File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/metho/99/w99-0109_metho.xml
Size: 31,835 bytes
Last Modified: 2025-10-06 14:15:24
<?xml version="1.0" standalone="yes"?> <Paper uid="W99-0109"> <Title>O Q O O O O O @ @ O O O O O O O O O O @ O O O O O O O O O @ O O</Title> <Section position="3" start_page="0" end_page="72" type="metho"> <SectionTitle> 1 What is Centering? </SectionTitle> <Paragraph position="0"> Centering theory (C~) is a theory of discourse structure which models the interaction of cohesion and salience in the internal organlsation of a text. The main assumptions of the theory as presented by (Gross et a11995 (GJW), Brennan et al 1987) rare: 1. For each utterance in a discourse there is precisely one entity which is the centre of attention or center.</Paragraph> <Paragraph position="1"> 2. There is a preference for consecutive utter- null ances within a discourse segment to keep the same entity as the center, and for the most salient entity ~realised n in an utterance to be interpreted as the center of the following utterance.</Paragraph> <Paragraph position="2"> 3. The center is the entity which is most likely to be pronominalised.</Paragraph> <Paragraph position="3"> These principles will be more precisely explicated in Sect. 2.</Paragraph> <Paragraph position="4"> CT has proved attractive to NLP researchers because of the elegance and simplicity of the core proposals; it provides a framework for analysing text without having to make tough decisions about what a partfcular utterance is &quot;about&quot;, since all notions are defined in purely structural terms.</Paragraph> <Paragraph position="5"> Much research in CT has concentrated on interpretation, particularly reference resolution, developing algorithms to resolve anaph0ric expressions based on the assumption that the text is constructed according to Rules 1 and 2. So researchers have focussed on filling in de~ tails of the theory which were left unspecified: what counts as an utterance, and how should transitions be handled in complex sentences (Kameyama 1998; cf Suri and McCoy 1994)? how is salience ranking determined (Gordon et al 1993; Stevenson et al 1994;. Strube and Hahn 1996)? what counts as ~r~Migstion ~ - does this include bridging references (Strube and Hahn op cit.)? how do centering tra~L~itions relate to discourse segment boundaries (Walker 1998, Passoneau 1998)? In fact I will leave many of these issues aside for the purposes of this paper; I will not examine the empirical adequacy of CT, for which the reader is referred to papers cited above and * others collected in Walker et al (1998). I will take a different approach, which is to examine how the dements of CT can be applied to the planning of texts, with the rules and constraints interpreted as instructions to a generator rather than a guide for interpretation. To avoid introducing too many complications I shall assume a Ucanonical ~ formulation of CT as outlined by Walker et al. (1998, Chapter 1) and the schematic ~consensus ~ generation architecture described by Reiter and Dale (Reiter 1994; Reiter and Dale 1997). This consists a ~pipelins&quot; of distinct tasks: Text Planning- deciding the content of a message, and organising the component propositions into a text tree; Sentence Planning - aggregating propositions into clausal units and choosing lexical items corresponding to concepts in the knowledge base, including referring expressions (RE); Linguistic re_8!isation which takes care of surface details such as agreement, orthography etc. &quot; Previous researchers have implemP.nted pronominalisafion decisions using CT, and so have located Centering as part of RE generation (e.g., Dale 1992, Passoneau 1998), while Mittal et al (1998) have a ~centering module&quot; which forms part of Sentence Planning and seeks to realise the center as Subject in successive sentences. In what follows I will try to separate out the tasks which make up centering theory and argue that the way to implement CT is not as a discrete module but as a series of constraints on the various levels of the generation process from Text Planning Constraints and Rules to RE generation. I shall also briefly note points of comparison with systems discussed by CAhill and Reape (1998) in a survey of applied NLG systems, and conclude with some remarks on the applicability of my proposals to the &quot;reference architecture n envisaged by Cahill et al. (1999), RAGS (1999).