Anaphorie Reference to Events and Actions: 
A Representation and its Advantages 
Ethel SCHUSTER 
Department of Computer and Information Science 
University of Pennsylvania 
Philadelphia, PA 19104-6389 
Abstract 
Tiffs paper focuses on anaphora interpreted as referring t'o en- 
tities of type event and action. It considers two issues: (i) what 
aspects of the discourse give evidence of the events and the actions 
the speaker is talking about, and (ii) how actions and events are 
represented in the discourse in order to be able to refer to them 
anaphorically. 
1 Introduction 
When people speak or Write, they refer to things, objects, events, 
actions, facts or states that they (or other people) referred to be- 
fore. They use certain words to "refer" or "point" to those things: 
previously mentioned. Such context-dependent reference is called, 
anaphora, and the words used to "refer" are called anaphors. 
Some examples of anaphors include pronouns such as he, she, it' 
and noun phrases that contain this; that, these and those. Consider 
for example the following pair of sentences: 
(1) U: I want to move a 0lock of text as a unit. How do I do it? 
The it in the second sentence is the anaphor which points back 
to the action that the user wants to perform, described in the first 
sentence. 
In our communications, we benefit from the use of anaphoric 
forms which make our interactions more coherent and intelligible. 
If we were forced to describe everything explicitly, our discourse 
would become very complex, long and time-consuming. Moreover 
it could become confusing and lead to potential misunderstand- 
ings. Such is the case in the following example which is similar 
to example (1) but in which a pronoun is not used in the second 
sentence: 
(2) U: I want to move a block of text as a unit. How do I move 
a block of text as a unit? 
We as listeners may find these-sentences very odd and lacking 
coherence. We may wonder about the need to repeat the description 
which has already been introduced. If the speaker fails to use the 
pronoun, 'the listener may believe that he is meant to conclude 
something special from this unnatural usage. This conclusion may 
be unwarranted. 
The work we present here describes the process of dealing with 
anaphoric language when the reference is to events and actions. 
It considers two issues: (i) what aspects of the discourse give 
evidence of the events and the a~tions the speaker is talking about, 
and (ii) how actions and events are represented in the discourse in 
order to be able to refer to them anaphoricaUy. The overall goal is 
to make natural-language communication between human beings 
and machines more robust and coherent. This can be done by 
providing computer systems with the ability to adequately generate 
602 
and interpret text which includes anaphoric references to events and 
actions in a similar way to how human beings do it. To illustrate 
the problem that we are dealing with, we use some examples taken 
from a set of natural language transcripts about the EMACS text 
editor. The users were given a task to perform using EMACS and 
at the same time they were able to ask an expert about the various 
things they could do in EMACS. The goal of the interaction was 
for the users to learn how to use the EMACS editting system. 
In the next section we will describe how we view discourse 
models along with the representation of entities which form part 
of them. In section 3 we describe a representation of those entities 
based on the language used. We propose a generalization of that 
representation which allows us to have access to the different enti- 
ties characterized by the text. In section 4 we relate the proposed 
representation with the particular pronouns used to refer to events, 
based on some data analysis. We conclude by giving a brief sum- 
mary of what the advantages of the proposed representation are. 
2 Discourse Models 
An overall concern of this work is to describe how communication 
is done via discourse. A piece of discourse is a set of sentences 
or pieces of text that are spoken by one or more speakers. When 
we talk about discourse, we usually indicate the fact that those 
sentences in the discourse are connected in some way that makes 
them comprehensible and coherent. Speakers do so by attempting 
to get their listeners to construct an appropriate model: a discourse 
model. A discourse model is viewed as containing representations 
of entities, along with their properties and relations they partici- 
pate in \[Webber 1982, Helm 1982, Kamp 1984\]. The key, then, in 
successful communication is for the speaker to transmit as much 
information about those representations of the entities, their prop- 
erties and relations to the listener. Usually, this cannot be done in a 
single utterance, so it requires reference back to things mentioned 
previously. The speaker refers to a particular representation of a 
person, object, action or event in his or her discourse model and 
he or she can do so by using a pronoun, a definite noun phrase, 
or a form such as do it, do that. The speaker expects the listener 
to (i) have in his or her discourse model a representation for those 
objects, actions or events (or to be able to create one with mini- 
mal effort), and (ii) make the link between the referent 1 and the 
representation of the entity. 
