File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/metho/81/p81-1012_metho.xml
Size: 22,995 bytes
Last Modified: 2025-10-06 14:11:23
<?xml version="1.0" standalone="yes"?> <Paper uid="P81-1012"> <Title>TWO DISCOURSE GENERATORS</Title> <Section position="1" start_page="0" end_page="0" type="metho"> <SectionTitle> TWO DISCOURSE GENERATORS </SectionTitle> <Paragraph position="0"/> </Section> <Section position="2" start_page="0" end_page="0" type="metho"> <SectionTitle> USC Information Sciences Institute WHAT IS DISCOURSE GENERATION? </SectionTitle> <Paragraph position="0"> The task of discourse generation is to produce multisentential text in natural language which (when heard or read) produces effects (informing, motivating, etc.) and impressions (conciseness, correctness, ease of reading, etc.) which are appropriate to a need or goal held by the creator of the text.</Paragraph> <Paragraph position="1"> Because even little children can produce multieententiaJ text, the task of discourse generation appears deceptively easy. It is actually extremely complex, in part because it usually involves many different kinds of knowledge. The skilled writer must know the subiect matter, the beliefs of the reader and his own reasons for writing. He must also know the syntax, semantics, inferential patterns, text structures and words of the language. It would be complex enough if these were all independent bodies of knowledge, independently employed. Unfortunately, they are all interdependent in intricate ways. The use of each must be coordinated with all of the others.</Paragraph> <Paragraph position="2"> For Artificial Intelligence, discourse generation is an unsolved problem. There have been only token efforts to date, and no one has addressed the whole problem. Still, those efforts reveal the nature of the task, what makes it diffic;,It and how the complexities can be controlled.</Paragraph> <Paragraph position="3"> In comparing two AI discourse generators here we can do no more than suggest opportunities and attractive options for future exploration.</Paragraph> <Paragraph position="4"> Hopefully we can convey the benefits of hindsight without too much detailed description of the individual systems. We describe them only in terms of a few of the techniques which they employ, partly because these tschnk:lUes seem more vaJuable than the system designs in which they happen to have been used.</Paragraph> </Section> <Section position="3" start_page="0" end_page="0" type="metho"> <SectionTitle> THE TWO SYSTEMS </SectionTitle> <Paragraph position="0"> The systems which we study here are PROTEUS, by Anthony Davey at Edinburgh \[Davey 79\], and KDS by Mann and Moore at ISI \[Mann and Moore 801. As we will see, each is severely limited and idiosyncratic in scope and technique. Comparison of their individual skills reveals some technical opportunities.</Paragraph> <Paragraph position="1"> Why do we study these systems rather then others? Both of them represent recent developments, in Davey's case, recently published.</Paragraph> <Paragraph position="2"> Neither of them has the appearance of following a hand-drawn map or some' other humanly-produced sequential presentation. Thus their performance represents capabilities of the programs more than cs4)abilities of the programmer. Also, they are relatively unfamiliar to the AI audience. Perhaps most importantly, they have written some of the best machine-produced discourse of the existing art.</Paragraph> <Paragraph position="3"> Rrst we identify particular techniclues in each system which contribute strongly to the quality of the resulting text. Then we compare the two Systems discussing their common failings and the possibilities for creating a system having the best of both.</Paragraph> </Section> <Section position="4" start_page="0" end_page="43" type="metho"> <SectionTitle> DAVEY'S PROTEUS </SectionTitle> <Paragraph position="0"> PROTEUS creates commentary on games of tic.tac-toe (noughts and crosses.) Despite the apparent simplicity of this task, the possibilities of producing text are rich and diverse. (See the example in Appendix .) The commentary is intended both to convey the game (except for insignificant variations of rotation and reflection), and also to convey the significance of each move, including showing errors and missed opportunities.</Paragraph> <Paragraph position="1"> PROTEUS can be construed as consisting of three 13rincipal processors, as shown in Figure 1.