File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/metho/96/w96-0405_metho.xml
Size: 27,959 bytes
Last Modified: 2025-10-06 14:14:24
<?xml version="1.0" standalone="yes"?> <Paper uid="W96-0405"> <Title>Input Specification in the WAG Sentence Generation System</Title> <Section position="4" start_page="41" end_page="41" type="metho"> <SectionTitle> 2. Ideational Metafunction: concerned </SectionTitle> <Paragraph position="0"> with the propositional content of the text, structured in terms of processes (mental, verbal, material, etc.), the participants in the process (Actor, Actee, etc.), and the circumstances surrounding the process (Location, Manner, Cause, etc.).</Paragraph> <Paragraph position="1"> 3. Textual Metafunction: how the text is constructed as a message conveying information. This concerns, for instance, the thematic structuring of the ideation presented in the text, its presentation as recoverable or not, the semantic relevance of information, etc.</Paragraph> <Paragraph position="2"> Although these metafunctions apply to both the semantics of sentence-size and multi-sentential texts, this paper will focus on sentential semantics, since we are dealing with the input to a sentence generator. Below we explore the nature of this semantic specification in more detail.</Paragraph> </Section> <Section position="5" start_page="41" end_page="44" type="metho"> <SectionTitle> 2 Interactional Specification </SectionTitle> <Paragraph position="0"> Interactional representation views the text as part of the interaction between participants.</Paragraph> <Paragraph position="1"> Sentences themselves serve an important part in interaction, they form the basic units - the moves - of which interactions are composed.</Paragraph> <Paragraph position="2"> Moves are also called speech-acts. Note that WAG serves in monologic as well as dialogic interactions.</Paragraph> <Paragraph position="3"> The input to the WAG generator is basically a speech-act specification, although this specification includes ideational and textual specification. Figure 1 shows a sample speech-act specification, from which the generator would produce: I'd like information on some body repairers. The distinct contributions of the three meta-functions are separated by the grey boxes. Say is the name of the lisp function which evaluates the speech-act specification, calling the generator, dialog-5 is the name of this particular speech-act (each speech-act is given a unique identifier, its unit-id).</Paragraph> <Paragraph position="4"> In specifying the speech-act, there are sev- null eral important things which need to be specified: null * Speech-Function: what does the speaker requires the hearer to do in regard to the encoded proposition? 1 This is called in Systemics the speech-function.</Paragraph> <Paragraph position="5"> Is the hearer supposed to accept the content as a fact? Or are they supposed to complete the proposition in some way? Or perform some action in response to the utterance? Participants: who is uttering the speech-act (the Speaker), and who is it addressed to (the Hearer).</Paragraph> <Paragraph position="6"> Content: what proposition is being negotiated between the speaker and hearer? The participant roles do not need to be included in every sentence-specification, but may be in some, for the following reasons: * Pronominalisation: If the filler of the Speaker or Hearer role happens to play some role in the ideational specification, then an appropriate pronoun will be used in the generated string (e.g., T, 'you').</Paragraph> <Paragraph position="7"> * Voice Selection: If the spoken output mode is used, WAG will select a voice of the same gender as the speaker entity.</Paragraph> <Paragraph position="8"> * User Modelling: In theory, the Speaker and Hearer fields are available for user-modelling purposes (cf. Paris 1993): lexico-grammatical choices can be constrained by reference to attributes specified in the Speaker and Hearer roles. 2 This has not, however, been done at present: while the implementation is set up to handle this tailoring, the resources have not yet been appropriately constrained. null WAG's semantic input improves over that of Penman in regards to the relationship between the speech-act and the proposition. In Penman, the ideational specification is central: a semantic specification is basically an ideational specification, with the speech-act added as an additional (and optional) field. This approach is taken because Penman was designed with monologic text in mind, so the need for varied speech-acts is not well integrated. 3 2Since the fillers of the Speaker and Hearer roles are ideational units, they can be extensively specified for user-modelling purposes, including the place of origin, social class, social roles, etc of the participant. Relations between the participants can also be specified, for instance, parent/child, or doctor/patient relations. Lexico-grammatical decisions can be made by reference to this information: tailoring the language to the speaker's and hearer's descriptions.</Paragraph> <Paragraph position="9"> a~VAG also allows the representation of non-verbal moves (e.g., the representation of system or user physical actions), which allows WAG to model interaction in a wider sense.</Paragraph> <Paragraph position="10"> WAG however takes the speech-act as central, the semantic specification is a specification of a speech-act. The ideational specification is provided as a role of the speech-act (the :proposition role). WAG thus integrates with more ease into a system intended for dialogic interaction, such as a tutoring system. In particular, it simplifies the representation of speech-acts with no ideational content, such as greetings, thank-yous, etc.