<?xml version="1.0" standalone="yes"?>
<Paper uid="P84-1084">
  <Title>SOME LINGUISTIC ASPECTS FOR AUTOMATIC TEXT UNDERSTANDING</Title>
  <Section position="1" start_page="0" end_page="0" type="metho">
    <SectionTitle>
SOME LINGUISTIC ASPECTS FOR AUTOMATIC TEXT UNDERSTANDING
</SectionTitle>
    <Paragraph position="0"/>
  </Section>
  <Section position="2" start_page="0" end_page="0" type="metho">
    <SectionTitle>
ABSTRACT
</SectionTitle>
    <Paragraph position="0"> This paper proposes a system of mapping classes of syntactic structures as instruments for automatic text understanding. The system illustrated in Japanese consists of a set of verb classes and information on mapping them together with noun phrases, tense and aspect. The system. having information on direction of possible inferences between the verb classes with information on tense and aspect, is supposed to be utilized for reasoning in automatic text understanding.</Paragraph>
  </Section>
  <Section position="3" start_page="0" end_page="411" type="metho">
    <SectionTitle>
I. INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> The purpose of this paper is to propose a system of mapping classes of syntactic structures as instruments for automatic text understanding. The system consists of a set of verb classes and Jnformatlon on mapping them together with noun phrases, tense and aspect, and \]s supposed to he utilized for inference in automatic text understanding.</Paragraph>
    <Paragraph position="1"> The language used for illustration of the system is Japanese.</Paragraph>
    <Paragraph position="2"> There Is a tendency for non-syntactic analysers and semantic grammars In automatic text understanding. However. this proposal Is motivated by the fact that syntactic structures, once analyzed and classified in terms of semantic relatedness, provide much information for&amp;quot; understanding. This is supported by the fact that human beings use syntactically related sentences when they ask questions about texts.</Paragraph>
    <Paragraph position="3"> The system we are proposing has the following elements:  1) Verb classes.</Paragraph>
    <Paragraph position="4"> 2) Mapping of noun phrases between or among some verb classes.</Paragraph>
    <Paragraph position="5"> 3) Direction of possible infel'ence between the classes with information on  tense and aspect.</Paragraph>
    <Paragraph position="6"> Our experiment, in which subjects are asked to make true-false questions about certain texts, revealed that native speakers think that they understand texts by deducting sentences lexically or semantically related. For instance, a human being relates questions such as 'Did Mary go to a theater?' to a sentence in texts such as 'John took Mary to a theater.' Or, by the same sentence, he understands that 'Mary was in the theater.&amp;quot; II. FEATURES OF THE JAPANESE SYNTAX Features of ,Japanese syntax relevant to the discussion in this paper are presented below.</Paragraph>
    <Paragraph position="7"> The sentence usually ha:# case markings as postpositions to noun phrases. For instance.</Paragraph>
    <Paragraph position="8"> I. John qa Mary D_J_ himitsu o hanashita 'John told a secret to Mary.' In sentence 1. postpositions ga. ni and o indicate nominative, dative alld accusative. respectively.</Paragraph>
    <Paragraph position="9">  However. postposJtions do not unique{y map to deep cases. Take the followitlg sentences for example.</Paragraph>
    <Paragraph position="10">  2. John ~ia_ sanii B i_ itta.</Paragraph>
    <Paragraph position="11"> &amp;quot;John went at :? o'cio(-k.' 3. John w_a Tokyo r!t itta.</Paragraph>
    <Paragraph position="12"> &amp;quot;John ~,~'ellt to Tokyo.&amp;quot; 4. Johr~ w;~ Tokyo ILI :~undeiru.</Paragraph>
    <Paragraph position="13">  'John lives in Tokyo.' Ni in the sentences 2, 3. 4 indicate time. goal and location, respectively. This is due to the verb ca|egory (3 and 41 OF the class of noun phrases (2 and 31 appearing in each sentence.</Paragraph>
    <Paragraph position="14"> Certain mor'phemc classes hide the  casemark ing. e.g.</Paragraph>
    <Paragraph position="15"> 5. John ~Q itta.</Paragraph>
    <Paragraph position="16"> &amp;quot;John also went (y;omewhere).</Paragraph>
    <Paragraph position="17"> 6. Tokyo mo itta.</Paragraph>
    <Paragraph position="18">  'Someone went to Tokyo also.' The mo in sentence 5 and 6 means 'also'. Therefore these sentences are derived from different syntactical constructions, that is. sentences 7 and 8. respectively. 7. John ga itta.</Paragraph>
    <Paragraph position="19"> &amp;quot;John went (somewhere).' 8. Tokyo n__ki itta.</Paragraph>
