<?xml version="1.0" standalone="yes"?>
<Paper uid="E91-1043">
  <Title>A LANGUAGE i BIDIRECTIONAL MODEL FOR NATURAL PROCESSING</Title>
  <Section position="4" start_page="0" end_page="0" type="metho">
    <SectionTitle>
2 INTERLEAVING GENERATION
AND ANALYSIS
</SectionTitle>
    <Paragraph position="0"> The strategy of viewing natural language processing as based on a uniform deduction process has a formal elegance and results in more compact systems. There is one further advantage that is of both theoretical and practical relevance: uniform architectures offer the possibility to view generation and parsing as strongly interleaved tasks. By this I mean</Paragraph>
    <Paragraph position="2"> that during performing one task (e.g., generation) the other one (e.g., analysis) is used for monitoring the former. In principle this results in a bidirectional and incremental flow of information: * During the parse of an utterance the addressee of the utterance can simultaneously start to construct his answer. In doing so, partial results of the parsing process can be used directly during generation (e.g., if a paraphrase will be generated). In such flow of control it will be possible that generation can be used for completing the resulting structure of elliptic, underspecified or ill-formed input during the process of understanding or for generating paraphrases in due time.</Paragraph>
    <Paragraph position="3"> * During generation interleaved parsing could help to avoid the construction of ambiguous utterances. E.g., it is necessary for a natural language help system to generate utterances that reflect exactly the intended meaning (if possible at all) to be sure that the dialog partner will perform the correct operations. For instance, producing the utterance &amp;quot;Remove the folder by means of the system tools&amp;quot; is better than &amp;quot;Remove the folder with the system tools&amp;quot; because for the latter utterance there exists the reading &amp;quot;Remove the folder that contains the system tools&amp;quot;, too.</Paragraph>
    <Paragraph position="4"> Of course, it is also possible to analyse a generated utterance if processes are performing their tasks in an isolated way. 4 In such flow of control the complete istructure has to be generated again if ambiguities are detected that have to be avoided. BeCause the source of an ambiguous utterance is not used directly to guide the generation process it is possible that the newly generated structure is still ambiguous (and it may happen that the same ambiguous structure is generated again).</Paragraph>
    <Paragraph position="5"> This results in inefficient systems because in general the loop between the i isolated processes must be performed several' times.</Paragraph>
    <Paragraph position="6"> The advantage of a uniform architecture is that intermediate results of one direction can  loop' of the HAM-ANS system (see Hoeppner et al. 1983) to determine whether it can be actually uttered elliptic or not.</Paragraph>
    <Paragraph position="7"> immediately be used in the opposite direction to determine the ambiguous information in due time.</Paragraph>
  </Section>
  <Section position="5" start_page="0" end_page="0" type="metho">
    <SectionTitle>
3 BIDIRECTIONALITY SUPPORTS
FLEXIBLE AND EFFICIENT
GENERATION
</SectionTitle>
    <Paragraph position="0"> One of the disadvantages of currently developed generation systems is that they view the structure of linguistic knowledge only statically. If alternatives exist for a particular linguistic expression, decision points are evaluated to determine the appropriate actual utterance. It is necessary to specify corresponding decision points for all possible utterances otherwise the choice must be performed randomly (the determination of the appropriate set of decision points is one of the sources of complexity in existing generation systems). The flexibility of such systems depends directly on the flexibility that is brought into the system via the decision points that are specified by hand during the development of a generation system (i.e. the flexibility is restricted).</Paragraph>
    <Paragraph position="1"> On the other side, in a bidirectional system the resulting structures of the parsing task can be used directly during generation. E.g., in general a set :of alternative lexemes is specified during the process of lexical choice which are synonymous in the actual situation or when the semantic input cannot be sufficiently specified (e!g., in German, some drinkingdevices can be denoted either 'Tasse' (cup) or 'Becher' (mtip) because their shape cannot be interpreted Unequivocally). An appropriate choice would be to use the same lexeme that was previously used by the hearer (if no other information is available). In principle this is also possible for the choice between alternative syntactic structures.</Paragraph>