</Paragraph> <Section position="1" start_page="42" end_page="44" type="sub_section"> <SectionTitle> 2.1 Types of Speech-Acts </SectionTitle> <Paragraph position="0"> Figure 2 shows the systems of the speech-act network used in WAG (based on O'Donnell 1990, drawing upon Berry 1981; Martin 1992).</Paragraph> <Paragraph position="1"> The main systems in this network are as follows: null Initiation: The grammatical form used to realise a particular utterance depends on whether the speaker/writer is initiating a new exchange, or responding to an existing exchange (e.g., an answer to a question). Responding moves reflect a far higher degree of ellipsis than initiating moves. In particular, a move responding to a wh- question usually only needs to provide the wh- element in their reply.</Paragraph> <Paragraph position="2"> Negotiatory vs. Salutory: negotiatory speech-acts contribute towards the construction of an ideational proposition. while salutory moves do not, rather is the speaker's indication of what they want the hearer to do with the utterance.</Paragraph> <Paragraph position="3"> An elicit move indicates that the speaker requires some contentfull response, while a propose move may require changes of state of belief in the hearer, support moves indicate the speaker's acceptance of the prior speaker's proposition. Other speech-functions cater to various alternative responses in dialogue, for instance: deny-knowledge - the speaker indicates that they are unable to answer a question due to lack of knowledge; contradict: the speaker indicates that they disagree with the prior speaker's proposition; requestrepeat: the speaker indicates that they did not fully hear the prior speaker's move.</Paragraph> <Paragraph position="4"> * Object of Negotiation: Speech-acts can negotiate information (questions, statements, etc.), or action (commands, permission, etc.). A move with features (:and elicit negotiate-action) would be realised as a request for action (e.g., Will you go now?), while a move with features (:and propose negotiate-action) would be realised as a command (e.g., Go now. O.</Paragraph> <Paragraph position="5"> In writing a speech-act specification, the :is field is used to specify the the speech-act type (the same key is used to specify ideational types in propositional units). The speech-act of figure 1 is specified to be (:and initiate propose). Feature-specifications can be arbitrarily complex, consisting of either a single feature, or a logical combination of features (using any combination of :and, :or or :not). One does not need to specify features which are systemically implied, e.g., specifying propose is equivalent to specifying (:and move speech-act negotiatory propose).</Paragraph> <Paragraph position="6"> Hovy (1993) points out that as the input specification language gets more powerful, the amount of information required in the specification gets larger, and more complex. WAG thus allows elements of the semantic specification to take a default value if not specified. For instance, the example in figure 1 does not specify a choice between negotiate-information or negotiate-action (the first is the default). Other aspects are also defaulted, for instance, the relation between the speaking time and the time the event takes place (realised as tense).</Paragraph> </Section> </Section> <Section position="6" start_page="44" end_page="46" type="metho"> <SectionTitle> 3 Ideational Specification </SectionTitle> <Paragraph position="0"> Once we have specified what the speech-act is doing, and who the participants are, we need to specify the ideational content of the speechact. null</Paragraph> <Section position="1" start_page="44" end_page="44" type="sub_section"> <SectionTitle> 3.1 Ideational Representation </SectionTitle> <Paragraph position="0"> When talking about ideational specification, we need to distinguish ideational potential the specification of what possible ideational structures we can have; and ideational instanrials - actual ideational structures. The first is sometimes termed terminological knowledge - knowledge about terms and their relations, the second, assertional knowledge - knowledge about actual entities and their relations.</Paragraph> <Paragraph position="1"> Ideational Potential: Ideational potential is represented in terms of an ontology of semantic types, a version of Penman's Upper Model (UM) (Bateman 1990; Bateman et al.</Paragraph> <Paragraph position="2"> 1990). 4 The root of this ontology is shown in figure 3. Many of the types in this ontology will have associated role constraints, for instance, a mental-process requires a Sensor role, which must be filled by a conscious entity. The UM thus constrains the possible ideational structures which can be produced.</Paragraph> <Paragraph position="3"> The UM provides a generalised classification system of conceptual entities. For representing concepts which are domain-specific (e.g., bodyrepairer), users provide domain-models, where domain-specific concepts are subsumed to concepts in the UM.