<?xml version="1.0" standalone="yes"?>
<Paper uid="C92-4179">
  <Title>Ward, Nigel (to appear). A Connectionist Language Generator. Ablex. revised and extended version of A Flexil)le, Parallel Model of Natural Language Generation, Ph D. thems and Technical Report UCB</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
2. Proposal
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
2.1 Participatory Protiles
</SectionTitle>
      <Paragraph position="0"> i propose to represent in detail the 'participatory properties' of objects. For ex~Lrnl)h b in the scene in volving Jn(l~Ls, Jesus, and a kiting, Judas can be described as actiwb volitional, very responsible, ba sically uaafl'ected, a direct-cause, and so ()It. I will refer to the set of these properties ~m the 'participa-.</Paragraph>
      <Paragraph position="1"> tory profile' of that object. A participatory profile is il|lplelnetlted its it vector O\]' rallies over '(:;~,~e t(-:attlres'.  For example, Judas a.s a kisser may be (-.2 affected), (+.7 responsible), and so or,, as shown in Figure 2 and a.s contra.sted to the traditional representation shown in Figure 1.</Paragraph>
      <Paragraph position="2"> A participatory profile is a precise description.</Paragraph>
      <Paragraph position="3"> To illustrate this with a spatial metaphor, a par,it ipatory profile can be identified with a point in an n-dimensional space, which I will call 'c~me space', where the axes are the ea.se features. Figure 3 shows an impressionistic projection of this space onto two dimensions, populated with sentences about John, positioned appropriately for his role in them. Super imposed on this with curved lines is a suggestion of the way that a traditional ease account might divide up this space. This illustrates how case allows only a relatively coarse description, providing only the opportunil, y to describe a participant's role a.s being in a certain region of the space.</Paragraph>
      <Paragraph position="4"> This proposal Mso makes it easy to explain simi larities. For example, comparing the roles of &amp;quot;yeasl&amp;quot; in &amp;quot;yeast makes bread r~se&amp;quot; and &amp;quot;spoon&amp;quot; ill &amp;quot;eat with a ,spoon&amp;quot;, they are similar in that both are concrete and directly acting, but different it, that the yea.st is not manipulable, nor is it identifiable as a sep~rate entity afterwards. Profile representations of the roles of yea.st and spoor, can show that they are similar on specific stlared dimensions, while not obscur in K the differences on other dimensions. Profile representations also make it easy to quantitatiwdy describe similarity on a single dimension. For example, it is possible to describe John as active in both &amp;quot;John .~peculated t~i commodities&amp;quot; and in &amp;quot;John watched the ducks&amp;quot;, but somewhato less active in the latter; there is no forced choice between assigning John to a case where he is active and one where im is not.</Paragraph>
      <Paragraph position="5"> (-'.~se is traditionally considered to be a cla.ssific~ Lion of tile semantic relations between predicates and their arguments, but the proposal replaces it with an account of the roles of participants in events. In some languages things like. individuation or definit, e ness, which would seem to have nothing to do with the verb, affect choice of ease markers and constructions (Fillmore 1968; flopper gz Thompson 1980). q'hus it seems that meaning relations should relate to the sit ua,lion, Ilot just to the predicate. (Here 'situation' is meant in a narrow sense (DeLancey 1991), where &amp;quot;John asked Mar# to leave&amp;quot; involw~s two situations.)</Paragraph>
    </Section>
    <Section position="2" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
2.2 Profiles and Language
</SectionTitle>
      <Paragraph position="0"> Iamguage refers to regions of case space. 'Fhis is true, in particular, of 'case markers', constructions, aiid grammatical roles.</Paragraph>
      <Paragraph position="1"> Consider for example the Nmily of uses of &amp;quot;of&amp;quot; exemplified in &amp;quot;.lohn died of cancer&amp;quot;. &amp;quot;Of&amp;quot; is used for causes which are direct causes, invisible, iInrnaterial, of unknown origin, and at most only slightly con,toned (Del,ancey 1984). If direct-cause, visible, and so on are treated a.s ease features, this use of &amp;quot;of&amp;quot; can he described as appropriate for participants in a certain region of ease space. Ill generM, the meanings of 'ease markers', that is, words conveying relational information, caa, be identified wit}, regions of ease ACRES DE COLING-92, NANTES. 23-28 AO~q' 1992 1 1 3 8 P~.OC. OF COLING-92, N^NTES, AUG. 23-28. 1992 space The tueallings of sonic constructions also can he identified with regions. ('Construction' here is meam in the sense of l&amp;quot;ilhnore, Kay, and (')'('.onnor (1988).) For a given participant, the extent to which its profih~ leads to selection of function words or to mobilization( of constructions (affecting word order), or to bulb, depends entirely on the language.</Paragraph>
      <Paragraph position="2"> Regions in ca.se space can also he used to describe grammatical roles. For examl)le, consider lhe set of things which can he subjects of passiw: seld;en(:es.</Paragraph>
      <Paragraph position="3"> Rather than saying tha.t this includes Iheme.% l)a tients, and recipients, provided they meel certahl con ditions, we can describe this am the set of things which are highly topicalized, not very active, alld Inure or less aft'coted; this of course describes a region of (m.se space. The set of things which (:~m he direct objects is another region, ow~rlapping that for t)assive st;bjeets, but also including the region of highly all'cried things even if they ~u:e not at all topics, and exchnling all highly tol)icalized things, and also mildly topicalized things unless they are highly atfected. The set of things thai can be tnmsive subjects in Japanese is yet. another region, again overlapping but slightly different.</Paragraph>