</Paragraph> <Paragraph position="2"> Move characterization employs a ranked set of move generators, each identified as defensive or offensive, and each identified further with a named tactic such as blocking, forking or completing a win. A move is characterized as being a use of the tactic which is associated with the highest-ranked move generator which can generate that move in the present situation* The purpose of move characterizaiton is to intefl:ret the facts so that they become significant to the reader. (Implicitly, the system embodies a theory of the Contrast arises between certain time-adiacent moves and also between an actual move and alternative possibilities at the same point. For example: * Best move VS. Actual move: The move generators are used to compute the &quot;best&quot; move, which is compared to the actual one. If the move generator for the best move has higher rank than any generator proposing the actual move, then the actual move is treated as s mistake, putting the best move and the actual move in contrast.</Paragraph> <Paragraph position="3"> .Threat VS. Block: A threat contrasts with an immediately following block. This contrast is a fixedreflex of the system. It seems accedteble to mark any goal pursuit followed by blocking of the goaJ as contrastive.</Paragraph> <Paragraph position="4"> Sentence scope is determined by several heuristic rules including I. Express as many contrasts as possible explicitly. (This leeds to immediate selection of words such as &quot;but&quot; and &quot;however&quot;.) 2. Limit sentences to ,3 clauses.</Paragraph> <Paragraph position="5"> 3. Put as many clauses in a sentence as possible.</Paragraph> <Paragraph position="6"> 4. Expmas only the worst of several mistakes.</Paragraph> <Paragraph position="7"> The main clause struotum is built before entering the grammar, Both the move characterization process and the use of contrasts as the principal ~ of sentence scope contribute a great deal to the quality of the resuRing text. However, Davey's central concern was not with these two 9rocessos but with the third one, sentence generation. His system includes an elaborate Systemic Grammar, which he de,scribes in datall in \[Devey 79\]. The grammar draws on work of Halliday \[Halliday 76\], Hudson \[Hudson 71\], Winograd \[Winograd 72\], Sinctalr \[Sinclair 72\], i~uddleston \[Huddlaston 71\] and F_ K. Brown, following H,..,d_~_n most closely.1 Hudson's work offers a number of significant advantages to anyone comddering implementing a discoume generation system.</Paragraph> <Paragraph position="8"> I. ComDrehensivaness- Its coverage of English is more extensive than comparable work.</Paragraph> <Paragraph position="9"> 2. Explicitness. the rules are spelled out in full in formal notation.</Paragraph> <Paragraph position="10"> 3. Unity. Since the grammar is defined in a single pubilcalion with a single 8uthomhiD, the is*ups of compatibility Of parts are minimized, It is intemsUng that Oevey does not employ the Systemk: Grlmm~lr dehvstJon rules at the highest level Although the grammer is defined in terms of the generation of sentences, Devoy entem it at the clause level with 8 sents~cs desc~Dtlon whiC/;h conforms to Systemic Grammar but was built by other means. A sentence st this level is temporal principally of Ctl-_,,~__. but the surface conjunotlens have already been chosen.</Paragraph> <Paragraph position="11"> Although Oavey real(as no claim, this may redrasent a gener~d result about text generation systems. Above some level of al:atnm~on in the text planning proces~ planning is not conditioned by the content of the grammar. The obvious place to exbeot planning tO become indegendertt of the grammar is at the sentence I~. But in both PROTEUS and KD.~ Operations independent of the grammar extend down to the level of independent clm within sentences. Top leve~ coniunctlons am not within such ci~,~__; so they are determined by Dlenning pr~ before the grammar is enter~l.</Paragraph> <Paragraph position="12"> It would be extremely awkward to implement Oavey'$ sentence sC/obe heuristics in a syetamic grammar. The formalism is not well suited for oDer~tion~ such as maximizing the total number of explicit contrastive (dements. However, the problem is not just a i~rololem with the formalism; grammars generally do not deal with this sort of operations, and so are ~oorly equil~ped to do so.</Paragraph> <Paragraph position="13"> them i~ no need to &quot;rw~nm&quot; it. G~mo~ ~ dlvid~d imo ~ Id~ ~ &C/~Iv~. mle-ll3t~lca~nL A sylmlm of choiC/.e~ (surJ1 u t~e ch~C/~ i~lt~men -d~ -ind &quot;~mm,e&quot; kT,~,-,~ de.minim *,vh~J~ cm &quot;ai~-ttve') is mech~ ~ other cboP~a ~d w is C/ondi~mC/. but cny ch~C/e. ~C/e mechU, &quot;.. ,.m,~m~rair,~L . Ru~ S~lUenc~ ~ femunl-emL ejcn ~ tl~ &quot;We~l.