Discourse entities can represent objects, sets, actions, events, 
and facts which are viewed as individuals. The referent of a def- 
inite pronoun is then an entity in the speaker's discourse model 
which, given the goal of the communication, is expected to exist 
XReseareh in linguistics has defined the problem of anaphom as that of finding 
the antecedent of an anaphoric expression, that is, finding the word or phrase to 
which the anaphor is linked. In this work, the problem of anaphom is defined 
not solely as that of identifying the antedecent but how the referent is found. 
We consider the antecedent to be the linguistic text which gives rise to an entity, 
as compared to a referent which is a non-linguistic entity. 
also in the listener's model, hi the next section, we describe how 
discourse entities describing events or actions can be represented 
in a discourse model in order to indicate what they make available 
for future reference. 
3 Formalizing the Representation 
3.1 Characterization 
First, let us consider what characterizes actions or events. In gen- 
eral, each sentence gives rise to an event. Similarly, an action is 
considered to be part of that event. As a way to establish the differ- 
ences linguistically, we describe actions as being characterized by 
the predicate of the sentence (the verb phrase) and events as being 
characterized hy the whole sentence. Therefore, we consider ac- 
tions to be part of events. This notion is similar to Jackendoff's who 
notes that "sentences that express \[ACTIONS\] are a subset of those 
that express \[EVENTS\]" \[Jaekendoff 1983\] (p. 179). He proposes 
introducing "what happened was" as a diagnostic for \[EVENTS\] 
and "what x did" as a diagnostic for \[ACTIONS\]. So we have 
(3) What happened was that the pig ran away. ~ EVENT 
and 
(4) What Fled did was run away. ~ ACTION 
Withiu this view, "an \[EVENT\] that is also an \[ACTION\] involves 
a character with a special role- the one who is performing the 
\[ACTION\]," called the \[ACTOR\] (p. 180). 
Consider for example: 
(5) Mary deleted the region. 
Here, the action of deleting, which occurred in some past time, 
was performed by Mary and it was done on the region. 2 The 
'delete' action relates Mary and the region. 
Events correspond to the conjunction of the action predicate 
with other predicates described in the sentence such as time, place, 
along with the agent performing the action. Tense and aspect usu- 
ally indicate the sense of time in an event. The tense indicates 
present, past, or future and the aspect indicates the perfect (com- 
pletion) and progressive (continuous) forms. In general, they are 
indicated syntactically by certain verbs and/or the auxiliaries. For 
instance, the auxiliary verb gives us a sense of whether the event 
is occurring (presen0, occurred (past), will occur (future) or is just 
hypothesized-as well as whether an event is continuous or it has 
been completed. 3 Events and actions usually have associated with 
them a time interval. This time interval can have a well defined 
beginning and/or end. There may also exist events which occur as 
points, that is, their beginning and end times are the same as well 
as those in which there is no end or no beginning. These are among 
the issues that provide us with information about the event or the 
action. There is a vast literature of these subjects including works 
by \[Vendler 1967, Mourelatos 1978, Dowty 1986, Hinrichs 1986, 
Moens et al. 1987, Passonneau 1987\] to mention some. 
2In EMACS, a region is a block of text defined by the mark at one end and 
the cursor at the other end. More precisely, it is the area of the buffer between 
the dot and the mark. 
aEnglish has two divisions for aspect: (i) Progressive (verb to be and the 
verbal form -ing) and non-Progressive, and (it) Perfect (verb to have and Past 
Participle) and mm-PerfecL English also has a separate Habitual (which occurs 
only in the past tense), using the auxiliary form used to. The habitual can be 
replaced by its non-habitual equivalent, i.e. the non-habitual does not exclude 
habitual meaning \[Comrie 1976\]. 
To summarize, our characterization of events is based on indi- 
vidual sentences. Each event includes an action predicate which, 
along with other predicates describing tense, aspect, and the agent 
performing the action constitutes the particular event. 