    <Paragraph position="20"> * Someone went to Tokyo.&amp;quot; Furthermore. as illustrated in sentences 5 through 6, noun phrases ,lay be deleted freely, provided the context gives full information. In sentences 6 and 7. a noun phrase indicating the goal is missing and sentences 6 and 8 lack thal indicating the subject. Finally. there are many pairs of lexicalLy related verbs, tz'ansi t ire and inst\] a~it ire, indicating the :;ame phenomenon differently 9. John ga t,4ary ni hon o m_!seta.</Paragraph>
    <Paragraph position="21"> &amp;quot;,h)hn showed a hook to Mary.</Paragraph>
    <Paragraph position="22"> 10. Mal'y ga hon o !~ita.</Paragraph>
    <Paragraph position="23"> &amp;quot;Uary saw a book.' The two expressions, or viewpoints, on the same phenomenon, that is, 'John showed to Mary a book which she saw.' are related in Japanese by the verb root ~_l.</Paragraph>
    <Paragraph position="24"> The system under consideration utilizes some of the above features (case marking and lexically related verbs) and in turn can be used to ease difficulties of automatic understanding, caused by some other features (case hiding, ambiguious case marking and deletion of noun phrases.) III. VERB CLASS The system is illustrated below with verbs related to the notion of movement. The verb classes in this category are as follows:  (1) Verb class of causality of movementtCM) Examples:tsureteiku 'to take (a person)' tsuretekuru 'to bring (a person)&amp;quot; hakobu 'to carry&amp;quot; yaru 'to give&amp;quot; oshieru &amp;quot;to tell' Verbs of this class indicate that someone causes something or someone moves. How to move varies as seen later.</Paragraph>
    <Paragraph position="25"> (2) Verb class of movement(MV) Examples:iku &amp;quot;to go' kuru 'to come&amp;quot; idousuru &amp;quot;to move&amp;quot; Verbs of this class indicated that something or someone moves from one place to another.</Paragraph>
    <Paragraph position="26"> (3) Verb class of existence(EX)  (4) Verb class of possesslon(PS)  Examples:motsu 'to possess' kau 'to keep' Verbs of this class indicate someone's possession of something or someone. the case slot. As seen below, the difference between yaru, 'to give' and uru, 'to sell' is that the latter has 'money' as instrument, while the former does not. Incidentally, Japanese has a verb yuzuru which can be used whether the instruh~ent Is money or not.</Paragraph>
    <Paragraph position="27"> Notice that the fundamental notion of MOVE here is much wider than the normal meaning of the word 'move'. When someone learns some idea from someone else. it is understood that an abstract notion moves from the former to the latter.</Paragraph>
    <Paragraph position="28"> IV. MAPPING OF SYNTACTIC STRUCTURES Furthermore, verbs of each class differ slightly from each other in semantic structures. But the difference is described as difference in features filling  (ani, anim, h_.gum, abs and Ioc indicate animate, animal human, abstract and location, respectively) Diagram II1: ~erbs and conditions for realization  syntactic _~;tructures of the verb classes disc-usssed above is p\]'esented ill Diagram If.</Paragraph>
    <Paragraph position="29"> Items fill|rig the case slots in the semantic frame, or the nolln phrases in .qtlrf3c(&amp;quot; syntaclic 5~truclHFe.5. have particular conditions depending on individual verbs. Some examples of (-ond i t i pry.; are presented in Diagram III.</Paragraph>
    <Paragraph position="30"> inference would be possible among sentences II through 14 in automatic text understanding. Furthermore. this system can also be utilized in the automatic text understanding by locating missing noun phrases and determining ambiguous grammatical cases in the sentence, finding semantically related sentences between the questions and the text, and gathering the right semantic information.</Paragraph>
    <Paragraph position="31"> By the~ie conditions, the mapping of syntactic structures presented in Diagram II is transformed to that in terms of individual verbs. Furthermore, rules of directions for reasoning presented in Diagram IV connect specific sentences. Take the following sentence for example. Since this system uses information on syntactic structures, it is much simpler in terms of the semantic structures than the Conceptual Dependencey Model, for instance, and the mapping among the sentence patterns semantically related much more explicit.</Paragraph>
    <Paragraph position="32"> II. John ga keiki o r,,lary ni mott ekita. (+ani) (-ani) (+ani} (CV-past) 'John brought a cake for Mary.' has related sentences like the following. 12. Keiki ga r~ary ni itta.</Paragraph>
    <Paragraph position="33"> &amp;quot;A cake went to t,4ary.</Paragraph>
    <Paragraph position="34"> 13. Keiki ga ~,tary {no tokoro) ni aru. &amp;quot;There is a cake at Mary's&amp;quot;</Paragraph>
  </Section>
class="xml-element"></Paper>