&quot; ~mlC/~ enet~le ieedC/~ m,l~C/ltu~ enl n~ tm'efenemmnL Although the computer scientist who tries to learn from \[Oavey 79} will find that it presents difficulties, the underlying system is interesting enough to be worth the trouble. Devey's imDiementation generally allam~s to be orthodox, conforming to \[Hudson 71\]. Davey regularizes some of the rules toward type uniformity, and thus reduces the apparent correspondence to Hudson's formulabons. However, the linguistic babe does not appear to have been compromised by the implementation.</Paragraph> <Paragraph position="14"> One of the major strengths of the work is that it takes advantage of s comprehenal~, explicit and linguistically justified grammar.</Paragraph> <Paragraph position="15"> Text quality is also enhanced by some simple filtering (of what will be expressed) based on demmdencies between known facts. Some facts dominate otherJ in the choice of what tO Say. If them is only one move on the board having a certain significance, say &quot;threat&quot;, then the move is described by its significance alone, e.g. &quot;you threatened me&quot; without location informatic, n, since the reader can infer the locations. Similarly, only the most significant defensive and offensive aspects of a move ate described even though all are known.</Paragraph> <Paragraph position="16"> The resulting text is divn) and of good quality. Although them ere awlo~mrdn __es,~__~ the immense advantage conferred by using a sophisticated grammar prevails.</Paragraph> </Section> <Section position="5" start_page="43" end_page="44" type="metho"> <SectionTitle> MANN AND MOORE'S KDS </SectionTitle> <Paragraph position="0"> Major Modules of KDS SOace precJudes a thocou0h description of KDS, but fuller deecriptione are mml~ie \[Mann and Moore 80\], \[Mann 79\], \[Moore 7% KDS consists Of five me~r modules, as indicated in Figure 2. A Frl~lmentM is re~oonalble for eXtnL~ing the relevant knowledge from the notation given to it and dividing that knowledge into small exl:nmalble units, which we call fragments or pmtosentanceC/ A Prod=~m Solver, a goal-Oumuit engine in the AI tradition, is responsible for seeotlng the I~eUntmlm~d style of me text and ~ for iml~l~ng the grol8 ol~glmlze~Ion onto the text accordlng to m8~ style. A Knowk~ge Rater removes protasentencas that need not be expressed because they would be redundant to the medsr.</Paragraph> <Paragraph position="1"> The I~est and moat interesting r~__,_,~e is the Hill Climber, which has three raspon~billtisC/ tO compose complex i:rotoasntences from simpM one~ tO judge relative quality among the units resulting from compo~dtton, and to repeatedly improve the set of protosentencas on the Ioasm of those judgments so thM it is of the highest eyeful quality. Finally. s very simple Surface Sentence Maker cremes the sentences of me final text out of protoaec~lmc~.</Paragraph> <Paragraph position="2"> The data flow of these modules can be thought of as a simple pipeline, each module processing the relevant knowledge in turn.</Paragraph> <Paragraph position="3"> The principal contributors to the quality of the output text are: 1. The Fragment and Compose Paradigm: The information which will be expressed is first broken down into an unorganized collection of subsententiai (C/oproximstely clause-level) propositional fragments. Each fragment is crested by methods which guarantee that it is expressible by a sentence (usually a very short one, This makes it possible to organize the remainder of the processing so that the text production problen~ is treated as an improvement problem rather than as a search for feasible solutions, a significant advantage.) The fragments are then organized and combined in the remaining processing.</Paragraph> <Paragraph position="4"> 2. Aggregation Rules: Clause-combining patterns of English are represented in a distinct set of rules. The rules specify transactions on the set of propositional fragments and previous aggregation results. In each transection several fragments are extracted and an aggregate structure (capable of representation as a sentence) is inserted. A representative rule, named &quot;Common Cause,&quot; shows how to combine the facts for &quot;Whenever C then X&quot; and &quot;Whenever C then Y&quot; into &quot;Whenever C then X and Y&quot; at s propositional level.</Paragraph> <Paragraph position="5"> 3. Preference Assessment: Every propositional fragment or aggregate is scored using a set of scoring rules. The score represents s measure of sentence quality.