      <Paragraph position="4"> 'lb summtwize the ways in which this propos;d solves the problems raised in Section 1: it allows pre else representation heca/lse instances are rel)resented a.s points, ;rod this does not conflict with the need t(/ capture generalizations, because generMiz;ttlons art: represented as regions; and it can capture all gen eralizations because there is no assumption of correspondence bet, wren the regions required for different generalizations.</Paragraph>
    </Section>
    <Section position="3" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
2.3 Exalnl)les and Details
</SectionTitle>
      <Paragraph position="0"> '.Fo define the regions for various case markers by precisely specifying their boundaries would he oner ous at best. Instead we can define these inlplicit/y by reference to their prototypica\[ meanings. For ex ample, the prototypical use of &amp;quot;of&amp;quot; in &amp;quot;die of caticer&amp;quot; carl be described as ~ point in case space, lty computing the proxinfity of a participator's profiles to such prototypes for various case markers it is possible to determine the m(xst suitable case marker for tha~ participant.</Paragraph>
      <Paragraph position="1"> Similarly for constructions; they are used when a participant's profile is sufficiently close to tile con struction's prototype. (Polysemous constructions can probably be amdyzed as having several prototypes.) For example, one can analyze the Passive Construe tion a.s being relevant if a participant expressed in subject position has a profile is 'closer than 1.2' to the prototype (affected +1., volitiom:d -1., responsi hie -1.), as shown in Figure 4.</Paragraph>
      <Paragraph position="2"> Unlike prepositions, constructions' meanings do not form a partition of case space; thus a single point can fall into the regions of several constructions. It is son\]etlnles necessary to elllploy inure than one construction to adequately specify the profile of a participmlt. For example, to describe a participant who is active and possibly affected, but not responsible nor directly affected, the Passive and Causative Construe  ex~mqde: &amp;quot;,lohn died&amp;quot; comment: riwd lo the Passive (k)nstruction; prevellts &amp;quot;.\]ohr~ irla.s died&amp;quot; coIIdil, ion for relevaucv: expressloa of a \[)articil)alll closer than 2.5 to the prototype below; also the availability of a st~tte change-verb prototyI)e weights  ~fl'e(:ted \] 1 l.</Paragraph>
      <Paragraph position="3"> voliti(mal - 1 l.</Paragraph>
      <Paragraph position="4"> responsible -- 1 t.</Paragraph>
      <Paragraph position="5"> object-of force 1 1.</Paragraph>
      <Paragraph position="6">  depends on profiles tiolls lntlst be rise(1 together, a. ~, in a John rllas made lo k~.~s lhe .stalur &amp;quot;; each constructio, expressing SOil|{! dimensions of the participant's profile. The ide~t of ;tdditive colltribntiolts {ronl several constructions call also be applied Io, for example, &amp;quot;John was k~ssed&amp;quot;, where &amp;quot;dohC/~&amp;quot; is a perfl~ctly good subject, and also a perfectly good passiw~ s~duect. This style of aualy sis means factoring out infbrmation, which of course makes \['or siIHI)~e (OllSIrllctio;ls.</Paragraph>
      <Paragraph position="7"> \[ise of COllSl.rtlctions provides a way to acc(Hln\[ for the 'subcaLegorization' properties of w~rbs. To explain why &amp;quot;John broke the dish&amp;quot; is English but &amp;quot;*lhe magwm~ vanished lhe rabbit&amp;quot; is not, one can say that the verb %real&amp;quot; can participate m the Lex ical Causative ('onstructkm but &amp;quot;vanish&amp;quot; can only participate in the Periphra.stic Causative Construe tion. Thus it is not necessary to directly describe the allowable cases of a verb and their mappings to prep() sitions ~md grammatical roles; that information can he factored Oil( into constr:lctions. That is~ the case frame (valence) of a verb ca1 be explained in terms of the constructions the verb can participate in.</Paragraph>
      <Paragraph position="8"> (}ralnmatical roles cart ~lso be analyzed in ternLs AC*rES DI.: COLING-92, NANTES, 23-28 Aotrr 1992 1 1 3 9 PROC. OF COLING-92, NANTES, AU(}. 23-28, 1992 feature prototype it)cation weights</Paragraph>
    </Section>
    <Section position="4" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
Subject-Predicate Construction
</SectionTitle>
      <Paragraph position="0"> of prototypes - for example it haw long been said that the prot.otypical direct object is probably that of &amp;quot;kill&amp;quot; -- and these prototypes can be mapped into case space. Proximity to prototypes can then be computed. This allows, for example, the simple rule: 'for subject, select tire partieipam which is closest in case space to the prototypical subject' (to slightly modify a proposal by 1)nwty (1991)). As sonic fitctors are more important than others, it is appropriate to assign weights to the various case features, to bias the computation of proximity. For example, the weights for subject shown in Figure 5 account for subject selection (in the context of the system described in Section 4), explaining:  la) John kissed Mary lb) Mary made the boy eat a peach lc) Mary was kissed by John (if she is the topic in the larger context) ld) the wind broke a dtsh le) Mary was killed and Mary died  This account of subject is more parsimonious than a subject hierarchy, that is, a list of cases in order of preference for which can become the subject (Fillmore 1968), plus rules for overriding it for tire sake of topics. This description also ohviat, es the need for explicit statements that topicness is more important than agentivity or that volition is more important than activity; such facts are simply encoded in tire weights.</Paragraph>
      <Paragraph position="1"> In the current implementation of ease space, the range of values for each feature go front -1 to +1. Whereas participants can be located at any point in the space, it seems appropriate to site prototypes at the corners or edges of the space. A few more exan|pies of profiles are shown in Figure 4, arrd many more in Ward (to appear).</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>