</Paragraph> <Paragraph position="4"> Ideational Structure: An ideational specification is a structure of entities (processes, t-hings and qualities), and the relations between these entities. Such a structure is specified by providing two sets of information for each entity (as in the propositional slot of figure 1): * Type Information: a specification of the semantic types of the entity, derived from the UM, or associated domainmodel. null 4WAG's Upper Model has been re-represented in terms of system networks, rather than the more loosely defined type-lattice language used in Penman. WAG thus uses the same formalism for representing ideational, inteLctional and lexico-grammatical information. null</Paragraph> <Paragraph position="6"> - thing 1 t. nonhuman...</Paragraph> <Paragraph position="7"> nonconscious...</Paragraph> <Paragraph position="8"> \[- material...</Paragraph> <Paragraph position="9"> F mental...</Paragraph> <Paragraph position="10"> - process m verbal... F relational...</Paragraph> <Paragraph position="11"> '- existential...</Paragraph> <Paragraph position="12"> \[- modal quality... q-material-quality. . . quality I -pdeglar'quality''&quot; * Role Information: a specification of the roles of the entity, and of the entities which fill these roles.</Paragraph> </Section> <Section position="2" start_page="44" end_page="46" type="sub_section"> <SectionTitle> 3.2 Expressing the KB: Stand-alone </SectionTitle> <Paragraph position="0"> vs. Integrated approaches Typically, a text-planner has a knowledge-base (KB) to express, and produces a set of sentence-specifications to express it. The form of the sentence-specifications differs depending on the degree of integration between the text-planner and the sentence-realiser.</Paragraph> <Paragraph position="1"> In most systems, the sentence-realiser has no access to the KB of the text-planner. This is desirable so that the sentence-realiser is independent of the text-planner - it can act as an independent module, making no assumptions as to the internal representations of the text-planner. The sentence-realiser can thus be used in connection with many different textplanners. null The sole communication between the two systems is through a sentence-specification - the text-planner produces a sentencespecification, which the sentence-realiser takes as input. The text-planner thus needs to re-express the contents of its KB into the ideational notation used by the sentencerealiser. This approach has been followed with systems such as Penman, FUF, and Mumble.</Paragraph> <Paragraph position="2"> Each of these has been the platform supporting various text-planners (often experimental).</Paragraph> <Paragraph position="3"> WAG also has been designed to support this planner-realiser separation, if need be. WAG can thus act as a stand-alone sentence realiser. The sentence specifihation of figure 1 reflects this mode of generation.</Paragraph> <Paragraph position="4"> However, WAG supports a second mode of generation, allowing a higher degree of integration between the text-planner and the sentence realiser. In this approach, both processes have access to the KB. Ideational material thus does not need to be included within the input specification. Rather, the input specification provides only a pointer into the attached KB. Since the information to be expressed is already present in the KB, why does it need to be re-expressed in the semantic specification? Taking this approach, the role of the semantic specification is to describe how the information in the KB is to be expressed, including both interactional and textual shaping.</Paragraph> <Paragraph position="5"> This integration allows economies of generation not possible where content used for text-planning and content used for sentence generation are represented distinctly. One benefit involves economy of code - many of the processes which need to be coded to deal with ideation for a text as a whole can also be used to deal with ideation for single sentences. Another involves the possibility of integrating the two processes - since the sentence realiser has access to the same knowledge as the multi-sentential planner, it can make decisions without requiring explicit informing from the planner.</Paragraph> <Paragraph position="6"> Another economy arises because translation between representations is avoided. In the stand-alone approach, the sentence-planner needs knowledge of how ideational specifications are formulated in the sentence specification language. It needs to map from the language of its KB to the language of the sentence specification. This is not necessary in an integrated approach.</Paragraph> <Paragraph position="7"> To demonstrate this integrated approach to sentence generation, we show below the generation of some sentences in two stages firstly, assertion of knowledge into the KB, and secondly, the evaluation of a series of speechacts, which selectively express components of this knowledge.</Paragraph> <Paragraph position="8"> knowledge about John and Mary into the KB.</Paragraph> <Paragraph position="9"> The information basically tells that Mary left a party because John arrived at the party, tell is a lisp macro form used to assert knowledge into the KB.</Paragraph> <Paragraph position="10"> Now we are ready to express this knowledge.</Paragraph> <Paragraph position="11"> The following sentence-specification indicates that the speaker is proposing in/ormation, and that the leaving process is to be the semantic head of the expression. It also indicates which of the roles of each entity are relevant for expression (and are thus expressed if possible), -and which entities are identifiable in context (and can thus be referred to by name). The generation process, using this specification, produces the sentence shown after the form.