</Paragraph> </Section> <Section position="4" start_page="72" end_page="72" type="metho"> <SectionTitle> 2 TrAnsition rules </SectionTitle> <Paragraph position="0"> The rn~in clahns of CT are formalised in terms of C5, the &quot;backward-looking center ~, C/, a list of ~'orward-looking centers z for each utterance Un, and Cp or ~preferred center z, the most salient candidate for subsequent utter* ances. Cf(Un) is a partial ordering on the entities mentioned (or ~lised n) in Un, ranked by grammatical role, e.g. SUBJ ) DIR-OBJ ></Paragraph> <Paragraph position="2"> is the highest ~,,ked member of C/(U,J (usually susJ), and is predicted to be Cb(U,+~).</Paragraph> <Paragraph position="3"> C.f is partial/), ordered in most accounts, which leaves open the possibility that there is no -nlque Cb. AJSO, if two successive utterances have no referent in common the second Will ha~ no Cb.</Paragraph> <Paragraph position="4"> Successive pairs of utterances are characterised in terms of tmns/t/on.~ as defined in Figure 1; for instance if two consecutive utterances have the same Co, and the Cb in the second utterance occurs in Subject position, this is classified as a CONTINUE transition. A text is judged to be coherent to the extent that transitions follow the preference ordering given in Rule 2 (Fig 2); and on the assumption that the text is coherent, pronominalisation is predicted to conform to Rule 1.</Paragraph> <Paragraph position="5"> The notion of &quot;realisation&quot; is subdivided into &quot;direct' and &quot;indirect&quot;: an entity is directly realised in an utterance if it is the denotation of an overt NP (or a zero pronoun where this is syntactically licensed), while &quot;indirect realisation&quot; covers for example subsectional anaphora, possessive pronouns and inferential links such as bridging reference. Corpus~based investigations of CT have tended to concentrate on direct realisation, since ~nnotation of indirect anaphoric links depends on theoretically-based decisions and it may be difficult to achieve reliability in this area. This has obvious implications for the resulting measure of coherence, which I return to below.</Paragraph> <Section position="1" start_page="72" end_page="72" type="sub_section"> <SectionTitle> 2.1 Salience and cohesion </SectionTitle> <Paragraph position="0"> Transitions are defined in terms of tests which I shall call cohesion: Cb(Un) = Cb(U~-l), and salience: ~(Un) = ~v(Un). There are four possible combinations, which are displayed in apply, namely co~Imm, and the least preferred is where neither apply, ItOUQH S~. For the intermediate cases there are three logical possibilities: prefer cohesion (It,&quot;rAm), prefer salience (SMOOTH SHIFt) or allowboth equally. There is no obvious way to settle this a pr/or/, but Walker et al (1998, Ch. 1) ~ipulate that ~&quot;rAm is preferred over SMOOTH SHIFT. Evidence for this position is not conclusive, and indeed di Eugenio (1998), Passoneau (1998) and Hurewitz (1998) all found a higher percentage of shifts than retains. This suggests either that salience is a stronger requirement than cohesion or that it.is easier to satisfy. &quot;That is, the l~n. guages studied (English and Italian) may be sufficiently flexible that there is usually some way to realise 6'b as Subj (or first-mention) but on the other hand the same 6'b can only be maintained for a- finite n,,mher of utterances.</Paragraph> <Paragraph position="1"> I suggmtthat these results should be treated with some caution since it is not dear that the authors have the same assumptions about the claims of CT or that what they are testing directly reflects formulations of CT in the more theoretical literature. For instance Passoneau (1998) refers to two variantS of CT: &quot;Version A&quot; based on Brennan et al (1987) and ~Version B&quot; taken from Kameyama et al (1993). Passoneau does n~t address the issue of direct vs indirect realisation and it appears from the examples given that she only takes account of entities realised by a full NP or (possibly null) pronoun. The analysis according to Version B results in a count of 52% NULL transitions, i.e.</Paragraph> <Paragraph position="2"> no Cb, which gives the impression that CT is in fact a rather poor measure of coherence, It is probable that a higher measure might have been obtained if Passoneau had allowed entities to be added to the U/'s by inference, as discussed in (Brennan et al, op cit.). It is of course impossible to verify this without access to the original texts, but it is instructive to consider the-following example from Strube and Hahn (1996):</Paragraph> <Paragraph position="4"> (A reserve battery pack - supplies- the 316LT- ca. 2 minutes - with power.) b. Der Status des Ak/ms wird dem Anwemier anges .