<?xml version="1.0" standalone="yes"?>
<Paper uid="T75-1005">
  <Title>WHAT MAKES SAM RUN? SCRIPT BASED TECHNIQUES FOR QUESTION ANSWERING</Title>
  <Section position="1" start_page="0" end_page="0" type="metho">
    <SectionTitle>
WHAT MAKES SAM RUN?
SCRIPT BASED TECHNIQUES
FOR QUESTION ANSWERING
</SectionTitle>
    <Paragraph position="0"/>
  </Section>
  <Section position="2" start_page="0" end_page="0" type="metho">
    <SectionTitle>
I. INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> The A~I. group at Yale has developed a program SAM (ScriptApplier Mechanism) which models processes in story understanding~ The basic theoretical construct underlying SAM is the notion of a script (Schank &amp; Abelson 75)~ Script based knowledge is mundane information which tends to lie in the periphery of consciousness~ Going to a restaurant, watching a football game, taking a bus, and paying bills are examples of script activities. Scripts describe situations which are frequently encountered with negligible or predictable variations~ People in situational scripts are seldom conscious of script related actions~ The acts which define a script are things which people automatically do or expect to occurs Since a person who has not seen a football game will not fully comprehend stories about football games, we assume script based knowledge is used in story understandings SAM utilizes a restaurant script in order to paraphrase, summarize, and answer questions concerning stories about eating out in a restaurant~ The question answering techniques described in this paper were devised as SAM evolved~ The following story is an input story which SAM has processed: John went to a restaurant~ The hostess seated Johns The hostess gave John a menus The waiter came to the table~ John ordered lobsters John was served quickly~ John left a large tip~ John left the restaurants SAM responds in a sample question answering session:  Q~ Why did John go to a restaurant? A. So John could eat.</Paragraph>
    <Paragraph position="1"> Q~ Did the waiter give John a menu? A. No, the hostess gave John a menu.</Paragraph>
    <Paragraph position="2"> Q. Why did the hostess give John a menu? A. So John could orders Q. What happened when the hostess gave John a menu? A~ John read the menu. The waiter saw that John was at the table~ The waiter went to the table~ Q. What did John eat? A~ Lobster.</Paragraph>
    <Paragraph position="3"> Q. Who brought John the lobster? A. The waiter brought John the lobster. Q. What happened when John ate the lobster?  A, John indicated to the waiter that he would like a checks The waiter gave John the checks John remembered that the waiter had served the lobster quickly~ John left the waiter a large tips Q~ Did John enjoy the lobster? A~ Probably~ Q. Who paid the bill? A~ John.</Paragraph>
    <Paragraph position="4"> Q. Why did John pay the bill? A, So he could leave.</Paragraph>
  </Section>
  <Section position="3" start_page="0" end_page="0" type="metho">
    <SectionTitle>
II. INTERPRETING QUESTIONS:
FOCUS
ESTABLISHING
</SectionTitle>
    <Paragraph position="0"> A recurring issue in natural language processing which is particularly evident in question answering is the problem of focus~ What is interesting about a statement? Where is attention directed? What aspects of a statement are significant? Many questions have more than one acceptable answer and to a large extent people manage to agree on which answers seem most natural. The appropriateness of a response is a function of focus~ Questions usually have a focus (or emphasis) which renders one response more appropriate than another~ Consider the sample input story above and the question &amp;quot;Did the waiter give John a menu?&amp;quot; The most natural answer to this is &amp;quot;No, the hostess gave John a menu.&amp;quot; To arrive at this response we must go beyond the original yes or no question and answer a second question &amp;quot;Who gave John a menu?</Paragraph>
  </Section>
  <Section position="4" start_page="0" end_page="0" type="metho">
    <SectionTitle>
DID THE WAITER GIVE JOHN A MENU? / \
YES NO \
WELL THEN, WHO DID? \
THE HOSTESS
</SectionTitle>
    <Paragraph position="0"> The interesting problem here is how we picked up this second questions By going on to ask who gave John the menu we have interpreted the original question to focus on the actor who executes the transfer of the menus How did this emphasis arise? We could have gone on to ask &amp;quot;Well then, what did the waiter give John?&amp;quot; or even &amp;quot;Well then, what did the waiter do?&amp;quot; Emphasis in this direction would elicit answers like: No, the'waiter gave John a checks No, the waiter brought John his meal~ No, the waiter took John's orders While each of these'is an acceptable answer, they are less natural than: No, the hostess gave John a menus So to arrive at the best answer we have to focus on the actor being the most important or interesting component of the question.</Paragraph>
    <Paragraph position="1"> How do we do this?</Paragraph>
  </Section>
  <Section position="5" start_page="0" end_page="0" type="metho">
    <SectionTitle>
CONJECTURE:
WHEN GIVEN A CHOICE OF FOCUS,
TAKE VARIATION OVER EXPECTATION.