</Paragraph> <Paragraph position="12"> As stated above, this approach does not require the sentence-specification to include any ideational-specification, except for a pointer into the KB. The realiser operates directly on the KB, using the information within the sentence-specification to tailor the expression. Alternative sentence-specificati0ns result in different expressions of the same information, for instance, including more or less detail, changing the speech-act, or changing the textual status of various entities. The expression can also be altered by selecting a ~different entity as the head of the utterance. For instance, the following sentence-specification is identical to the previous, except the cause relation is now taken as the head, producing a substantially different sentence: We will now turn to the textual component of the input specification, which iS responsible for tailoring the expression of the ideational content.</Paragraph> </Section> </Section> <Section position="7" start_page="46" end_page="47" type="metho"> <SectionTitle> 4 Textual Specification </SectionTitle> <Paragraph position="0"> Textual semantics concerns the role of the text and its components as a message, While creating a text (whether a single utterance or a whole book), we have a certain amount of content we wish to encode. But there are various ways to encode this information, to present our message. The textual semantics represents the various strategies for structuring the message.</Paragraph> <Section position="1" start_page="46" end_page="47" type="sub_section"> <SectionTitle> 4.1 Relevant-Roles </SectionTitle> <Paragraph position="0"> One of the main steps in the text generation process involves content selection - the selection of information from the speaker's knowledge base for presentation. Such a process must decide what information is relevant at each point of the unfolding discourse.</Paragraph> <Paragraph position="1"> In some systems, content selection is driven through the construction of the rhetorical structure of the text (e.g., Moore & Paris 199).</Paragraph> <Paragraph position="2"> As we build a rhetorical structure tree, the ideation which is necessary for each rhetorical relation is selected. For instance, if we add an evidence relation to an existing RST tree, the ideation which functions as evidence is selected for expression. The rhetorical structure thus organises the ideational content to be expressed, selecting out those parts of the ideation-base which are relevant to the achievement of the discourse goals at each point of the text. I use the term rhetorical relevance to refer to this sort of relevance. 5 Rhetorical relevance is dynamic - it changes as the text progresses. It represents a shifting focus on the ideation base (Halliday ~ Matthiessen, 1995, pp373-380). What is relevant changes as the text unfolds, as the rhetorical structure is realised. Relevance forms what Grosz (1977/86) calls a focus space. 6 Halliday & Matthiessen (1995) extend Grosz's notion of focus space to include other types of textual spaces: thematic spaces, identifiability spaces, new spaces, etc. (p376). Each of these spaces can be though of as a pattern stated over the ideation base.</Paragraph> <Paragraph position="3"> According to Grosz, focus is &quot;that part of the knowledge base relevant at a given point of a dialog.&quot; (p353). However, Grosz's notion of relevance is based on the needs of a text understanding system - which objects in the knowledge-base can be used to interpret the utterance. My sense of relevance is derived from relevance in generation - what information has been selected as relevant to the speaker's unfolding discourse goals. She is dealing with a set of objects which may potentially appear in the text at this point, while I am dealing with the set of objects which most probably do appear in the text.</Paragraph> <Paragraph position="4"> To represent the relevance space in a sentence specification, I initially provided a :relevant-entities field, which listed those ideational entities which were relevant for expression. However, problems soon arose with this approach. Take for instance a situation where Mark owns both a dog and a house, and the dog destroyed the house. Now, we might wish to express a sentence to the effect that A dog destroyed Mark's house, which ignores Mark's ownership of the dog. In a system where relevance is represented as a list of entities, we could not produce this sentence.</Paragraph> <Paragraph position="5"> What we need is a representation of the relevant relations in the KB. To this end, WAG's input specification allows a field :relevant-roles, which records the roles of each entity which are currently relevant for expression, e.g., as was used in the examples of section 3.2.2. 7 While constructing a sentence, the sentence generator refers to this list at various points, to see if a particular semantic role is relevant, and on the basis of this, chooses one syntactic structure over another. At present, the ordering of roles in the list is not significant, but it could be made so, to constrain grammatical salience, etc.</Paragraph> </Section> <Section position="2" start_page="47" end_page="47" type="sub_section"> <SectionTitle> 4.2 Theme </SectionTitle> <Paragraph position="0"> The :theme field of the speech-act specifies the unit-id of the ideational entity which is thematic in the sentence. If a participant in a process, it will typically be made Subject of the sentence. If the Theme plays a circumstantial role in the proposition, it is usually realised as a sentence-initial adjunct. WAG's treatment of Theme needs to be extended to handle the full range of thematic phenomena. Theme specification in WAG is identical to that used in Penman.