</Paragraph> <Paragraph position="5"> (The status of- the accumulator- is to the user- indicated.) S & H treat Ak/m in the (b) sentence as indirectly ~;|~ing the 316LT (a kind of computer) in the (a) sentence, so the latter becomes the Cb of (b) resulting in a CONTINtrJS transitio~ If the authors had only taken account of direct realisations this would be analysed as a NULL tr~nRition.</Paragraph> <Paragraph position="6"> Furthermore, a preponderance of shifts over continues may reflect the domain and content rather than the organlp-~tion of a text. In fact it can be seen that sequences of smooth shifts are rather natural in certain kinds of narrative or descriptive texts; see example (2).</Paragraph> <Paragraph position="7"> (2) The name of your medicine is Rhinocort Aqu It contains budmonide.</Paragraph> <Paragraph position="8"> This is one of a group of medicines called</Paragraph> </Section> </Section> <Section position="5" start_page="72" end_page="72" type="metho"> <SectionTitle> corticosteroid~ SMOOTH SHIFT </SectionTitle> <Paragraph position="0"> These can help to relieve the symptoms of hay fever or rhinitis. SMOOTH SHIFT but there is no way that the cdegntent could be rearranged to turn the shifts into continues.</Paragraph> <Section position="1" start_page="72" end_page="72" type="sub_section"> <SectionTitle> 2.2 Deconstructing the transitions </SectionTitle> <Paragraph position="0"> Strube and Hahn (1996) question the canonical ordering of transitions, partly on the grounds that this ordering fails to predict the P~TAIN SHIFT pattern which has been claimed by many researchers to signal a segment boundary or the introduction of a new =discourse topic&quot;. (See Section 3.2 below.) Recall that the Up is defined as the most salient entity realised in Un, which is predicted to be the Gb of U,+l. However this &quot;prediction&quot; is not in fact cashed out in the rul~ for centering transitions, which take no account of whether Cp(Un) is actually realised in U,+l. S & H (op cit., p. 275) propose the principle of cheapness which is satisfied if</Paragraph> <Paragraph position="2"> to minimise the inferential costs of processing sequences of utteranCes, and is proposed as a constraint on pairs of successive transitions as a replacement for the canonical orderings in Rule 2.</Paragraph> <Paragraph position="3"> We call a tr~n.qition pair cheap if the backward-looldng center of the current utterance is correctly predicted by . the preferred center of the immediately preceding utterance, i.e~, Cb(Ui) = Cp(U,-d... In fact it turns out that although cheapness appears to be a sensible principle, it does not neatly partition the types of transition pairs; in particular, this principle does not necessar-Uy hold of all s~rAm - SMOOTH SHIFT sequences. S & H propose to rectify this by redefining the transitions, with an additional test Cb(Ui) = Cp(0'/-t) to subdivide CONTIN~ and mOOTS smFr (Strube, p.c.; Strube and HAhn forthcoming).</Paragraph> <Paragraph position="4"> In what follows I will also argue against the canonical ordering though on different grounds: one cannot in general predict a .preference for Retain over Shift, for the simple reason that there is no point at which the choice between these two alternatives arises. Rather, at different points in the generation process there is a choice between maintaining the .~me Cb or choosing a new. one, and a choice of which entit), (Cbor non-Cb) to make salient. So the various transition types emerge in a partial ordering from the interaction between salience and cohesion. Note that if we also include Strube and Hahn's &quot;cheapness&quot; principle, there is potential competition with salience in cases where Cb(Un) ~ Cb(Un+l). That is, we will need a way to decide which entity to realise as Cp in cases where there are two candidates~ one of which is the current G'b and the other the Cb of the following sentence. In the remainder of this paper I will not directly incorporate the &quot;cheapness&quot; principle but will suggest thatsimilar results are obtained with an appropriate interpretation of Constraint 3 in the context of generation.