<?xml version="1.0" standalone="yes"?>
<Paper uid="E99-1037">
  <Title>Dialogue Processing in a CALL-System</Title>
  <Section position="3" start_page="253" end_page="254" type="metho">
    <SectionTitle>
2 Discourse Grammars
</SectionTitle>
    <Paragraph position="0"> One way of realizing such dialogues is to develop discourse grammars which describe the steps through distinct parts of dialogues. This possibility is chosen in the present concept, since it enables the learner to lead written, situation-based dialogues almost as in the class-room situation.</Paragraph>
    <Paragraph position="1"> The advantage of a discourse grammar over a completely plan-based dialogue structure is the seperate representation of possible moves ('dialogue acts' in Alexandersson et al. (1994)) and the content of the discourse. The discourse grammar of an 'information-gathering' dialogue can be used while reporting an accident as well as while ordering a pizza. In the first case the police officer wants to know all about the accident and possible casualties and in the latter case the pizza delivery wants to know the toppings and size of the pizza. On the other hand guidance is needed for the learner in the CALL-scenario. Systems like the one described in Carberry (1990) are much too open to be used for language learning. The system would not be able to give any feedback to the learner in case of erroneous input. Therefore the system uses only restricted knowledge about what types of input to expect and how to react to them since the general intentions of the learner are known to the system through the situation presented to the learner. In other NLP-based systems like 'Herr Kommissar' (deSmedt, 1995) and 'LINGO' (Murray, 1995), the dialogue with the system either allows only single question-answer exchanges or is strongly embedded into the respective scenario. In the first case the structure of a complete dialogue does not become clear to the learner and the initiative is with the learner who might not know what to do. In the second case it is difficult to include new scenarios since not only the content of the new dialogue has to be coded but also the various dialogue structures.</Paragraph>
    <Paragraph position="2"> Moreover the design of a system might not allow for different types of dialogues: The dialogue component contains two main knowledge bases: The first one contains the discourse grammars, which structure so-called 'goal-driven dialogues' or 'task-oriented dialogues'. I The idea of discourse grammars as a means to handle dialogue situations is for instance presented in Fawcett and Taylor (1989). The second knowledge base contains knowledge about the content of the dialogue itself. This data is used to infer a mean1 For a discussion about discourse grammars in general see e.g. Taylor et al. (1989).</Paragraph>
    <Paragraph position="3"> ingful reaction to the input sentence. Additionally this base contains slots in which the information given by the learner is stored.</Paragraph>
    <Paragraph position="4"> The following figure shows a simplified part of a discourse grammar, which models an information gathering dialogue such as is necessary in the case of collecting information about an accident. Additional items of discourse grammars are of course needed, for example, to start and end a telephone call, etc.</Paragraph>
    <Paragraph position="5"> The same type of structures is also used in the analysis of dialogues, e.g. (Carletta et al., 1997). Here dialogues are analysed with the help of a 'Dialogue Structure Coding Scheme', which in particular contains only a limited number of possible moves between dialogue partners. A similar analysis was done in the preparational phase of the Verbmobil project (Alexandersson et al., 1994). In a dialogue system where the intentions of the dialogue partners are known and the fixed structures serve to assess the performance of the language learner, the restrictions will probably not make the overall behaviour of the system worse than more flexible dialogue systems.</Paragraph>
    <Paragraph position="6">  The dialogue module uses a surrounding discourse grammar, which includes the grammar parts for starting and ending a telephone call etc.</Paragraph>
    <Paragraph position="7"> From here the information gathering structure is called to try to fill the variables in the dialogue knowledge base (see below) by asking the learner a question. This process is continued as long as there are open questions (open questions) or until the learner does not provide interpretable input even after a repeated question (INQUIRE THANK.END). null The dialogue knowledge base contains the data  necessary to lead a dialogue with a certain content. The data is organized in a hierarchical structure. In the 'police call' example the root-node consists of a slot with a first reaction of the officer (greeting) to be presented to the learner. The daughter nodes (e.g. accident, theft) contain some slots which are used for the actual presentation of reactions on the screen or for information storage and retrieval. Some slots are: - question for pieces of information: This includes canned text, which is presented to the learner. For example the police officer might ask 'Are there any injured people?'.</Paragraph>
    <Paragraph position="8"> - information about expected answer: The semantic structure of the learner's input is checked against the content of this slot and in case of variables it is stored.</Paragraph>