</SectionTitle>
    <Paragraph position="0"> Thisconjecture is based on the premise that variables are more interesting than constants, i.e. the unexpected is more worthy of attention than the expected.</Paragraph>
    <Paragraph position="1"> In general, implementing such a rule may be hard, but within the context of a script, it's easy. Every script is characterized by a set or sequence of actions specific to that script. In a restaurant the patron expects to receive a menu, sit down at a table, order, eat, pay, etc. Expected acts such as these are constants within the script. We are surprised to hear things like: John went to a restaurant but he didn't eat.</Paragraph>
    <Paragraph position="2"> John went to a restaurant and didn't pay the check.</Paragraph>
    <Paragraph position="3"> When John went to the restaurant he sat on the floor.</Paragraph>
    <Paragraph position="4"> In these cases our expectations have been violated because the script constants of eating, paying, and sitting at a'table have been contradicted or over-ruled~ When given a question, we examine the question statement in order to establish which components comprise a script constant. Once we know which script constant matches our question statement, we take the object of focus to be that element of the question statement which is not a part of the script * constant (if one exists). Since this extraneous element should be a script variable (being non-constant) we have established the appropriate focus.</Paragraph>
    <Paragraph position="5"> In our example, the act of transferring a menu to the patron is a script constant. We expect an ATRANS of the menu to John. Who gives him the menu is a script variable since we would not be surprised to hear it was the hostess or a waiter. Perhaps even the cook gave him the menu or he got it himself. A similar situation occurs when John gets the check. We expect him to get a check, but the actor of the transfer is variable. Of course these variables assume default bindings in the absence of explicit data; unless I hear otherwise, I assume the waiter brings the check.</Paragraph>
    <Paragraph position="6"> Whenever the answer to a did-question is &amp;quot;No&amp;quot;, it is natural to augment the negative response with a correction or explanation of some sort. There are two classifiable situations when the initial response is negative. In one case a focus exists and can be determined by our rule (as in the waiter giving John the menu). In the other case no focus is found in the question. No focus is found in &amp;quot;Did John 17.</Paragraph>
    <Paragraph position="7"> sit down?&amp;quot; or &amp;quot;Did John pay the check?&amp;quot; because the actions in question are full script constants with no possibility of variation within the expectations of the script. In such instances where no focus exists the expectations of the script have been violated. (John should have sat down and he should have paid the checks) Whenever expectations are violated, the natural question to be asked is &amp;quot;How come?&amp;quot; This is equivalent to &amp;quot;Why didn't John sit down?&amp;quot; or &amp;quot;Why didn't John pay the check?&amp;quot; Answers to these will either be wierd-oriented answers or interference-oriented answers (see part IV). When the original question statement does have a focus, the answer is found by matching the constant part of the statement against the script acts. Once a script act is matched, we instantiate the variable b~ndings and return the resulting conceptualization as the best augmentative answer.</Paragraph>
    <Paragraph position="8"> So in applying the rule of variation over expectation (V/E) to the question &amp;quot;Did the waiter give John a menu&amp;quot; we identify giving John a menu as a script constant and the actor binding as a script variable.</Paragraph>
    <Paragraph position="9"> Therefore the focus of attention falls on the actor, and we augment the minimally correct response &amp;quot;No&amp;quot; with the most natural addition, &amp;quot;the hostess gave John a menu.&amp;quot; Script variables also occur in instrumentality, manner, mode, and time fillers, e.g. &amp;quot;Why did John drive to the restaurant?&amp;quot; If we're in the restaurant script, we expect John to get to the restaurant. How he gets there is variables Applying V/E to the question, we establish the focus to be on driving. &amp;quot;Did John eat his meal in 10 minutes?&amp;quot; We expect John to eat his meal. How long it takes him is variable. Applying V/E we determine the focus to be on the time it took John to eat. If more than one variable occurs in a question, some hierarchy must be invoked to establish the focus. In answering &amp;quot;Why did John drive to the restaurant at 4:00A.M~?&amp;quot; we presumably find that going at 4:00A.M.</Paragraph>