</Paragraph> </Section> <Section position="3" start_page="47" end_page="47" type="sub_section"> <SectionTitle> 4.3 Information Status </SectionTitle> <Paragraph position="0"> The participants in an interaction each possess a certain amount of information, some of which is shared, and some unshared. I use the term information status to refer to the status of information as either shared or unshared.</Paragraph> <Paragraph position="1"> The information status of ideational entities affects the way in which those items can be referred to. Below we discuss two dimensions of information status: TIf the explicit ideational specification is included in the say form (as in figure 1), then the relevance space need not be stated, it is assumed that all the entities included within the specification axe relevant, and no others.</Paragraph> <Paragraph position="2"> . Shared Entities: entities which the speaker believes are known to the hearer can be referred to using identifiable reference, e.g., definite deixis, e.g., the President; and naming, e.g., Ronald Reagan. Entities which are not believed to be shared require some form of indefinite deixis, e.g., a boy called John; Eggs; Some eggs, etc.</Paragraph> <Paragraph position="3"> A speaker uses indefinite deixis to indicate that he believes the entity unknown to the hearer. It is thus a strategy used to introduce unshared entities into the discourse.</Paragraph> <Paragraph position="4"> Once the entity is introduced, some form of definite reference is appropriate.</Paragraph> </Section> </Section> <Section position="8" start_page="47" end_page="48" type="metho"> <SectionTitle> 2. Recoverable Entities: Entities which </SectionTitle> <Paragraph position="0"> are part of the immediate discourse context can be referred to using pronominalisation (e.g., she, them, it, this, etc.); substitution (e.g., I saw one;); or ellipsis (the non-mention of an entity, e.g., Going to the shop?). The immediate discourse context includes entities introduced earlier in the discourse; and also entities within the immediate physical context of the discourse, e.g., the discourse participants (speaker, hearer, or speaker+hearer) and those entities which the participants can point at, for instance, a nearby table, or some person.</Paragraph> <Paragraph position="1"> Two fields in the semantic specification allow the user to specify the information status of ideational entities - and thus how they can be referred to in discourse s (these lists will typically be maintained by the text-planner as part of its model of discourse context): * The Shared-Entities Field: a list of the ideational entities which the speaker wishes to indicate as known by the hearer, e.g., by using definite reference.</Paragraph> <Paragraph position="2"> * The Recoverable-entities Field: a list of t the ideational entities which are recoverable from context, whether from the prior text, or from the immediate interactional context.</Paragraph> <Paragraph position="3"> SInformation status only partially constrains the choice of referential form - the choice between the remaining possibilities can be made by the sentence planner, by specifying directly grammatical preferences.</Paragraph> </Section> <Section position="9" start_page="48" end_page="48" type="metho"> <SectionTitle> / 5 Conclusions </SectionTitle> <Paragraph position="0"> The input specification for the WAG sentence generator is a' speech-act, which includes an indication of which relations in the KB are relevant for expression at this point. Other information in the input specification helps tailor the expression of the content, such as an indicator of which KB element to use as the head of the generated form, which is theme, which elements are recoverable and identifiable.</Paragraph> <Paragraph position="1"> In taking this approach, WAG attempts to extend the degree to which surface forms can be constrained by semantic specification. In many sentence generation systems, direct specifications of grammatical choices or forms is often needed, or, in the case Of Penman, the user needs to include arcane inquiry preselections - interventions in the interstratal mapping component, perhaps more arcane than grammar-level intervention.</Paragraph> <Paragraph position="2"> By providing a more abstract form of representation, text-planners using WAG need less knowledge of grammatical forms, and can spend more of their efforts dealing with issues of text-planning. I say 'less' here because, although WAG has extended the level at which surface forms can be specified semantically, there are still gaps. To allow for this, WAG allows input specifications to directly constrain the surface generation, either by directly specifying the grammatical feature(s) a given unit must have, or alternatively, specifying grammatical defaults: grammatical features which will be preferred if there is a choice.</Paragraph> <Paragraph position="3"> The advantages of WAG's input specification language are summarised below:</Paragraph> </Section> <Section position="10" start_page="48" end_page="48" type="metho"> <SectionTitle> 1. Interactional Specification: By pla- </SectionTitle> <Paragraph position="0"> cing the proposition as a role of the speech-act, rather than visa-versa, WAG allows cleaner integration into systems intended for dialogic interaction. WAG's input specification also allows a wider range of specification of the speech-act type than used in Penman and other sentencegeneration systems.</Paragraph> </Section> class="xml-element"></Paper>