File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/metho/90/c90-3082_metho.xml
Size: 18,066 bytes
Last Modified: 2025-10-06 14:12:30
<?xml version="1.0" standalone="yes"?> <Paper uid="C90-3082"> <Title>The General Architecture of Generation in ACORD*</Title> <Section position="3" start_page="0" end_page="0" type="metho"> <SectionTitle> 2 The Semantic Representation </SectionTitle> <Paragraph position="0"> )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.</Paragraph> <Section position="1" start_page="0" end_page="0" type="sub_section"> <SectionTitle> 2.1 Resolution within InL </SectionTitle> <Paragraph position="0"> 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.</Paragraph> <Paragraph position="1"> *The work reported here has been carried out as part of the ESPRIT project P393 ACORD on &quot;The Construction and Interrogation of Knowledge-Bases using Natural Language Text and Graphics&quot;.</Paragraph> </Section> <Section position="2" start_page="0" end_page="0" type="sub_section"> <SectionTitle> 2.2 The problems encountered using InL ibr </SectionTitle> <Paragraph position="0"> generation 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.</Paragraph> <Paragraph position="1"> 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.</Paragraph> <Paragraph position="2"> Third, and most importantly, all of this has to be achieved in a language-, grammar- and formalismindependent way 2.</Paragraph> </Section> </Section> <Section position="4" start_page="0" end_page="388" type="metho"> <SectionTitle> 3 Designing SynInL </SectionTitle> <Paragraph position="0"/> <Section position="1" start_page="0" end_page="388" type="sub_section"> <SectionTitle> 3.1 State of the art </SectionTitle> <Paragraph position="0"> There is a main difficulty in the concept of planning-based 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.</Paragraph> <Paragraph position="1"> 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 &quot;locality&quot; 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 &quot;loose enough&quot; 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.</Paragraph> <Paragraph position="2"> be done deterministically. Itowever, using ~his al,proach such a planner would always run the risk that it would fail to geuerMe due to inconsistencies with the grammar.</Paragraph> <Paragraph position="3"> '\]'he second solution is to interle~rve planning and gener ation and allow the possibility that failure to generMe, results in different planning choices. Snch systems also exist, although they seem to be comparatively recent in the literature. We (lid not investigate this possibility since it requires a fairly tight integration of planner and (grammar and formalism specific) generator which scems inconsistent with our requirement th~tt we generate with three languages and two grammar formalisms.</Paragraph> </Section> <Section position="2" start_page="388" end_page="388" type="sub_section"> <SectionTitle> 3.2 Description of our aI)I)roach </SectionTitle> <Paragraph position="0"> Our solution is to attempt an independent level of syntactic representation which abstracts away from the peculiarities of the surface syntactic structures of particular languages and deals directly with syntactic notions which are language~indcpendcnt. Whether one thinks that this is possible, depends to a large degree on one's particular theoretical perspective.</Paragraph> <Paragraph position="1"> What might sucl, an &quot;abstract&quot; syntactic representation look like'.&quot; There are several related concepls in diterse linguistic theories which salisfy the criteria. The most directly related concept is lhat of l)-struelure in (~1~. l)-strncture is a lew~l of syntactic struct.ure which mirrors semantic funcl.or-argun~e~lt strnctnre directly (via the 0.-eril.erion and lhe l)rojeclion Principle) and which is also relaled io surface syntactic structure 1)y the rule of M,,,,e-a, a lransformation that nloves COll!:liluenls fronl oue position Io anolher, l~elaled IlOiiOlls of sirltctnl'o which Captllre the relation belwc(,n Selllal/l ic funtl.or-argllillellt slrncture (or predicate-arglmlent sirueture) and &quot;abstract&quot; or &quot;deep&quot; syntactic sirnclnre are tile f-s|rllcl/Ircs of LI.'C, and the. grammalical funclion hierarchy-based accounls of subcategorisalion in ltPSG and t'CG. All of lhese have the desiraMe pfoperiy that i.}ley express a level of representation which relate subeategorisatJ(qt, s(:ilianties and snrfac(! slruelllr('..</Paragraph> <Paragraph position="2"> Ply using such represenlations whic'h arc hypothesized lo be 'qinguislically .niversat&quot; t()ass()ciate parlial seman!ic representations wilh abstract syntaclic constituents, we also solve t}|e ol, ller requirements mentioned above.</Paragraph> <Paragraph position="3"> \[:'irst, most instances of noncanonicity are elimina.ted be<ause sul)-formulas are associated direetly with syntactic constiiuents..Second, quantifier scope readings are eliminated fi'om consMeration at this level of representation.