</Paragraph> <Paragraph position="6"> 4, Hill Ctimbing: Aggregation and Preference Assessment are aJternated under the control of a hill-climbing algorithm which seek.'s to maximize the overall quality of the collection, i.e. of the complete text. This allows a clean separation of the knowledge of what could be said from the choice of whet should be said.</Paragraph> <Paragraph position="7"> 5. Knowledge Filtering: Propositions identified by an extolicit model of the Reader's knowledge as known to the reader are not exl:resasd.</Paragraph> <Paragraph position="8"> The knowledge domain of KDS' largest example is a Fire Crisis domain, the knowledge of what happens when there is a fire in a computer room. The task was to cause the reader, a computer operator, to know what to do in all contingencies of fire.</Paragraph> <Paragraph position="9"> SYSTEI~ 1 (~OMPARISONS The most striking impression in comparing the two systems is that they have very little in common. In particular, 1. KDS has sentence scoring and a quslity.based selection of I~ow to say things; PROTEUS has no counterp;u't.</Paragraph> <Paragraph position="10"> 2. PROTEUS has a sophisticated grammar for which KOS has only a rudimentary counterpart, 3. PROTEUS has only a dynamic, redundancy-based P, nowledge filtering, whereas the filtering in KOS removes principally St=~tic, foreknown information.</Paragraph> <Paragraph position="11"> 4. KDS has clause-combining rules which make little use of conjunctions, whereas PROTEUS has no such rules but makes elaborate use of coniunctions.</Paragraph> <Paragraph position="12"> 5. KOS selects for brevity above all, whereas PROTEUS selects for contrast =hove all.</Paragraph> <Paragraph position="13"> 6. PROTEUS takes great advantage of fact significance assessment, which KDS does not use.</Paragraph> <Paragraph position="14"> They have little in common technically, yet both produce high quality text relative to predecessors. This raises an obvious question-- Could the techniques of the two systems be combined in an even more effective system? There is one prominent exception to this general lack of shared functions and characteristics, Recent text synthesis systems \[Davey 79\], \[Mann end Moore 80\], \[Weiner 80\], \[Swartout 77\], \[Swartoutthesis 81\], all include a facility for keeping certain facts or ideas from being expressed. There is an implicit or explicit model of the reader's knowledge. Any knowledge which is somehow seen as obvious to the reader is suppressed.</Paragraph> <Paragraph position="15"> All of the implemented facilities of this sort are rudimentary; many consist only of manually-ornduced lists or marks. However, it is clear that they cover a deep intellectual problem. Discourse generation must make differing uses of what the reader knows and what the reader does not know.</Paragraph> <Paragraph position="16"> It is absolutely essential to avoid tedious statement of &quot;the obvious.&quot; Proper use of presupposition (which has not yet been attempted computationally) likewise depends on this knowledge, and many of the techniques for maintaining coherence depend on it as well. But identification of what is obvious to a reader is a difficult and mostly unexplored problem. Clearly, inference is deeply involved, but what is &quot;obvious&quot; does not match what is validly inferable. It appears that as computer-generated texts become larger the need for a robust model of the obvious will increase rapidly.</Paragraph> </Section> <Section position="6" start_page="44" end_page="45" type="metho"> <SectionTitle> POSSIBILITIES FOR SYNTHESIS </SectionTitle> <Paragraph position="0"> This section views the collection of techniques which have been discussed so far from the point of view of a designer of a future text synthesis system. What are the design constraints which affect the possibility of particular combinations of these techniques? What combinations are advantageous? Since each system represents a compatible collection of techniques, it is only necessary to examine compatibility of the techniques of one system within the framework of the other.</Paragraph> <Paragraph position="1"> We begin by examining the hypothetical introduction of the KDS techniques of fragmentation, the explicit reader model, aggregation, preference scoring and hill climbing into PROTEUS. We then examine the hypothetical introduction of PROTEUS' grammar, fact significance assessments and use of the contrast heuristic into KDS. Finally we consider use of each system on the other's knowledge domain.