Sadler's Analogical Semantics (1989) which has not yet proved effective. His results may be improved if more sophisticated techniques and larger corpora are used to establish similarity between words (such as in (Hindle, 1990)).</Paragraph>
      <Paragraph position="2"> Conflicting data. In very few cases two alternatives were supported equally by the statistical data, thus preventing a selection. In such cases, both alternatives are valid at the independent level of the lexical relation, but may be inappropriate for the specific context. For instance, the two alternatives of 'to take  a job' or 'to take a position' appeared in one of the examples, but since the general context concerned with the position of a prime minister only the latter was appropriate. In order to resolve such examples it may be useful to consider also cooccurrences of the ambiguous word with other words in the broader context. For instance, the word 'minister' seems to cooccur in the same context more frequently with 'position' than with 'job'.</Paragraph>
      <Paragraph position="3"> In another example both alternatives were appropriate also for the specific context. This happened with the German verb 'werfen', which may be translated (among other options) as 'throw', 'cast' or 'score'. In our example 'werfen' appeared in the context of 'to throw/cast light' and these two correct alternatives had equal frequencies in the corpus ('score' was successfully eliminated). In such situations any selection between the alternatives will be appropriate and therefore any algorithm that handles conflicting data will work properly.</Paragraph>
    </Section>
    <Section position="2" start_page="135" end_page="135" type="sub_section">
      <SectionTitle>
6.2 Incorrect Selection
</SectionTitle>
      <Paragraph position="0"> Using the inappropriate relation. One of the examples contained the Hebrew word 'matzav', which two of its possible translations are 'state' and 'position'. The phrase which contained this word was: 'to put an end to the {state I position} of war ... '.</Paragraph>
      <Paragraph position="1"> The ambiguous word is involved in two syntactic relations, being a complement of 'put' and also modified by 'war'. The corresponding frequencies were: (9) verb-comp: put-position 320 verb-comp: put-state 18 noun-nob j: state-war 13 noun-nob j: position-war 2 The bound of the odds ration (Ba) for the first relation was higher than for the second, and therefore this relation determined the translation as 'position'. However, the correct translation should be 'state', as determined by the second relation.</Paragraph>
      <Paragraph position="2"> This example suggests that while ordering the involved relations (or using any other weighting mechanism) it may be necessary to give different weights to the different types of syntactic relations. For instance, it seems reasonable that the object of a noun should receive greater weight in selecting the noun's sense than the verb for which this noun serves as a complement.</Paragraph>
      <Paragraph position="3"> Confusing senses. In another example, the Hebrew word 'qatann', which two of its meanings are 'small' and 'young', modified the word 'sikkuy', which means 'prospect' or 'chance'. In this context, the correct sense is necessarily 'small'. However, the relation that was observed in the corpus was 'young prospect', relating to the human sense of 'prospect' which appeared in sport articles (a promising young person). This borrowed sense of 'prospect' is necessarily inappropriate, since in Hebrew it is represented by the equivalent of 'hope' ('tiqva'), and not by 'sikkuy'.</Paragraph>
      <Paragraph position="4"> The reason for this problem is that after producing the possible target alternatives, our model ignores the source language input as it uses only a mono-lingual target corpus. This can be solved if we use an aligned bilingual corpus, as suggested by Sadler (1989) and Brown et al. (1990). In such a corpus the occurrences of the relation 'young prospect' will be aligned to the corresponding occurrences of the Hebrew word 'tiqva', and will not be used when the Hebrew word 'sikkuy' is involved. Yet, it should be brought in mind that an aligned corpus is the result of manual translation, which can be viewed as a manual tagging of the words with their equivalent senses in the other language. This resource is much more expensive and less available than the untagged monolingual corpus, while it seems to be necessary only for relatively rare situations.</Paragraph>
      <Paragraph position="5"> Lack of deep understanding. By their nature, statistical methods rely on large quantities of shallow information. Thus, they are doomed to fail when disambiguation can rely only on deep understanding of the text and no other surface cues are available. This happened in one of the Hebrew examples, where the two alternatives were either 'emigration law' or 'immigration law' (the Hebrew word 'hagira' is used for both subsenses). While the context indicated that the first alternative is correct, the statistics preferred the second alternative. It seems that such cases are quiet rare, but only further evaluation will show the extent to which deep understanding is really needed.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>