</Paragraph> <Paragraph position="4"> 'Fhird, since the level of representation is taken to be ltniversal, the,'e are language-dependent maps from the represerttation to surface syntactic structure.</Paragraph> </Section> <Section position="3" start_page="388" end_page="388" type="sub_section"> <SectionTitle> 3.3 SyIllnI, description </SectionTitle> <Paragraph position="0"> '\['lie al)|)l'Oac\]l Lakell \]lcre is to encode synla<:tic strnc- |ure in ierm.,; of sc:hematie X theory familiar fl'om mosl luodern generative gra.lnlllar fOI'H|&\]iSIlIS. As mentioned above, this is most similar to D-structure i, cm t\]mory.</Paragraph> <Paragraph position="1"> ~:;ynlnL expresses both syntactic and semantic inibrma-I ion.</Paragraph> <Paragraph position="2"> Idealizing considerably, SynlnL formulas consist of four types: heads, complements, modifiers and specifiers. This corresponds directly to the stamtard constituent types in theory. (We follow LI.'C/; f-structure and UCG subcategorisation structnre in treMing subjects as ordinary com-I,lements raLher l\],an spe(:ifiers of clauses). These four (alegories are Meal for attaining a level of languagei,del)cndence in liiIgnistie description and are general (:,tough lhat it is reasonable to expect that such X repre-s(mtations cant be mapped onto lallgl;age-depcn(lent sux'face syllla(:Iic slrllCl.llres.</Paragraph> <Paragraph position="3"> The idea then is Io encode this )( struct,lre in Synlttl, formulas. SpeciJiers in Synlnl, are of tile general Ibrm: specifier (Semantics, tfead) \]'hat is, they specify their own semantics and the properties of their head.</Paragraph> <Paragraph position="4"> Heads are of the general form: head(Semantics, /trgList, hdjunc'tList) That is, they specify their own head semantics and a lisI of arguments and adjuncts which are also either specifier or head structures.</Paragraph> <Paragraph position="5"> All of these struclures also allow the encoding of syntactic requirements on arguments and adjnncts. IIowever, there is no indication of either surface syntactic order of the complements and adjuncts or of the relative scope of quantitiers occurring in either complements or modifiers. Tile language generators are free to realize both scope and surface syntactic structure in any way which is consistent with the SynlnL specification.</Paragraph> <Paragraph position="6"> ttow is this augmented representation built ? The parsers produce nnresolved lnL. This InL contains enm~gh syntactic infm'mation for a uniqne mapping into an equivalent SynlnL expression. This mapping is done by the InL -~ SynlnL module.</Paragraph> <Paragraph position="7"> C, iven av Inl, expression, it distinguishes between struclural and prime predicales. For prime predicates there is ahva.ys a real)ping into a SynlnI, formula with a unique category. The structural predicates then determine how to merge the Synlnl, formnlas which replace the origil!:d parlial InL expfession.</Paragraph> </Section> </Section> <Section position="5" start_page="388" end_page="389" type="metho"> <SectionTitle> 4 The Phmning Component </SectionTitle> <Paragraph position="0"> 'Fhe role of the planning component is to produce SynInL expressions from which phrases can be generated by lhe langnage specilic generators and lo decide whether any objects on the screen have to be highlighled.</Paragraph> <Paragraph position="1"> \Vithin ACOIlD, the planner gets as input lhe Synlnb expression corresponding to the user question (yes/no rifles tion, wh-queslion or 'how mnch'/'how many'-question) and the KB answer, q'he planner output consists of an optional canned texl marker and the Synl. L of the answer Io be generated.</Paragraph> <Paragraph position="2"> The planner uses three snb-planners i'or planning verb phrases, NPs and modificalions.</Paragraph> <Section position="1" start_page="388" end_page="389" type="sub_section"> <SectionTitle> 4.1 Architecture of the generator </SectionTitle> <Paragraph position="0"> The answer process consists of the following steps: e The question is parsed. The output is the InL representa.tion of the question with informalion for resol, tion.</Paragraph> <Paragraph position="1"> * This InL expressiof is transformed into SynlnL by the Ill l, --~ SynlnL module a.nd also resoh, cd using the occurrence inh)rmation by the resolver. The resolver provides the generator with information which encodes the user's qnestion as vnderstood by Ihe system.</Paragraph> <Paragraph position="2"> (r) The resolved lnL is passed on to tile KB which provides the KB answer.</Paragraph> <Paragraph position="3"> , The planner module takes as input the SynlnL expression of the query and the KB answer. Depending on the. type of questions asked, the planner makes decisions such as: what kind of canned text prefix is needed, what type of NP planning is necessary, what ldnd of answer is expected and what type of processing ca.n be done on lids answer. It calls the NP sub-planner in order to process all the NPs appearing i~ the queslion, as well as the \[~I~ answer which is trans\[brmed into an appropriate Syn\[n L cx pression (generally an N 1'). 