    <Paragraph position="10"> is more interesting than driving. People need to be able to resolve focus in order to understand what a question is driving at~ &amp;quot;Why did John roller skate to the restaurant at 4:00A.M.?&amp;quot; tends to have the effect of two different questions: &amp;quot;Why did he roller skate?&amp;quot; and &amp;quot;Why did he go at 4:00A.M.?&amp;quot; The ambiguity in this question results from the ambiguity of focus. We have trouble deciding which is more interesting, the mode of transportation, or the hour. When focus is not resolved a question seems confused or ill-defined.</Paragraph>
  </Section>
  <Section position="6" start_page="0" end_page="0" type="metho">
    <SectionTitle>
III~ ANSWERING WHAT-HAPPENED-WHEN-QUESTIONS
</SectionTitle>
    <Paragraph position="0"> Part of SAM's internal representation for the input story is a causal chain of conceptual dependency diagrams (Schank 75).</Paragraph>
    <Paragraph position="1"> A causal chain is an alternating sequence of states and actions in which each state enables the following action and each action results in the following state.</Paragraph>
    <Paragraph position="2"> Understanding the relationship between two conceptualizations is at reflected by the ability causal chain between them~ least in part to construct a If I hear that John had a bad car accident, I am not surprised to hear that his car was wrecked, or that he was injured, or that Mary doesn't want to ride with him any more. These all relate to the accident as causal consequences~ Even when expectations are violated as in &amp;quot;John was in a car accident. He was overjoyed.&amp;quot; We try to make sense out of it by constructing the most feasible causal chain we can: Maybe the car was worthless anyway and John was not too badly hurt but he was insured and they're giving him a big settlement and he can really use the money for some reasons When SAM processes an input story, causal chains are established between consecutive input conceputalizations~ Generating causal chains in a situational script is easy because the script contains all the expected actions which will fill in a chain between any two acts of the scripts A major part of the script data base consists of various causal paths throughout portions of the restaurant script. When SAM receives a what-happened-when question, it matches the act in question against its corresponding script counterpart and simply returns that portion of the causal chain representation of the story which begins with the act in question and ends at the next conceptualization mentioned in the input story~</Paragraph>
  </Section>
  <Section position="7" start_page="0" end_page="0" type="metho">
    <SectionTitle>
IV. ANSWERING WHY-QUESTIONS
</SectionTitle>
    <Paragraph position="0"> Once we have interpreted a question by establishing its focus, we still have to answer the questions The most interesting class of questions in this respect seem to be why-questions~ There appear to be roughly four types of answers to why-questions~ Two are script based and two require data outside of scripts~ The script based answers have implementable heuristics</Paragraph>
    <Paragraph position="2"> In any script context we may get an unexpected occurrence which is relevant to the scripts Answers dependent on the wierd occurrence may relate back to it in a number of ways. Consider the following examples: Ex.1: John went to a restaurant and broke his wrist when the chair he was sitting on collapsed. John sued the restaurant.</Paragraph>
    <Paragraph position="3"> Q. Why did John sue the restaurant? A. His chair collapsed and he was injured.</Paragraph>
    <Paragraph position="4"> Ex.2: John went to a restaurant and found out that everyone got a free drink of their choicer John ordered the cheapest drink they had.</Paragraph>
    <Paragraph position="5"> Q. Why did John order a cheap drink? Adeg I have no idea.</Paragraph>
    <Paragraph position="6"> Ex.3: John went to a restaurant and ordered a hamburger. When the waiter was carrying it from the kitchen he dropped it on the floors John ate the hamburger and lefts Q~ Why did John eat the hamburger? A~ He must not have known it was dropped~ In Ex~1, a causal chain can be constructed between the wierd occurrence and the act in questions The act in question is consistent with our expectations after the wierd ocurrence; the chair collapsing and resulting injury are the causal antecedents of John suing the restaurant~ In Ex~2, no causal chain can be constructed between the wierd occurrence and the act in question, so we are at a loss to answer the questions In Ex~3, our expectations are violated as in Ex~2, but here we can