<?xml version="1.0" standalone="yes"?>
<Paper uid="C80-1004">
  <Title>SGS: A SYSTEM FOR MECHANICAL GENERATION OF JAPANESE SENTENCES</Title>
  <Section position="2" start_page="22" end_page="22" type="metho">
    <SectionTitle>
KAKI-WO TABE-TA TOKI KANE-GA NAT-TA.
</SectionTitle>
    <Paragraph position="0"> (a persimmon) (ate) (a bell) (rang) When I ate a persimmon, a bell rang.</Paragraph>
    <Paragraph position="1"> According to the principle, TA of TABE-TA assures that eating-a-persimmon preceds bellringing. But, unfortunately, such is not the case. The fact implied by the sentence is the simultaneity of eating-a-persimmon and bell-ringing.</Paragraph>
    <Paragraph position="2"> Such an exception may be ascribed to the peculiarity of the conjunctive TOKI. Since TOKI is also a noun and means time. TOKI used as a conjunctive is apt to connote 'at the itme when'. Exceptions to tense interpreation seem to depend on the conjunctive in the case of an adverbial clause, or the head noun in the case of a relative clause. Therefore case studies of tense interpretation are needed.</Paragraph>
    <Paragraph position="3"> Tense interpretation of the sentence type SI-- conj --$2 concerning Japanese tense conjunctives rOKI(when), MAE(before), ATe(after) is summarized in Fig. 6.</Paragraph>
    <Paragraph position="4"> S1 is a subordinate clause. $2 is a main clause. The aspect feature +-stative is a feature belonging to the predicate of $2. 'applicable' means that the principle is applicable. 'simultaneous' means that the tense interpretiation is exceptional and the simultaneity of the events refered to by S1 and 82. In the case of relative clauses, a tense interpretation table like the above can be similarly constructed, but the situation is worse in the case of adverbial clauses. There ....... at&amp;quot; ..................................... I S2 I interpretation</Paragraph>
    <Paragraph position="6"> also exsist complex sentences requiring tense interpretation opposite to the principle.</Paragraph>
    <Paragraph position="8"> The cake that TAROU ate was made by HANAKO.</Paragraph>
    <Paragraph position="9"> The main clauses is HANAKO-GA TUKUT-TA (HANAKO made a cake). The relative clause is TAROU-GA TABE-TA(TAROU ate the cake). Both clauses include TA, so the prediction by the principle is that the event TAROU-GA TABE-TA preceds the event HANAKO-GA TUKUT-TA, which is exactly opposite to usual tense interpretation.</Paragraph>
    <Paragraph position="10"> Because of these difficulties, SGS did not go far with respect to aspect and tense interpretation. Obviously further investigation from a linguistic point of view is needed for mechanical aspect-tense interpretation.</Paragraph>
    <Section position="1" start_page="22" end_page="22" type="sub_section">
      <SectionTitle>
Generation Examples
Relative Clause
</SectionTitle>
      <Paragraph position="0"> There are two types of relative clause.</Paragraph>
      <Paragraph position="1"> One is the TAROU-GA TABE-TA KEIKI(the cake which TAROU ate) type. The other is the TAROU-GA KEIKI-WO TABE-TA ZIZITU(the fact that TAROU ate a cake) type.</Paragraph>
      <Paragraph position="2"> The example shown is the former type.</Paragraph>
      <Paragraph position="3"> Meaning structures consist of two propositional frames P0000Ol and P000002. Note that they have a common filler (NO00002.1TA).</Paragraph>
      <Paragraph position="4"> Initially specified are the top category SS, the arrangement of propositional phrases-first THEME then LOCUS, and the surface subject --THEME. These inputs are goals saying &amp;quot;generate a sentence from the frames shown in figure 7. As to the sentence, its category must be SS(simple sentence), its surface subject must be THEME--ITA(a board), and THEME must be to the left of LOCUS&amp;quot;.</Paragraph>
      <Paragraph position="5"> On receiving these inputs, the system starts rule invocations. The invoked rule  selects a frame suitable for a main clause.</Paragraph>
      <Paragraph position="6"> Priority of the selection is given to the frame which includes a REL-TM(relative time) slot filled with &amp;quot;HATUWA&amp;quot;(speech time). In this example, P000001 is selected. It states that</Paragraph>
    </Section>
  </Section>
  <Section position="3" start_page="22" end_page="22" type="metho">
    <SectionTitle>
TAROU-GA ITA-WO TATEKAKE-RU(TAROU leaned a board
</SectionTitle>
    <Paragraph position="0"> somewhere). P000001 being selected, the system continues invoking rules in order to translate P000001 into a main clause.</Paragraph>
    <Paragraph position="1"> During the course of rule invocations, the generation process reaches the stage where the THEME slot is treated. Because the THEME slot and its filler--(NO00002.ITA), are always supposed to correspond to a noun phrase, rules of the form &lt;NP&gt;~&gt;... are invoked one by one.</Paragraph>
    <Paragraph position="2"> As (N000002/ITA) is shared with another frame, P000002, which states that HANAKO-GA ITA-WO OI-TA(HANAKO put a board), &lt;NP&gt;-~&lt;SS&gt;&lt;NP&gt;, a rule for a relative clause, eventually is invoked. It produces a relative clause--HANAKO- null somewhere). It first builds a tree for the sentence HANAKO-GA ITA-WO OI-TA from P000002 and completes the realtive clause by moving the position of ITA to the end of the sentence.</Paragraph>