    <Paragraph position="2"> This means that uniform architectures offer the possibility to model the assumption that during communication the use of language of one interlocutor is influenced by means of the language use of the others. This adaptability to the use of language of partners in communication is one of the sources for the fact that the global generation process of humans is flexible and efficient. Of course, adaptability is also a kind of co-operative behaviour. This is necessary if new ideas have to be expressed for which no mutually known linguistic terms exist (e.g., during communication between experts and novices).</Paragraph>
    <Paragraph position="3"> In this case adaptability to the use of language  of the hearer is necessary in order to make possible that the hearer will be able to understand the new information.</Paragraph>
    <Paragraph position="4"> I do not want to argue that all choices are determined by means of language use of others. But, when structures that are determined during analysis are considered during generation, the number of decision points or parameters which have to be specified during the development of a generation system is reduced. This leads to more flexibility: not all necessary parameters need to be specified in the input of a generator because decision points can also be set dynamically during run-time.</Paragraph>
    <Paragraph position="5"> This dynamic behaviour of a generation system will increase efficiency, too. As McDonald et al. (1987) define, one generator design is more efficient than another, if it is able to solve the same problem with fewer steps. They argue that &amp;quot;the key element governing the difficulty of utterance production is the degree of familiarity with the situation&amp;quot;. The efficiency of the generation process depends on the competence and experience one has acquired for a particular situation. In such situations the generation process performs its task by using compiled knowledge and preferences.</Paragraph>
    <Paragraph position="6"> Currently, it is a great problem how compiled knowledge is acquired dynamically and how it is activated in particular situations. But a uniform architecture as proposed in this paper seems to be a promising basis for designing such a system, because the structures determined during analysislcould be used for restricting the potential search space.</Paragraph>
  </Section>
  <Section position="6" start_page="0" end_page="0" type="metho">
    <SectionTitle>
4 AN OUTLINE OF A
BIDIRECTIONAL ARCHITECTURE
</SectionTitle>
    <Paragraph position="0"> If both aspects - interleaving parsing and generation and using the language use of interlocutors as additional criterion for the structure of linguistic knowledge - are realized within a uniform architecture thenthis will increase flexibility and efficiency in natural language processing. E.g., when starting the generation from a :logical form, the grammatical process is able to ::call the conceptual module's attention if a subphrase causes ambiguity. Thus it is not necessary that the conceptual module has detailed information about the grammar.</Paragraph>
    <Paragraph position="1"> The flow of control within a system based on an interleaved approach is bidirectional.</Paragraph>
    <Paragraph position="2"> E.g., during the generation of an utterance partial structures are analysed to avoid unnecessary ambiguities. The bidirectional flow of control supports incremental processing: it is possible to start processing of partial structures before the whole structure is known. In Finkler and Neumann (1989) and Neumann and Finkler (1990) we have already described an implemented generation system (named POPEL-HOW) that realizes an incremental and bidirectional flow of control based on a uniform parallel processing model.</Paragraph>
    <Paragraph position="3"> The incremental and bidirectional flow of control has two main advantages during generation. Firstly, the determination of contents can be done on the basis of conceptual considerations only, because POPEL-HOW is flexible enough to handle underspecified input. Secondly, the conceptualizer has to regard feedback from POPEL-HOW during the computation of the further selection process. This means, an incremental system like POPEL can model the influence of linguistic restrictions on the process that determines what to say next.</Paragraph>
    <Paragraph position="4"> Underspecified structures are analysed in POPEL-HOW at each level of description by means of declarative described mapping rules.</Paragraph>
