<?xml version="1.0" standalone="yes"?>
<Paper uid="H90-1071">
  <Title>MacWhinney, B. Competition and Lexical Categoriza-</Title>
  <Section position="4" start_page="367" end_page="368" type="metho">
    <SectionTitle>
4. An Analogy.based Model of Lexical Acquisition
</SectionTitle>
    <Paragraph position="0"> We have been attempting to extend MIDAS-style word hypothesizing to be able to propose new word senses by using analogy to exploit these other kinds of lexical subregularifies. At this point, our work has been rather preliminary, but we can at least sketch out the basic architecture of our proposal and comment on the problems we have yet to resolve.</Paragraph>
    <Paragraph position="1"> (A) Detect unknown word sense. For example, suppose the system encountered the following phrase: &amp;quot;at breakfast&amp;quot; Suppose further that the function noun &amp;quot;breakfa.~t&amp;quot; were known to the system, but the determinerless usage were not. In this case, the system would hypothesize that it is lacking a word sense because of a failure to parse the sentence.</Paragraph>
    <Paragraph position="2"> (B) Find relevant cases/subregularities. Cues from the input would be used to suggest prior relevant lexical knowledge. In our example, the retrieved cases might include the following: bed-I/bed-3, class- 1/class-4 Here we have numbered word senses so that the first element of each pair designates a sense involving a core meaning, and the latter a determineless-activity type of sense. We may have also already computed and stored relevant subregularities. If so, then these would be retrieved as well.</Paragraph>
    <Paragraph position="3"> Relevant issues here are the indexing and retrieval of cases and subregularities. Our assumption is that we can retrieve relevant cases by a conjunction of simple cues, like &amp;quot;noun&amp;quot;, &amp;quot;functional meaning&amp;quot;, &amp;quot;extended determinerless noun sense&amp;quot;, etc., and then rely on the next phase to discriminate further among these.</Paragraph>
    <Paragraph position="4"> (C) Chose the most pertinent case or subregularity.</Paragraph>
    <Paragraph position="5"> Again, by analogy to MIDAS, some distance metric is used to pick the best datum to analogize from. In this  case, perhaps the correct choice would be the following: class- l/class-4 One motivation for this selection is that &amp;quot;class&amp;quot; is compatible with &amp;quot;at&amp;quot;, as is the case in point. Finding the right metric is the primary issue here. The MIDAS meuic is a simple sum of two factors: (i) the length of the core-relationship fi'om the input source to the source of the candidate metaphor, and (ii) hierarchical distance between the two concepts. Both factors are measured by the number of finks in the representation that must be traversed to get from one concept to the other. The hierarchical distance factor of the MIDAS metric seems directly relevant to other cases. However, there is no obvious counterpart to the core-relationship component. One possible reason for this is that metaphoric extensions are more complex than most other kinds; if so, then the MIDAS metric may still be applicable to the other subregularities, which are just simpler special cases.</Paragraph>
    <Paragraph position="6"> (D) Analogize to a new meaning. Given the best case or subregularity, the system will attempt to hypothesize a new word sense. For example, in the case at hand, we would like a representation for the meaning in quotes to be produced.</Paragraph>
    <Paragraph position="7"> class- l/class..d :: breakfast-If'period of eating breakfast&amp;quot; In the case of MIDAS, the metaphoric structure of previous examples was assumed to be available. Then, once a best match was established, it is relatively straightforward to generalize or extend this structure to apply to the new input. The same would be true in the general case, provided that the relation between stored polysemous word senses is readily available.</Paragraph>
    <Paragraph position="8"> (E) Determine the extent of generaliTation. Supposing that a single new word sense can be successfully proposed, the question arises as to whether just this particular word sense is all the system can hypothesize, or whether some &amp;quot;local productivity&amp;quot; is possible. For example, if this is the first meal term the system has seen as having a determinerless activity sense, we suspect that only the single sense should be generated. However, if it is the second such meal term, then the first one would have been the likely basis for the analogy, and a generaliTmion to meal terms in general may be attempted.</Paragraph>
    <Paragraph position="9"> (F) Record a new entry. The new sense needs to be stored in the lexicon, and indexed for further reference. This task may interact closely with (E), although generalizing to unattested cases and computing expficit subregularities are logically independent.</Paragraph>
    <Paragraph position="10"> There are many additional problems to be addressed beyond the ones alluded to above. In particular', there is the issue of the role of world knowledge in the proposed process. In the example above, the system must know that the activity of eating is the primary one associated with breakfast. A more dramatic example is the role of world knowledge in hypothesizing the meaning of &amp;quot;treed&amp;quot; in expressions like &amp;quot;the..dog treed the cat&amp;quot;, assuming that the system is acquainted with the noun &amp;quot;tree&amp;quot;. All an analogical reasoning mechanism can do is suggest that some specific activity associated with trees is involved; the application of world knowledge would have to do the rest.</Paragraph>
  </Section>
  <Section position="5" start_page="368" end_page="369" type="metho">
    <SectionTitle>
$. Other Directions of Investigation
</SectionTitle>
    <Paragraph position="0"> We have also been investigating exploiting subregularities in &amp;quot;intelligent dictionary reading&amp;quot;. This project involves an additional idea, namely, that one could best use a dictionary to gain lexical knowledge by bringing to bear on it a full natural language processing capability.</Paragraph>
    <Paragraph position="1"> One problem we have encountered is that dictionaries are full of inaccuracies about the meaning of words. For example, even relatively good dictionaries have poor enuies for the likes of determinerless nouns like &amp;quot;bed&amp;quot;. E.g., Webster's New World (Second Edition) simply lists &amp;quot;bedtime&amp;quot; as a sense of &amp;quot;bed&amp;quot;; Longman's Dictionary of Contemporary English (New Edition) uses &amp;quot;in bed&amp;quot; as an example of the ordinary noun &amp;quot;bed&amp;quot;, then explicitly lists the phrase &amp;quot;time for bed&amp;quot; as meaning &amp;quot;time to go to sleep&amp;quot;, and gives a few other determinerless usages, leaving it to the reader to infer a generalization.* However, a dictionary reader with knowledge of the subregularity mentioned above might be able to correct such deficiencies, and come up with a better meaning that the one the dictionary supplies.</Paragraph>
    <Paragraph position="2"> Thus, we plan to explore augmenting our intelligent dictionary reader with the abifity to use subregularities to compensate for inadequate dictionary entries.</Paragraph>
    <Paragraph position="3"> We are also auempting to apply the same approach to acquiring the semantics of constructions. In particular, we are investigating verb.particular combinations and conventionalized noun phrases (e.g., nominal compounds). We are also looking at constructions like the ditransitive (i.e., dative alternation), which seem also to display a kind of polysemy. Specifically, Goldberg (1989, 1990) has argued that much of the data on this construction can be accounted for in terms of subclasses that are conventionally associated with the construction itself, rather than with lexical rules and transformations as proposed, for example, by Gropen et al. (1989). If so, then the techniques for the acquisition of polysemous *Longman's also defines &amp;quot;make the bed&amp;quot; u &amp;quot;make it ready for deepin s in&amp;quot;. We have no idea bow to cope with such ~rrurz, but they do undenoore the pmble~n.</Paragraph>
    <Paragraph position="4">  lexical items should prove equally applicable to the acquisition of knowledge about such constructions. We are attempting to determine whether this is the case.</Paragraph>
  </Section>
class="xml-element"></Paper>