</Paragraph> <Paragraph position="2"> Introducing KDS teohniques into PROTEUS Fragment and Compose is clearly usable within PROTEUS, since the information on the sequence of moves, particular move locations and the significance of each move all can be regarded as composed of many incleDendent propositions (fragments of the whole structure.) However, Fragment and Compose appears to give only small benefits, principally because the linear sequences of tic-tac-toe game transcripts give an acceptable organization and do not preclude many interesting texts.</Paragraph> <Paragraph position="3"> Aggregation is also useable, and would appear to allow for a greater diverSity of sentence forms than Oavey's Secluential assembly torocedures allow. In KDS, and presumably in PROTEUS as well, aggregation rules can be used to make text brief, in effect, PROTEUS already has some aggregation, since the way its uses of conjunction shorten the text is similar to effects of aggregation rules in KDS.</Paragraph> <Paragraph position="4"> Prefei'ence judgment and Hill climbing are interQependent in KDS. Introducing both into PROTEUS would appear to give great improvement, especially in avoiding the long awkward referring phrases which PROTEUS i=roduced. The system could detect the excessively long constructs and give them lower scores, leading to choice of shorter sentences in those cases.</Paragraph> <Paragraph position="5"> The Explicit Reader model could also be used directly in PROTEUS; it would not help much however, since relatively little foreknowledge is involved in any tic-tac-toe game commentary/.</Paragraph> <Paragraph position="6"> Introducing PROTEUS techniques into KDS Systemic Grammar could be introduced into KDS to great advantage. The KDS grammar was deliberately chosen to be rudimentary in order to facilitate exploration above the sentence level. (In fact. KDS could not be extended in any interesting way without ulxJrading its grammar.) Even with a Systemic Grammar in KDS, aggregation rules would remain, functioning as sentence design elements.</Paragraph> <Paragraph position="7"> Fact significance assessments are also compatible with the KDS design. As in PROTEUS they would immediately follow aoduialtion of the basic grogositianeL They could improve the text significantly.</Paragraph> <Paragraph position="8"> The contrast heuristic (and other PROTEUS heuristics) would fit well into KDS, not as an a priori sentence design device but as a basis for assigning preference. Higher score for contrast would improve the text.</Paragraph> <Paragraph position="9"> In summary, the principal techniques appear to be completely compatible, and the combination would surely produce better text than either system alone.</Paragraph> <Paragraph position="10"> Exchange of Knowledge Domains The tic-tac-toe domain would fit early into KDS` but the KOS text-organization Drocesles (not discuased in this I:~ger) would have littJe to do. The fire crisis domain would be too complex for PROTEUS. It involves several actorS at once, several parallel contingencies and no single clear organizing principle. PROTEUS lacks the necessary text-organization methods.</Paragraph> </Section> <Section position="7" start_page="45" end_page="46" type="metho"> <SectionTitle> SHARED SHORTCOMINGS </SectionTitle> <Paragraph position="0"> These systems share (with many others) the i=rimitive state of the computer.be,sad discourse-generation a~. Their groce~,~l are \[=rimarily devoted to activities that go without notice among literate I~eogle. The deeper linguistic and metorical phenomena usually associated with the term &quot;discourse&quot; are hardly touched. These systems make little attempt at coherence, and they do not respond in amy way to the coherence (or lack of it) which they achieve.</Paragraph> <Paragraph position="1"> Presupposition, topic, focus, theme, the pro~er role of inference, imglicature, direct and indirect Sl:~ech act performance and a host of other relevant concepts all go unrepresented. Even wome, the underlying conceotual agpars.tus in both systems is extremely adhoc and idiosyncratic, severely limiting the I=OSSiblities for using general knowledge of the semantics of English.</Paragraph> <Paragraph position="2"> Despite these deficiencies, the systems produce relatively smooth readable texL They are significant principally as collections of methods which may well survive to become l=arts of more competent and general.purOose systems of the future.</Paragraph> </Section> class="xml-element"></Paper>