    <Paragraph position="9"> - keywords to match the learner's input: In case the parser was not able to produce a semantic representation, the system retreats to keyword matching in order to provide at least some reaction. null - text as answer: A sentence is passed to the learner to acknowledge or confirm the processing of the input ('So, there has been an accident.'}.</Paragraph>
    <Paragraph position="10"> In case the system chooses to ask a question based on the discourse grammar, the question from the appropriate slot in a daughter node (topdown left-right) is passed to the learner. After the grammatical processing of the answer, the content is checked against the expected one. If they match, a confirmation may be passed to the learner and the next step in the discourse grammar is taken. If the answer was considered not appropriate for the question the system tries to find a response in a hierarchy of steps from world knowledge checking to simple keyword analysis.</Paragraph>
    <Paragraph position="11"> The final output can thus be from the same node, a subnode or from a more general independent source of possible reactions. Some mechanism has to manage the matching-procedure of the sentence. Possible mechanisms thus include:  - the content matches completely: The system was able to recognize the input sentence as some meaningful reaction to the previous question or statement.</Paragraph>
    <Paragraph position="12"> - the content fits only partly (too general): There are subnodes which inelude variables for more specific information. null - the content fits only partly (only one aspect}: A general keyword-based mechanism recognizes only parts of the expected input. If possible the  learner is asked for further clarification. null the content does not fit: A question for rephrasal will be displayed to the learner. Additionally the learner might consult a helpfile with information about how to proceed in the current situation.</Paragraph>
    <Paragraph position="13"> A difficulty that might arise is the change of control (or initiative) between the dialogue partnets. Allowing the learner to take the initiative has several consequences, which are difficult to realize. In contrast to the present concept the dialogue module should include a language generation device to generate natural language output to database-inquiries. From this follows that the dialogue knowledge base should not contain any contradictions etc. to allow for easy inference of possible answers to the input question. Finally in case the learner keeps on asking questions the system might fail to continue the dialogue in a meaningful way. Thus a system designed for the use by pupils must be rigid enough to deal with this kind of input.</Paragraph>
    <Paragraph position="14"> The seemingly limited flexibility in this system is not really a disadvantage, because 1) the learner is suppose d to act in a foreseeable way and 2) the system should give feedback in case of deviating action. Especially the latter seems only possible if a discourse grammar structures the moves which dialogue partners might take.</Paragraph>
  </Section>
  <Section position="4" start_page="254" end_page="255" type="metho">
    <SectionTitle>
3 System Overview
</SectionTitle>
    <Paragraph position="0"> The idea behind the system is to extend the types of training which the student gets in a class room setting into a computer. One important kind of training is the practising of dialogues. Therefore the program realizes small written dialogues for the learner to train her/his 'communicative competence', as explained above.</Paragraph>
    <Paragraph position="1"> The system consists of four main modules. The dialogue control module mainly functions as an interface. It organizes the flow of the input data between the user-interface and the various processing modules. Every input sentence is first passed to the linguistic module, which checks it for orthographic and syntactic errors. The orthographic check is done in the spirit of Oflazer (1996). With  Proceedings of EACL '99 the help of a finite state recognizer mildly deviating strings are identified and correct versions are presented to the learner if necessary. The syntactic check follows a rather traditional path. The main work is done by a LFG-parser (Bresnan and Kaplan, 1982), originally implemented by Avery Andrews (Australian National University) and now modified to suit the needs of error detection with the help of modified grammar processing including error rules (Kriiger et al., 1997). As a next step the analysis of the sentence is checked against a world knowledge base, from which feed-back follows to the learner if the sentence does not match the internal model of the world. In contrast to the dialogue knowledge base this model of the world cannot be altered by the learner because of its usage for inference and the absence of a consistency-checking module to prevent contradictions etc. If the student has made an error, the system provides feedback to support the learner in typing a syntactically correct or semantically more plausible sentence. After this step the dialogue component tries to find a reaction to continue the dialogue, as described above.</Paragraph>
    <Paragraph position="2"> The main focus in all the analyses is to continue the dialogue but without ignoring the errors made by the learner. Only the orthographic check will actually interrupt the dialogue with a suggestion of correct words for the misspelled items. In all other cases the dialogue partner will react to the erroneous input depending on the type of error.</Paragraph>
  </Section>
class="xml-element"></Paper>