    <Paragraph position="3"> Generally speaking, complex noun phrase restrictions should be considered, but they do not work here. After the completion of the relative clause concerning (N000002.ITA) with a corresponding derivation tree, SGS tries to complete the main clause, but, since the rule invoked for the main clause allows only CACT--TAROU as a surface subject, it can not satisfy one of the initial goals (S-SUBJ = THEME). So backtrack occurs.</Paragraph>
    <Paragraph position="4"> Finally, the alternative rule &lt;SK&gt;=&gt;&lt;SK&gt;&lt;RAREi&gt; is invoked. It generates a passive sentence whose subject is THEME--ITA, and the rest of the specifications are also satisfied. '-*-' in the derivation tree indicates a non-exsistent filler of the obligatory case in the given frame.</Paragraph>
    <Paragraph position="5"> A passive sentence treated by SGS is 'a pure passive sentence' which does have a counter part in English. There is also another type called 'an adversitive passive sentence'.</Paragraph>
    <Paragraph position="6"> This type is too subtle to treat mechanically. Therefore we consider only pure passive sentence and the rules for them.</Paragraph>
    <Section position="1" start_page="22" end_page="22" type="sub_section">
      <SectionTitle>
Causative Passive Sentence
</SectionTitle>
      <Paragraph position="0"> Japanese causative sentences, which are identified by the occurence of VERB + SERU.</Paragraph>
      <Paragraph position="1"> SASERU, often admit two types of interpretation. Consider the next sentence.</Paragraph>
      <Paragraph position="3"> CACT ....... THEME .................. SK ............... SASE-WO .I ) J ) I I I i I I THEME ..... LOCUS ...... VERB I I 1 1 I I t ' MP .... PPK MP---PPK HP---PPK NP--PPK I I I I t I I I I I I ~ ' NOUN L NOUN t NOUN ~ NOUN I I I I t I I I ~ I I I -%- HIYORI HAHAKO GA HASIGO WO -%- HI TATEKAKE-RU 5ASE-WO RARE% TA OUT-PUT- HANAKOGA HASIGOWO TATEKAKESASERARETA</Paragraph>
    </Section>
  </Section>
  <Section position="4" start_page="22" end_page="22" type="metho">
    <SectionTitle>
\[HASIGO TATEKAKE-RU\]
</SectionTitle>
    <Paragraph position="0"> TA\]. The symbol -*means non-exsistent filler.</Paragraph>
    <Paragraph position="1"> Owing to this structure, a passive sentence whose subject is THEME--HANAKO can be derived and (S-SUBJ is satisfied.</Paragraph>
    <Paragraph position="2"> One interpretation is that TAROU forces HANAKO to go. The other is that TAROU permits HANAKO to go. Ambiguities can be resolved by adverbials or context. These ambiguities bring difficulties to the treatment of causative sentences, but, for simplicity, SGS deals with only the former type.</Paragraph>
    <Paragraph position="3"> The example above is a causative-passive sentence. User's specifications are of the category SS and (S-SUBJ = THEME). The initial meaning structures consist of two propositional frames. The generation process begins by choosing a HATUWA frame to serve as an orign of time relations in the given frames. The chosen frame, P000067, includes a predicate slot containing SASERU. It will produce a causative sentence.</Paragraph>
    <Paragraph position="4"> While SASERU is a causative particle, it behaves as a verb in the deep level. It is a verb which takes a sentencial object whose case is THEME. Therefore the invoked rule responsible for completing a causative sentence searches for a sentencial object. P000068 is the frame for a sentencial object. It states:  intelligent system, such as a consultant system or a Q.A. system, e.t.c.. SGS, though it is far from being satisfactory, is one step closer to an intelligent sentence generation system. The next step should be manifold. SGS admits various improvements.</Paragraph>
    <Paragraph position="5"> During the generation process, diverse messages are exchanged between invoked rules so that messages tend to get out of control. Greater regulation is needed.</Paragraph>
    <Paragraph position="6"> As for the dictionary, it would be interesting to incorporate 'lexical decomposition'. Introducing 'lexical decomposition' can be helpful in organizing lexical items in a dictionary. However it requires a more refined method of lexical insertion. Linguistic knowledge should be thoroughly investigated and digested. Though the aspect-tense system in Japanese has been investigated to some extent, it is not obvious whether the description of aspect-tense system by features is sufficient to represent temporal knowledge. Presently, SGS lacks the ability to continuously produce sentences. In order to form a paragraph the problem of coreference mechanism  --2?-must be solved. Japanese is so rich in ellipsis it is necessary to reveral and implement the ellipsis system.</Paragraph>
    <Paragraph position="7"> ACKNOWLEDGEMENT: The auther is grateful to Mr. Tanaka, Chief of Machine Inference Section of Electrotechnical Laboratory and, other members of the section, for helpful discussions.</Paragraph>
  </Section>
class="xml-element"></Paper>