<?xml version="1.0" standalone="yes"?>
<Paper uid="P79-1025">
  <Title>RESPONSE GENERATION IN QUESTION - ANSWERING SYSTEMS</Title>
  <Section position="3" start_page="0" end_page="99" type="metho">
    <SectionTitle>
2. PROBLEMS OF RESPONSE GENERATION
</SectionTitle>
    <Paragraph position="0"> To understand how this can simplify response generation, we must consider a few of the problems of generating responses. The basic mechanism of answer generation is very simple. Yes-no questions are translated into predicate formulas; if the formula evaluates to ~r~e, print &amp;quot;yes&amp;quot;, else &amp;quot;no&amp;quot;. Wh-questions translate into setformers; the extension of the set is the answer to the question.</Paragraph>
    <Paragraph position="1"> One complication is embedded set-formers. An embedded set-former arises when the question contains a quantifier or conjunction with wider scope than the question word.</Paragraph>
    <Paragraph position="2"> For example, the question Which students passed the French exam and which failed it? will be translated into two set-for~ers connected by G~d: {s E set-of-students I passed (s, French exam)} ~d {s E set-of-students I failed (s, French exam)} It would be confusing to print the two sets by themselves. Instead, for each set to be printed, we take the predicate satisfied by the set, add a universal quantifier over the extension of the set, and convert the resulting formula into an English sentence. For our example, this would mean</Paragraph>
    <Paragraph position="4"> where S 2 = {s E set-of-students I failed(s,French exam)} which would generate a response such as John, Paul, and Mary passed the French exam; Sam and Judy failed it.</Paragraph>
    <Paragraph position="5"> The same technique will handle set-fo~aers within the scope of quantifiers, as in the sentence Which exams did each student take? Additional complications arise when the system wants to add some words or explanation to the direct answer to a question. When asked a yes-no question, a helpful question-answering system will try to provide more information than just &amp;quot;yes&amp;quot; or &amp;quot;no&amp;quot;. In our system, if the outermost quantifier is existential -- (3x ~ S) C(x) --we print {x E S I C(x\]}; if it is universal -(Vx E S) C(x) --we print {x E S I 7C(x)}. For example, in response to Did all the students take the English exam? our system will reply NO, John, Mary, and Sam did not.</Paragraph>
    <Paragraph position="6"> When the outermost quantifier is the product of predicate expansion, however, it is not sufficient to print the corresponding set, since the predicate which this set satisfies is not explicit in the question. For example, in the data base of radiology reports we are currently using, a report is negGtiue if it does not show any positive or suspicious medical findings. Thus the questiQn Was the X-ray negative? would be translated into negative iX-ray) and expanded into (Vf E medical-findings\] ~show(X-ray,f) sO the system would compute the set {f E medical-findings \[ show(X-ray,f)} Just printing the extension of this set, NO p ~tastases.</Paragraph>
  </Section>
  <Section position="4" start_page="99" end_page="99" type="metho">
    <SectionTitle>
QUESTION ANALYSIS RESPONSE SYNTHESIS
QUESTICN RESPONSE
</SectionTitle>
    <Paragraph position="0"> string analysis I PARSE TREE decomposition generative transformations transformational OPERATOR-OPERAND-ADJUNCT TREE OPERATOR-OPERAND'~ans~T TREE quantifier analysis arise tO op-op-adj tree PREDICATE CALCULUS FORMICA PRED. CALC. ~(P~degU~Sd ~ ged)  would be confusing to the user. Rather, by using the sam~ rule as before foe printing a set, we produce a response such as No, ~he X-ray showed metastases.</Paragraph>
    <Paragraph position="1"> Similar considerations apply to yes-no questions wi~h a conjunction of Wide scope.</Paragraph>
  </Section>
  <Section position="5" start_page="99" end_page="100" type="metho">
    <SectionTitle>
3. DESIGN AND IMPLEMENTATION
</SectionTitle>
    <Paragraph position="0"> As we noted earlier, our question-analysis procedu~ is composed of several stages which transform ~he question t.hrou~h a se=ias of represen~ationsx sentence, pine tree, operator-operand-ad:Junct tree (~ans formational deconpoei~Lon), predic&amp;te calculus fornula, retrieval request. TIlLs mul~L-#tage structure has made At straightfor~a~d to design our sen~nce geuere~inn, or synthesis, pro~edttre, which const~cts ~he sm representations in ~he reveres order from the analysis procedure * In designing ~he synthesis procedure, ~he first decision we had to make weal which representation should the synthesls p~ocedm accept as input? The retrieval procedure instant.lares varifies in ~he re~leval request, so it might seem ~ost s~.raightforwaurd for ,':hit re~ieval procedure to pass to ~he synthesis pz~c~du~ a modified retrieval request representation. Al~rna~ively, we could keep track of the correspondence between components of ~he retrieval request and com~nen~ of the parse t~, ope=a~o~-operand-adJunct tree, or predicate calculus representation. Then we could subs~.itute ~he results of retrieval back into one of ~he latter representations and have ~-he synthesis component work fz~m there. This would simplify the synthesis procedure, since its s~ar~ing point would be &amp;quot;closer&amp;quot; to ~he sentence representation.</Paragraph>
    <Paragraph position="1"> A beullo z~equi=nt for using one o! ~eee rtpresentatlona is ~hen the ability to emtLblish a correspondence between those ccn~onen~ of the retrieval request which may be significant in genera~Lng a response and components of ~he other representation. Because predicate e~rmlon introduces variables and relations which are no~ present earlier but which may have to be used in the response, we could not use a representation closer to the surface than the outpot of predicate expansion (a predicate calculus formula). Subsequent s~aqes of ~he analysis procedure, hcMevtr, (translation to retrieval request and simplification), do not introduce structures which wall be needed in generating responses. We ~herefore choose tO simpllfy Stir syn1~lesizer by using as its input the output of predicate expansion \[instantiated wi~h the result.s of retrieval) rather than ~he retrieval z~quest.</Paragraph>