3.2 Representation of Events 
Given our characterization of events and actions as described be- 
fore, and assuming a syntactic representation for each sentence, the 
next step is to describe the kind of (semantic) representation we 
use to characterize those events. Many representations for events 
have been proposed to handle similar issues as we describe here 
\[Davidson 1967, Moore 1981, Neale 1987\]. The representation we 
have chosen is AProlog, a fortnaI logical representation described 
by \[Miller et al. 1986\]. This approach allows us to represent enti- 
ties describing events and actions in a logical and complex way. In 
this representation, the logical form describes the events that char- 
acterize the sentence (as compared to a proposition or individual), 
therefore allowing subsequent references to any one of the events 
described by the sentence. For example, 
(6) Mary types control-W. 
which is usually represented as 
type(Mary, control-W), 
will get mapped onto the following semantic representation: 
3v\[type( Mary, control-W, v)\], 
which posits an individual typing event following \[Davidson 1967\]. 
From this semantic representation, we obtain the action described 
by the sentence which corresponds to its predicate (e.g. 'type 
control-W' in this example). This action can be represented in 
terms of )~ predicates as in, 
Ax.\[tvpe( x, control-W, e)\]. 
The sentence characterizes an event description which is rep- 
resented as 
E : Ae.\[type(Mary, control-W, e) A present(e)\], 
meaning that E is an entity describable as 'the event in which 
Mary types control-W'. This is the entity associated with the event 
description characterized by the sentence. Present(e) means that 
the event occurs now. 4 As a way of illustrating the representation, 
consider an example: 
(7) John was shot in broad daylight in Philadelphia. 
which can be represented as follows: 
during(daylight_hours, e) A 
in(Philadelphia, e) A past(e)\]. 
4\[Hobbs 1985\] describes a similar approach by introducing what he calls a 
"nominalization" operator ' : p ~ p': 
Corresponding to every n-ary predicate p there will be an (n+ 1)- 
ary predicate p' whose first argument can be thought of as the 
condition that holds when p is true of the subsequent arguments. 
Thus if run(1) means that John runs, run'(E,l) means that E is 
a running event by John, or John's running ...... The effect of 
this notational maneuver is to provide handles by which various 
predications can be grasped by higher predications (p. 62). 
603 
Here, E(r)-~ can be described as 'the event in which John was 
shot in broad.daylight in Philadelphia') E(r)4 corresponds to the 
real world event description in which John was shot which took 
place at a time during the daylight_hours, in Philadelphia. z is the 
person who did the shooting, who is not explicitly mentioned in 
the sentence. Here, past(e) is defined as 
past(e ) --¢, time(e) < now. 
So E(r)-~ makes a predication about the event in which John was 
shot and the details that form part of that predication. 
Given this representation of the event, the next issue is how to 
generate references to that event. That is, we want to be able to 
generate references to (7) as in: 
(8) John was shot in broad daylight in Philadelphia. It happened 
at 10 am. 
it = the event in which John was shot in broad daylight in 
Philadelphia. 
(9) John was shot in broad daylight in Philadelphia. It shocked 
me very much. 
it = the event in which John was shot in broad daylight in 
Philadelphia. 
(10) John was shot in broad daylight in Philadelphia. It has never 
happened before. 
it = an event in which someone was shot in broad daylight 
in Philadelphia. 
(11) John was shot in broad daylight in Philadelphia. AI Pacino 
had done it last year in a warm summer evening in New York 
City. 
it = shoot someone/John. 
(12) John was shot in broad daylight in Philadelphia. That would 
never happen in BogotL 
that = an event in which someone was shot in broad daylight. 
As seen in these examples, the referents of the pronouns may 
have been introduced explicitly. That is, the anaphoric expression 
in the second sentence can refer to the specific event as charac- 
terized by the sentence or to a less specific event than the one 
described by the sentence. Therefore, what we need is to have 
access to the specific event description along with more general 
event descriptions of the one characterized by the sentence. This 
representation allows us to do so by being able to perform a gen- 
eralization on the specific event description as we show in the next 
section. 