    <Paragraph position="5"> The analysis of such structures is performed with generation specific operations. If the system would be based on a uniform architecture then such specific operations are no more necessary.</Paragraph>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
4.1 BiLD - A MODEL FOR
</SectionTitle>
      <Paragraph position="0"/>
    </Section>
  </Section>
  <Section position="7" start_page="0" end_page="0" type="metho">
    <SectionTitle>
BIDRECTIONAL LINGUISTIC
DEDUCTION
</SectionTitle>
    <Paragraph position="0"> At the University of Saarbriicken a project called BiLD is now being started where it will be investigated how interleaving of parsing and generation can be efficiently performed and how such a model can be used for increasing flexibility and efficiency during natural language processing. Fig. 1 (next page) shows the schematic structure of its architecture.</Paragraph>
    <Paragraph position="1"> The core of the system is a uniform parametrized deduction process. The main task for the process in both directions is the determination of the corresponding syntactic informationi'that functions as an interface between graphematic and semantic information (a formalism based on Head-driven Phrase Structure Grammar (Pollard and Sag 1987) will be used).</Paragraph>
    <Paragraph position="2">  The task of the deduction process during generation is to construct the graphematic form of a specified semantical feature description. 5 For example, to yield the utterance &amp;quot;A man sings&amp;quot; the deduction process gets as input the semantic feature structure</Paragraph>
    <Paragraph position="4"> and deduces the graphematic structure \[graph : (A_man_sings.) \] by means of successive application of lexical and grammatical information. In the same way the deduction process computes from the graphematic structure an appropriate :semantic structure in parsing direction.</Paragraph>
    <Paragraph position="5"> The author has now started to develop and implement a first version of a prototype of a uniform algorithm for HPSG. The main idea 6 is that the approach is head-driven in both directions. In the first phase of the algorithm the maximal projection for all head elements are computed (or predicted) bottom-up.</Paragraph>
    <Paragraph position="6"> Phrases are then combined top-down. The completion step is controlled by syntactic and semantic information inherited from lexical heads and by the principles of HPSG.</Paragraph>
    <Paragraph position="7">  head-driven parser of Proudian and Pollard (1985). Because heads are processed first the completion of structures must be performed in left as well as in right direction.</Paragraph>
    <Paragraph position="8"> The approach supports the ID/LP format of rules. But it is an open question whether linear precendence can be processed in the same way for generation and parsing. The problem is that during parsing the task of LP rules is to filter out ungrammatical structures. During generation the task of LP rules can be seen as an ordering criterion. But in this case the problem of choice between paraphrases emerges. In POPEL-HOW it is assumed that the order of activation of concepts (which is determined using pragmatical knowledge) should be maintained if it is syntactically wellformed; otherwise the segments are reordered. Whether such viewpoint is acceptable for generation in general is still open.</Paragraph>
  </Section>
  <Section position="8" start_page="0" end_page="0" type="metho">
    <SectionTitle>
4.2 ASPECTS OF CONTROL
STRUCTURE
</SectionTitle>
    <Paragraph position="0"> A major aspect of the BiLD project is that specific parametrization of the deduction process is represented in the lexicon as well as in the grammar to obtain efficient structures of control (Uszkoreit 1991). The main idea is that preference values are assigned to the elements (disjuncts or conjuncts) of feature descriptions. For example, in HPSG all lexical entries are put together into one large disjunctive form. From a purely declarative point of view these elements are unordered.</Paragraph>
    <Paragraph position="1"> But a preference structure is usrd during processing in order to guide the process of lexical choice efficiently which itself influences the grammatical process.</Paragraph>
    <Paragraph position="2"> To support flexibility and efficiency (in the way described in section 3) the language use of interlocutors will be considered to influence the preference values. For example, the frequency of access of a lexeme will increase its preference value. In a uniform lexicon it is no matter whether the lexeme was accessed during parsing or generation. But this means that the use of particular linguistic elements of the interlocutor influences the choice of lexical material during generation.</Paragraph>
  </Section>
class="xml-element"></Paper>