</Paragraph> </Section> </Section> <Section position="6" start_page="72" end_page="77" type="metho"> <SectionTitle> 3 Architecture </SectionTitle> <Paragraph position="0"> If we decompose the rules and constraints into separate specifications we see that they potentially fall under quite different headings in the ,schematic architecture described above. The tr_~,sitions mentioned in Rule 2 are defined in terms of two principles which I have called cohesion (maintaining the same ~ from one utterance to the next) and salience (realising the Cb as Cp, normally Subject). If we consider these as p|ann|ng operations, cohesion naturally comes under Text Planning and salience under Sentence pl~nnlng, while Rule I concerning pronominalisation falls under the Referring Expression component of Sentence Planning.</Paragraph> <Section position="1" start_page="72" end_page="72" type="sub_section"> <SectionTitle> 3.1 Text Planning </SectionTitle> <Paragraph position="0"> A text planner which operated according to C~ would seek to order clauses within ~ segment to m~t~m the same Cb in a sequence of clauses.</Paragraph> <Paragraph position="1"> There are two related issues which compUcate this project: firstly, Constraint 3 in Fig. 2 implies a requirement for/~ to determlne the Cb. In addition, there is a potential conflict between top-dow~ hierarchical RST-type planning and sequential centering rules.</Paragraph> <Paragraph position="2"> Constraint 3 states that ~for each utterance U~ in a discourse segment D...</Paragraph> <Paragraph position="3"> The center, Cb(Ui, D) is the highest-ranked element of C/(Ui-I,D) that is realised in Ui.&quot; (Walker et al 1998:3).</Paragraph> <Paragraph position="4"> There are two different implementation strategies which could satisfy this constraint: 75 , 1. Take the ranking of Cf(Ui-h D) as given and use this to identify the Cb.</Paragraph> <Paragraph position="5"> 2. Take the Cb as given and plan the reali null sation of Ui-~ to make this entity the highestranked. null The first strategy is clearly appropriate for interpretation (cf Brennan et al 1987) but for gene.ration the issue is less clear-cut. Either the generator &quot;interprets&quot; its own output to designate Cb in terms of the grammatical structure of the previous utterance, in which case there have to be separate principles for deciding on the grammatical structure, or Cb is independently defined in the text plan and this information is used to plan the sentence structure. According to the pipelining principle information cannot flow 'backwards' between tasks. In a pipelined system, the ~a!isation of an entity as Cp may have the effect of setting up an expectation on the reader'S part that this entity will be Cb of the following utterance, but it Cannot influence the decision made by text planning. This would mean that the 6&quot;b will no longer be defined as in Coustraint 3 but must be independently designated by the text planner as the centre of attention in an utterance. In fact the resulting distribution of tasks would be rather similar to the Gossip system (Carcagno and Iordanskaja 1989) as described by Ca/aiR and Reape (1998): First, the planner produces &quot;sentencesized semantic nets&quot; which it marks with theme-rheme information.</Paragraph> <Paragraph position="6"> ... Furthermore, the theme/theme constraints influence clause ordering, ...pronominalisation ...and lexical choice.</Paragraph> <Paragraph position="7"> An implementation of CT with feedback seems likely to fit more naturally into an in-C/rernenta/architecture, where generation tasks may. be carried out on an utterance-byutterance basis in contrast to top-down generation of a text tree for an entire discourse. In incremental systems it is possible in principle to plan the content of an utterance according to which entity is currently made salient by its surface grammatical role, whereas this would not in general be possible in a top-down pipelined system. In fact it turns out that incremental generators tend to perform sentence planning incrementally but not text planning. (See e.g. Reithinger 1991, DeSmedt and Kempen 1991.) Ill fact I would argue that the feedback problem is only an artefact of an interpretation of Constraint 3 as an implication rather than a constraint. The ~implicational ~ interpretation is that if an entity a is Cp of Un and is realised in Un+l, it should be designated as Cb of Un+l. The declarative interpretation is non-directional and simply equates Cb of Un+l with the most salient entity rea lised in Un which is also realised in Un+l. The way to implement this while keeping to the pipelining principle is to assume that the text planner independently designates the &quot;theme &quot;, &quot;topic ~ or intended centre of attention in each clause, which is marked aS Cb if it is realised in the previous clause, and to have the Sentence Planner promote an entity to salience in Un if it is Cb of Un+l. So the text planner should annotate each clausal node Un in the text tree with the following information: Cb of\[/.