account for the discrepancy, and we use the explanation as our answer~ We expect a causal chain which includes John refusing the hamburgers Since this construction is contradicted when we hear that John ate the hamburger, we reconstruct the causal chain and account for the validity of the new construction in our answers The difficulties in arriving at answers of this type are apparent: I) Since scripts normally run in the background of a story line and are rarely in the foreground, we need to be able to identify wierd occurrences as distinguished from commonplace occurrences which are irrelevant to the script~ For example, how do we know that smoke coming from a wall is wierd and smoke coming from an open barbecue pit in a steak house is OK~ Similarly, if John stands up and starts making a toast, this is not wierd unless perhaps there is no one else at his tables Some very strong inference mechanisms or higher level structures must come into play in the problem of recognizing wierdness~ 2) We need to know if the act in question is consistent with the wierd ocurrence (as in Ex~1) or if it violates expectations (as in Ex~2)~ This is equivalent to knowing when a causal chain can be constructed between two conceptualizatons and when no such chain exists~ 3) If our expectations have been violated, we need to be able to construct feasible explanations whenever possible (as in Ex~3). Constructing a feasible explanation is equivalent to construting a believable causal chain. In Ex~3, the causal chain behind our explanation is arrived at by suppressing the inference that John knew about the waiter dropping his hamburgers Since this is the key to a valid causal construction, we zero in on it for our answers In general the problems of recognizing an unusual occurrence or constructing a causal chain are major issues which are far  Questions like &amp;quot;Why did John walk to the restaurant?&amp;quot; or &amp;quot;Why did John order a hamburger?&amp;quot; require data from outside of the script. Little can be said about these general script exits until we have developed some data structures outside of scripts~ (3). GOAL-ORIENTED ANSWERS (script based) These occur in one of two ways: I) The focus Of the question (as determined by V/E) is a variable whose default binding is a character in the script.</Paragraph>
    <Paragraph position="7">  2) The question has no focus (via V/E)~ QI: Why did John go to the restaurant? (focus:nil) Q2: Why did John go to a table? (focus:nil) Q3: Why did the hostess give John a menu? (focus:hostess) Q4: Why did the waiter give John a check? (focus:waiter) Q5: Why did John pay the check? (focus:nil)  Each script has a static goal structure which consists of scriptgoals and a set of subgoals. The subgoals may exist on different levels of detail. The hierarchy of the restaurant script has only one level of subgoals and one scriptgoal. The goal structure for the restaurant script looks like:</Paragraph>
  </Section>
  <Section position="8" start_page="0" end_page="0" type="metho">
    <SectionTitle>
EATING
GOING TO BEING ORDERING PAYING --~ LEAVING
RESTAURANT SEATED / / /
GOING TO GETTING GETTING
A TABLE A MENU A CHECK
</SectionTitle>
    <Paragraph position="0"> The top level of this structure contains the scriptgoal of eating~ The second level represents the subgoals of the restaurant script and the third level contains other acts found in the script (not all shown).</Paragraph>
    <Paragraph position="1"> Goal-oriented answers are derived by the following rules: a) If the act in question is a subgoal, go to the next goal in the next level up.</Paragraph>
    <Paragraph position="2"> If no such goal exists, go to the next goal in the same level.</Paragraph>
    <Paragraph position="3"> b) If the act in question is not 'a subgoal, go to the next goal in the lowest level of subgoals.</Paragraph>
    <Paragraph position="4"> c) If the act in question is a scriptgoal, there is nogoal-oriented answer. It probably has an externally-oriented answer.* Using the goal algorithm we  Notice that this goal structure is oriented with respect to the central character of the script, in this case the restaurant patron. If we were in a restaurant script with respect to the waiter we would answer Q4 with something like &amp;quot;Because it's his Job&amp;quot; or &amp;quot;Because John was done eating&amp;quot;. Intrinsic to all scripts is a point of view.</Paragraph>
  </Section>
  <Section position="9" start_page="0" end_page="0" type="metho">
    <SectionTitle>
(4) INTERFERENCE-ORIENTED ANSWERS
</SectionTitle>
    <Paragraph position="0"> (script based) These are similar to wierd-oriented answers but are distinguished by being more commonplace. The restaurant script contains alternative paths which contain occurrences of goal interference. For example, if no tables are available, we have interference with the goal of being seated.</Paragraph>
