The General Architecture of Generation in ACORD

This paper describes the general architecture of generation in the ACORD project. The central module of this architecture is a planning component, which allows to plan single sentences as an answer to a KB query. The planner works for three different languages (English, French and German) and for sentence generators based on two different grammar formalisms (ucG for English and French, Lr'G for German) independent of the particular grammar or grammar formalism. It uses several knowledge sources of the ACORD system to make its decisions. The output of the planner is used for the language specific generators as well as for the update of information needed for pronoun resolution. 1 I n t r o d u c t i o n 'I~he ACOI~D prototype offers an interactive update and query of a knowledge-base (Kn). In the query situation the user asks the KB using natural language and possibly graphical pointing. The final response composed of natural language and also if appropriate, graphical highlighting, is generated with a language specific generator, in the three ACORD languages (English, French and German) using the same grammar formalisms and grammars employed in parsing: ucc for English and French, and LFG for German. The generators are fully described in [9] for the UCG framework, and in [3] and [5] for the LFG framework. The objective of this paper is to describe the modules common to the three languages, which build the semantics of the answer to be generated using the semantics of the question posed to the system, the dialogue history, and the KB answer. 2 T h e S e m a n t i c R e p r e s e n t a t i o n )dost components in the ACORD system share a semantic representation language called [nL (Indexed Language (see [8])). InL is based upon Ramp's Discourse Representation Theory (see [1] and [2]). The generators work on a derived representation called SynInL, which was designed during the project. 2.1 R e s o l u t i o n w i t h i n InL The parsers produce information which allows a central component, the resolver, to determine the possibilities of coreference between anaphoric expressions and their antecedents (see [7]). This additional information is incorporated into an InL expression in the form of occurrence information or lists, stating for every element which may be coreferential with some other element properties relevant for determining coreference. We refer to InL expressions which incorporate such information as unresolved InLs and to lnL expressions where this information has been used to determine coreference (and thereafter removed) as resolved InLs. *The work reported here has been carried out as part of the ESPRIT project P393 ACORD on "The Construction and Interrogation of Knowledge-Bases using Natural Language Text and Graphics". 2.2 T h e p r o b l e m s e n c o u n t e r e d u s i n g InL ibr g e n e r a t i o n Planning and generation operate on a different but derivated semantics formalism called SynInL. Several reasons brought us to design and use SynInL as opposed to InL: First, to work efficiently the ucG generators require that their input be canonical with respect to the respective grammars. Canonicity means that only those InL formulas are treated, which could be produced by the parser, but not all formulas, which are logically equivalent 1. In the context of InL, the notion of canonicity cannot be formalized outside the grammar definition. We then needed a semantic language where canonicity could always be provided, even though an expression was produced without any grammar dependent information. Second, the generator needs NP planning to control the generation of referring expressions (see [6]). In order to specify information about the type of NP to be generated, a representation is required which allows the encoding of syntactic information in addition to semantic information. Furthermore, the individual bits of semantics must be related to the syntactic structure. More generally speaking, we need a mechanism for modifying or structuring the semantic representation to be generated prior to generation. Standard InL, being a purely semantic representation language, is inadequate for encoding this syntactic information. Third, and most importantly, all of this has to be achieved in a language-, grammarand formalismindependent way 2. 3 D e s i g n i n g S y n I n L 3.1 S t a t e of t he a r t There is a main difficulty in the concept of planningbased generation systems which explains the monolithic nature of many systems described in the relevant literature. If a planner plans a particular type of syntactic structure in the absence of grammatical intbrmation, there is no guarantee that the structure specified will actually be accepted by the grammar as being well-formed. There are basicMly two solutions to this problem. One is to simply assume that the planner only specifies structures from which it will be always possible to generate. This works perfectly when there are no interactions between structures specified locally. An example of a grammar formalism with this "locality" property is the context free languages. However, for most modern approaches to grammar (including Government and Binding theory (GB) and all unification-based grammar formalisms), the locality property does not hold. In this case, we have to assume that the grammar is "loose enough" that anything we might plan can in fact be generated despite any interactions. Such a planning could 1To determine whether two syntactically distinct InL expressions are logically equivalent under laws such as commutativity and associativity is factorial in complexity. 2Language independence must be viewed as language independence regarding French, English and German.