</Paragraph> <Paragraph position="8"> Cb of U._l Cb of Un+l The sentence planner will then make use of this information to decide on pronominali.qation according to the values of the current and previous Cb, and on promotion of arguments to salience depending on the current and \]ollowing Cb. Some concrete proposals are discussed in Section 3.2, &quot;Sentence Planning ~. The general division of labour is outlined in Fig. 3.</Paragraph> <Paragraph position="9"> The reader may be disappointed that no independent definition of ~topic&quot; or &quot;theme&quot; is offeted. In fact we consider that this may be outside the scope of CT. When used for interpretation, CT offers a set of rules of thumb to guide the system in identifying the centre of attention in each utterance and finding probable antecedents for anaphors, but the notion of ~centerhood&quot; is not defined separately from these rules. When used for generation, the most C~ can offer is to take the topic or theme as 9/yen and exploit the centerln~ rules and constraints to construct the text in a way which foregrounds these entities and enables the user to correctly identify antecedents. So CT has to sit on top of an independently specified treatment of information structure. One candidate is Strube and Hahn's (1996) reformulation of the notions of 1. Content determination.</Paragraph> <Paragraph position="10"> 2. Discourse planning: order clauses Ui (within segments) to maximise continuity of reference.</Paragraph> <Paragraph position="11"> For each clause Un: o Designate at most one argument as Ub(U~,), which must be an argument of U,z-I. (If intersection of Ufs(U,) and Ufs(U~_l) has only one member, that member is Ub.) o Annotate clause node with IDs of Ub(Un), Ub(Un-l) and Cb(Un+l). Sentence Planning 1. $ente'nce aggregation.</Paragraph> <Paragraph position="12"> 2. Lexica/isation: select verb form for Un so that a. Cb(U,+t) is most grammatically salient of intersection of Cfs(U,) and Cfs(U,+t); b. subject to (a), Ub(Un) is reafised in most salient available position. 3. Referring expression generation: working hypotheses .</Paragraph> <Paragraph position="14"> theme and theme. Another pomibi\]ity, which is currently under investigation, is to experiment with the effects of rhetorical structure on choice of Cb.</Paragraph> <Paragraph position="15"> I've assumed above that the task of mainraining continuity of reference can be located in the Text Planner. That is, the TP would be responsible both for annotating the Cb in each utterance, and for organising the text so that the same Cb is m~intained over a sequence of clauses. However, according to Reiter and Dale (1997) a more common method of structuring text is to make use of &quot;discourse relations, such as those described by Mann and Thompson (1987), which do not explicitly take continuity of reference into account. Richard Power (p.c.) has proposed that the implementation of CT in an RST-ba~i text planner can be treated as an opt~mi-*-~tion problem. That is, the text plan is iuitiAlly taken to be a tree structure with discourse relations defined on adjacent nodes but at most a partial specification of linear order.</Paragraph> <Paragraph position="16"> The problem will then consist of selecting a Ub for each propositional leaf node in such a way as to maximise the coherence of the text according to centering rules. This is an area of active research. Cheng (MS) has proposed a similar strategy for maintaining local coherence in a text planner using a genetic algorithm.</Paragraph> <Paragraph position="17"> Another issue is whether the CT rules, which ass-me a &quot;flat&quot; sequence of utterances, will remain valid for a hierarchical/); structured text plan. In fact it is an open research question whether CT should operate in this manher or whether the rules should be reformufated to take account of dominance in addition to precedence; di~erent positions are taken by Kameyama (1988) and Suri and McCoy (1994).