    <Paragraph position="1"> Ex.1: John went to a restaurant and ordered a hotdog. The waiter said they didn't have any. So John ordered a hamburger.</Paragraph>
    <Paragraph position="2"> Ex.2: John went to a restaurant and was told he'd have to wait an hour for a ,table. John left.</Paragraph>
    <Paragraph position="3"> Ex.3: John went to a restaurant. He read the menu, became very angry and left. A goal interference predicts an action which will be either a resolution or consequence of the interference. Therefore any question which points to such a resolution or consequence is explained by the interfering occurrence.</Paragraph>
    <Paragraph position="4"> QI: Why did John order a hamburger? At: The waiter said they didn't have hotdogs.</Paragraph>
  </Section>
  <Section position="10" start_page="0" end_page="0" type="metho">
    <SectionTitle>
V. THE THEORETICAL SIDE OF SAM
</SectionTitle>
    <Paragraph position="0"> The problems of interpreting a question or finding the best answer to a why-question are both characterized by the necessity of knowing what is interesting about the question. Interpretation is facilitated by establishing focus. Answering a why-question may entail examination and construction of causal chains or knoweldge of goal hierarchies. In any case, the solution to what is interesting lies within some structural representation of the story.</Paragraph>
    <Paragraph position="1"> When we are within the confines of a script, the problem is relatively trivial since the structures we need are predetermined and static. Outside of a script we need dynamic processes which can generate the needed representation as we go along. To date, systems based on uncontrolled inferencing and propositional reasoning have failed to be effective precisely because no higher level structures were invoked to give the processing direction. The difference between a blind inferencing mechanism and a clever one is this crucial ability to determine what is deserving of attention.</Paragraph>
    <Paragraph position="2"> By studying the structures implicit in scripts, we may gain some insight concerning what types of guidance mechanisms exist and how analogous structures may be generated in contexts beyond scripts.</Paragraph>
    <Paragraph position="3"> The proposed heuristic of variation over expectation is theoretically significant insofar as it suggests an alternative to what might be called a propositional approach to memory retrieval.</Paragraph>
    <Paragraph position="4"> Suppose we know that the host gave John a menu, and we need to answer &amp;quot;Did the waiter give John the menu?&amp;quot; How are we to answer this question without recourse to scripts or the idea of focus? Suppose we approached the problem propositionally. One possible line of analysis might entail the following reasoning: (i) The act of transfering a menu to a restaurant patron usually occurs once in the course of a dinner out.</Paragraph>
    <Paragraph position="5"> (ii) The act of transfering a menu to a restaurant patron is executed by one actor only.</Paragraph>
    <Paragraph position="6"> (iii) The host and the waiter are two different actors.</Paragraph>
    <Paragraph position="7"> Given these three suppositions and some deductive reasoning capacity, we are in a position to conclude that the answer to the question is &amp;quot;No&amp;quot;.</Paragraph>
    <Paragraph position="8"> There are a number of problems with an approach of this type. In the first place, it is probably impossible to implement. We need some very clever inferencing to pull (i) out of the blue. Then deduction and inferencing must combine in some mysterious way to extract (ii) from (i). All in all, the whole argument smells like theorem proving, a technique which has proved ineffective and is certainly not the way people work. But ignoring all these objections, even if you could implement it, the fact remains that this has simply not done a very good Job of answering the question. It yields only a minimally 20.</Paragraph>
    <Paragraph position="9"> correct response and has no indication of the point of the question; there is no way of knowing how to augment the initial response &amp;quot;No&amp;quot;.</Paragraph>
    <Paragraph position="10"> By examining non-script based approaches to this question, it seems clear that the best possible answer can be derived only from a data base which enables us to establish the focus of the question. There is no way that the natural answer to this question can be found without some sense of what is interesting about the question.</Paragraph>
  </Section>
class="xml-element"></Paper>