    <Paragraph position="2"> The synthesis procedure has ~hree stages, which correspond to three of the staqes of the analysis procedure (Fi~IEt l). First, noun phrases which can be pronominalized are identified. Second, ~he predicate calculus expression is translated into an operator-operand-adJunct tree. Finally, a set of gtnerative transformations are applied to produce a parse ~e, whose frontier is the generated sentence.</Paragraph>
    <Paragraph position="3"> The correspondence between analysis and synthesis extends to ~he details of the analytic and generative transfoEmatlonal stages. Bo~h stages use the same prelim, ~he ~ransforma~ional component of ~he Linguistic String Parser \[3\]. MidSt analytic r.Tansformations have corresponding members (performing ~he reverse transformations) in ~he generative set. These correspondences have greatly facilitated ~he design and coding of our generative s t age.</Paragraph>
    <Paragraph position="4">  One problem in transforming phrases into predicate calculus and than regenerating them is that syntactic paraphrases will be mapped into a single phrase (one of the paraphrases). For example, &amp;quot;the negative X-rays&amp;quot; and &amp;quot;the X-rays which were negative&amp;quot; have the same predicate calculus representation, so only one of these structures would be regenerated. This is undesirable in generating replies ~ a natural reply will, whenever possible, employ the saume syntactic constructions used in the question. In order to generate ~uch natural replies, each predicate and quantifier which is directly derived from a phrase in the question is tagged with the syntactic structure of that phrase. Predicates and quantifiers not directly derived from the question (e.g., those produced by predicate expansion) are untagged. Generative transfora~tions usa these tags to select the syntactic str~ture to be generated. For untagged constructs, a special set of transformations select appropriate syntactic structures (this is the only set of generative transformations without corresponding analytic transformations ).</Paragraph>
  </Section>
  <Section position="6" start_page="100" end_page="100" type="metho">
    <SectionTitle>
4. OTHER EFFORTS
</SectionTitle>
    <Paragraph position="0"> AS we noted at the beginning, few question-answering systems incorporate full-fledged sentence generators I fixed-format and tabular responses suffice for systems handling a limited range of quantification, conjunction, and inference. However, several investigators have developed procedures for generating sentences from internal reprsentations such as semantic nets and conceptual dependency structures \[4,5,6,7\].</Paragraph>
    <Paragraph position="1"> Sentence generation from an internal representation involves at least three types of operations: o recursive sequencing through the nested predicate structure o sequencing through the components at one level of the structure o transforming the structure or generating words of the target sentence.</Paragraph>
    <Paragraph position="2"> The last function is performed by LISP procedures in the systems cited (in our system it is coded in Restriction Language, a language specially designed for writing natural-language grammars). The first two functions are either coded into the LISP procedures or are performed by an augmented transition network (ATN). Although the use of ATNs suggests a parallelism with recognition procedures, the significance of the networks is actually quite different; a path in a recognition ATN corresponds to the concatenation of strings, while a path in a generative ATN corresponds to a sequence of arcs in a semantic network. In general, it seems that little attention has been focussed on developing parallel recognition and generation procedures.</Paragraph>
    <Paragraph position="3"> Goldman \[5\] has concentrated on a fourth type of operation, the selection of appropriate words (especially verbs) and syntactic relations to convey particular predicates in particular contexts. Although in general this can be a difficult problem, for our domain (and probably for the domains of all current question-answering systems) this selection is straightforward and can be done by table lookup or simple pattern matching.</Paragraph>
    <Paragraph position="4"> 5. c0Nc~vBz0.</Paragraph>
    <Paragraph position="5"> We have discussed in this paper some of the problems of response generation for question-answering systems, and how these problems can be solved using a procedure which ganezates sentences from their internal representation. We have Driefly described the structure of this procedure and noted how our multistage processing has made it possible to have a high degree of parallelism between analysis and synthesis. We believe, in particular, that this parallelism is more readily achieved with our separate stages for parsing and transformational decomposition than with ATN recognizers, in which these stages are combined.</Paragraph>
    <Paragraph position="6"> The translation from predicate calculus to an operatoroperand-adjunct tree and the generative transformations are operational; the pronom/nalization of noun phrases is being implemented. We expect that as our question-answering system is further enriched (e.g., to recognize presupposition, to allow more powerful inferencing rules) the ability to generate full-sentence responses will prove increasingly valuable.</Paragraph>
  </Section>
class="xml-element"></Paper>