'l'he ou \[pHt of the planner is a SynlnL representation of the answer.</Paragraph> <Paragraph position="4"> * The SynInL answer is the input to the language specific generator of the current language. The selected generator produces the final answer.</Paragraph> <Paragraph position="5"> 4,2 Planning the Structure of Verb Phrases Within the ACOIID lexicon, verbal predicates may only take arguments which refer to objects. This means that we do not do any planning for arguments which denote events or states, i.e., verbal or sentential complements. Consequently we only distinguish between two types of predicates: the copula, which only takes a subject and a noun phrase or PPS as complement, and all other verbs. Other active verb forms take either one, two, or three arguments. The first argument always corresponds to the subject (in an active clause), the second to the object or a prepositional complement, and the third to the second object or a prepositional complement.</Paragraph> <Paragraph position="6"> Given ~ list of arguments, the verb planner calls the NP planner on each argument, providing information relative to the function of the argument position under scrutiny, its posilion in the argument list, and the subject of the sentence in which the argument occurs.</Paragraph> <Paragraph position="7"> '\]?he list of modifications of the original query (if any) is processed last. For each element of this list a call to the modification sub-planner is made.</Paragraph> </Section> <Section position="2" start_page="389" end_page="389" type="sub_section"> <SectionTitle> 4.a Planning Noun Phrases </SectionTitle> <Paragraph position="0"> The planning component is responsible for providing the best expression for Nes. It nses the dialogue history as well as I,:B knowledge to decide whether to adopt a pronominalization strategy, or find a non-pronominal description for the NP under analysis.</Paragraph> <Paragraph position="1"> The NP planner must be provided with enough information to decide whether and which kind of pronominalization is allowed, and whether a name coukl be used instead of a pronoun where such an option is available.</Paragraph> <Paragraph position="2"> It mnst also decide when to use demonstratives, definite or indefinite articles, and whether a complex description shonh\[ include relative clauses and adjuncts. In addition, our planner has to decide which objects should be highlighted on the screen.</Paragraph> <Paragraph position="3"> 'l~o do so, the NP planner needs a fully specified discourse referent and information about the syntactic environment of the NP to be produced.</Paragraph> <Paragraph position="4"> The output of the NP planner is a fully specitied SynInL expression, a possible extension of the list of objects to highlight on the screen, a possible extension of the list of local antecedents, and a possible change of the information corresponding to the answer in the event that the NP planner has produced the NP for the answer.</Paragraph> </Section> <Section position="3" start_page="389" end_page="389" type="sub_section"> <SectionTitle> 4.4 Planning modifications </SectionTitle> <Paragraph position="0"> Modiftcations appear either in the context of a verb or in the context of an NP. They express negation, Pps, relative clauses, adjectives and adverbs. The modification planner is currently handling relatives and PPS.</Paragraph> <Paragraph position="1"> In the case of a relative clause, the identifier of the object of the verb is set to the NP discourse referent, and the verb planner is called.</Paragraph> <Paragraph position="2"> In case of a Pp with exactly one argument, if this argument is in the focus of a wh-question, the I,:B answer has to give both the internM name and the new argument of the preposition. If the answer is no, the planner fails, since we currently don't have a semantic definition for the various Pp negations like 'nowhere' or 'never'. The overall result is then the canned text I don't know. Otherwise there is in generM a list of adjunct-argument pairs. For each pair a Y';ynInl, expression for the preposition is generated, calling the planner recursively on the argument (pronominalization is not allowed in the context of a PP). If there is more than one pair in the list, a pP co-ordination is initialized and reduced as will be explained below.</Paragraph> <Paragraph position="3"> Coordinated PPS are allowed to appear in a.nswers. A list of SyninL expressions for l'ps can be reduced, if the same preposition is used more than once, and the prepositional arguments are not demonstrative pronouns. The resulting ,CjynfnL expression contains the common preposition, and art NP coordination corresponding to the arguments of the tbrmer SynInf, expressions. The NP coordination then can also be reduced as described in \[4\].</Paragraph> </Section> </Section> class="xml-element"></Paper>