</Paragraph> </Section> <Section position="2" start_page="72" end_page="77" type="sub_section"> <SectionTitle> 3.2 Sentence planning </SectionTitle> <Paragraph position="0"> According to the re-interpretation of CT which was sketched above, Sentence Planning may promote an entity for salience if it is the Cb of the current or .following utterance. There is dearly potential competition between these two factors which will be discussed shortly. The preference for rp~di~mg Cb as ~ can be hnplemented by choosing a verb form which projects G'~ in subject position. Some poes~ilities are franker alternation: buy/sd~ gi~/receive, borrow/qend etc, or pamivisation: your doctor ma~/ prescribe this medicine for gout vs this mtdicine ,~y be pr~cnbed .for gout.</Paragraph> <Paragraph position="1"> If we compare the attested example (2) with the constructed (3) it is clear that the former reads more naturally: .</Paragraph> <Paragraph position="2"> O) Hypoglycaemia (Cb) may cause faintness, sweating, shaking, weakness and confusion.</Paragraph> <Paragraph position="3"> It m~y be due to lack of food or too high a dose of the medicine.CONTINU8 It can be put right by eating or drinking something sugary.CONTINU~ null (pharmaceutical leaflet) (4) -..Hypoglycaemia may cause faintness, sweating, shaking, weakness and confusion.</Paragraph> <Paragraph position="4"> A lack of food or too high a dose of the medieinemay cause it.RETAIN Eating or drinking something sugary can put it right.RETAIN (modified example) Hurewitz (i998) examined the use of passives to promote cohesion and salience and found that in both written texts and speech approximately 75% of passives had either the CONTINUE or SMOOTH-SHIFT transition. In each case the effect is to promote Gb to Subject in accordance with the salience principle. (For written texts this proportion was not signiRcantly different from a control sample, whereas with the spoken passages the proportion was slightly higher than in the'control.) One system which explicitly makes Use of CT is the Caption Generation System (CGS) reported in (Mittal et al 1998). This system has a separate &quot;centering module&quot; which orders arguments within a clause to improve coherence of a text but does not influence the order of clauses. Thus only the salience principle is implemented and the centering task is located as part of Sentence Planning:. the speci-l!.~ed Centering Module receives Control after clauses have * been ordered and aggregated (op cit:454). The strategy adopted is to keep ~the highest-ranking forward-looking center of the first clause of the segment ... as the Cp(Ui) of a/l the following clauses in the same segment&quot; (op cit:456; my emphasis). Clearly this strategy isunlikely to generalise to a variety of domtt;na.</Paragraph> <Paragraph position="5"> As mentioned above there is a potential conmet betwe~ Co~t 3 (make Cb(U.+t) salient) and salience (make Cb(U,) aslient).</Paragraph> <Paragraph position="6"> As noted in Sect. 2.2 there may also be compe, tition between salience and Strube & Halm's cheapness principle, which can be seen as a stronger version of C3. There are different ways this conflict could be tadded in the cases where it arises aad I will consider one of them, which is to let C3 win out over salience.</Paragraph> <Paragraph position="7"> Consider a text with four clauses Ul - U4.</Paragraph> <Paragraph position="8"> which all have a and b among their arguments.</Paragraph> <Paragraph position="9"> Let a be the Cb of Ul- U2 and b the Cb of Us- U#. According to salience and C3, b will be Cp of /\]3 since it is Cb of that clause and the following one. For U2 there is competition between a and b to be Up, and this is decided by C3 in favour of b. Finally I a is chosen as Up of Ul. The result is as follows:</Paragraph> <Paragraph position="11"> In terms of the conventional transitions this works out as U~/U2: RET^IN U2/U3:</Paragraph> </Section> </Section> <Section position="7" start_page="77" end_page="78" type="metho"> <SectionTitle> SMOOTH SHIFT </SectionTitle> <Paragraph position="0"> us/u~: COnTINUa This is consistent with Strube and Hahn's (1996) observation that &quot;a II~rAIN transition ideally predicts a SMOOTH ssw'r in the following utterance&quot;. Brenuan et al (1987) make a very similar claim: A computational system for 9e-emtion would try to plan a retention as a signal of an impending shift, so that after a retention, a shift would be preferred rather than a continuation.</Paragraph> <Paragraph position="1"> Grosz et al (1995) give the following example of the ~Am - SHIFT pattern: (5) a. John has had trouble arranging his vacation. null b. He (Cb; John) cannot find anyone to take over his responsibilities.</Paragraph> <Paragraph position="2"> c. He (C/~, John) called up Mike yesterday to work out a plan. CONTINUB d. Mike hasannoyed him (Cb; John) alot recently, lt~rAIN e. He (Cb; Mike) called John at 5 am on Friday last week. smrr Under the approach outlined here, which assumes that the Cb is independently designated, * the system does not needto plan particular transition types or even to know about them; the desired effects come about as a result of Iocal decisions by the sentence planner using information from the text pl-nner.</Paragraph> <Paragraph position="3"> * Example (5) incidentally illustrates a limitation of CT in its Canonical version: the theory l'~lle w~rd a~ does not imply that these decisions are .taken in sequence.</Paragraph> <Paragraph position="4"> correctly predicts the pronominal choices in (5C - e) but has nothing to say about the decision to make Mike rather than John the Subject of (Sd). In fact, we can construct a variant of this text which follows centering rules more faithfully, though it does not read any more naturally: null (6) e.</Paragraph> <Paragraph position="5"> & John has had trouble arranging his vacation. null b. He cannot find anyone to take over his responsibilities. (Cb -- John) c. He called up Mike yesterday to work out a plan.</Paragraph> <Paragraph position="6"> (CONTINUE; Cb = John) d. He has been pretty annoyed with Mike recently.</Paragraph> <Paragraph position="7"> (colqzlm~; Cb John) He got a call from him (Mike) at 5 am on Friday last week. (CONTrol; Cb = John) If we examine the discourse structure of example (5), it seems that the discourse as a whole is about John but (Sd,e) form a parenthetical section which tells us something about M/ke. So although a blind application of centering rules would judge:(6) to be more coherent, (5) is in fact maximally coherent within the constraints of the structure of the discourse.</Paragraph> <Paragraph position="8"> To snmmarise: we assvme that for each utterance U, the text planner has identified Cb(U,), Cb(U.-1) and Cb(U.+d. The task for the sentence planner is to select a verb form or some other syntactic device to malise Cb(Un+l) as the most salient of those entities which are reAl|.~ed in U. and U.+t, and subject to this, to realise Cb(gJ'.) in the most salient position available. (See Figure 3,) So for example if Cb(Un) is not to be realised in U,/t, it will normally be realised as Cp(U,); but if it/8 to be realised in Un+I then the Cb of U,+t will be at least as highly ranked in Un as the Cb of Un. Tlfisstrategy predicts the Ralisation of M//~ rather than John as Cp in (5d) above.</Paragraph> <Section position="1" start_page="78" end_page="78" type="sub_section"> <SectionTitle> 3.3 Referring Expressions </SectionTitle> <Paragraph position="0"> The contribution of CT to Referring Expression (RE) generation is to decide on pronominalisation. Rule 1 (Fig. 2) which concerns pronominalisation has a strong and a weak formulation: tile strong one is that a pronoun should be used for the Cb if it is the same as the Cb of the previous utterance, the weak one is that the Cb must be pronominalised if anything is.</Paragraph> <Paragraph position="1"> In the context of generation it is probably safer to use the strong version. Brennan (1998) proposes, arguing from corpus analysis, that the Cb should be pronominalised only if it is Cp of the previous utterance. Robert Dale's RPICURE system employs the terminology of CT in Condeg nection with RE generation, as does the ILEX system reported in (O'Donnell et al 1998). Both these systems implement a variant of Rule 1 to determine whether to pronominalise the center (Dale) or Cb (ILEX), though in neither case is the center identified according to the standard apparatus of CT. In ILEX the Cb is designated by the text planner without reference to the content of the previous sentence, and it may be pronominal|.qed if it is the same as the previous sentence's &quot;Cb&quot;. Dale's IZPIOURE identifies the center with Uthat entity which is the result of the previously described operation&quot; (Dale 1992:170). Passoneau (1998) constructed input for a prototype generator by &quot;hypothesising&quot; a Cb for each proposition in a text based on the salience of entities in a Situation. Passoneau's system uses centering constraints to decide whether to realise entities as definite pronouns, minimal NPs or full NPs.</Paragraph> </Section> </Section> class="xml-element"></Paper>