3.3 Generalization of Event Descriptions 
In general, each event represented as described in the previous 
section denotes a set of events. Given that there are entities cor- 
responding to events represented in the discourse model, each of 
which can have one or more descriptions, we can generalize to 
obtain the various descriptions. Generalization is defined as fol- 
lows: Given an event description E1 and an event description E2, 
5As pointed out by \[Sidner 1982\], referring expressions specify discourse en- 
tities; referring expressions may co-specO~y the same discourse entity; discourse 
entities represent objects or events in the world and people refer to objects and 
events in the world when they use referring expressions. 
we say that E1 generalizes E2 if every event description denoted 
by E2 is a member of the set of event descriptions denoted by El.6 
As we generalize tile representation of the event that we have 
obtained for each sentence, we incrementally obtain event descrip- 
tions of that event. These event descriptions are available in the 
discourse model for future reference. The generalization of the 
events fits in an ordered structure in which the most specific repre- 
sentation (corresponding to the description of the event character- 
ized by the original sentence) is at the bottom and the most general 
at the top. So if we consider (7) again 
(7) John was shot in broad daylight in Philadelphia. 
along with its representation 
E(7)-1 : Ae.\[3x\[shoot(z, John, e)\] A 
during(daylight_hours, e) A 
in(Philadelphia, e) A past(e)\]. 
We can generalize it to 'any person y' (being shot) as follows: 
E(r)-2 : ~e.\[3x3y\[shoot(x,y,e)\] A 
during(daylight_hours, e) A 
in(Philadelphia, e) A past(e)\]. 
We can further generalize to 'any place p' and obtain: 
Eft)-3: Ae.\[~x3y\[shoot(x,y,e)\] A 
during(daylight_hours, e) h 
3p\[in(p, e)\] A past(e)\]. 
And we can continue to generalize this last representation and 
obtain the following: 
E(7)-4 : Ae.\[3x3y\[shoot(x,y,e)\] A 
during(daylight_hours, e) A 
past(e)\]. 
E(,)-5 : Ae.\[3z3y\[shoot(z, y, e)\] ^ 3p\[in(p, e)\] A past(e)\]. 
E(,).~ : Ae.\[3~3y\[shoot(x, y, e)\] ^ past(e)\]. 
Eft)-,: Ae.\[3x3y\[shoot( x, y, e)\]\]. 
As specified by the generalization, every member of E(r)-~ is a 
member of E(r)-r. This set of generalizations can be ordered in a 
graph-like structure as shown in Fig. 1. 
In this structure, which provides a partial ordering of the events, 
some events are more specific than others. The structure is partially 
ordered, with the < relation. 7 We have not generalized to 'any 
time t' in the !during' predicate because all events occur during 
some time. Note that at the very bottom of our graph we could 
generalize on the predicate 'shoot' so as to have an event describing 
"somebody doing something" which is common to all events. We 
have chosen not to do so in order to have access to the initial 
referent of the pronoun, characterized by the predicate of the event. 
The generalization structure provides the potential referents for 
the pronoun s as they appear in examples (8), (9), (10), (12), and 
(11). Consider for instance, the pair of sentences in (10), where 
the referent of the pronoun it in the second sentence is "an event in 
6This definition is based on Millet and Nadathur's definition of subsumption 
(= generalization). They define it in terms of concepts as follows: "a concept 
Ca subsumes another concept (?2 if every element of the set denoted by C~ is 
a member of the set denoted by C1" lMitlet et al 1986\] (13. 6). 
7A relation ~ is called a partial order if it is reflexive (p ~ p), anti-symmetric 
(p "< q A q ~_ p ==~ p = q), and transitive (p ~_ q A q ~ r ~ p "< r). 
604 
most specific 
EO)-I : 
Ae.\[3x \[shoot(x, John, e)\]. 
during(daylight_hours, e) 
in(Philadelphia, e) 
pa~t(e)\] ,L 
E(1)-2 : 
during(daylight_hours, e) 
in(Philadelphia, e) 
past(e)\] 
Eo)-a : he.\[3x3y\[shoot(x, y, 
e)\] 
during(daylight_hours, e) 
3p\[in(p,e)\] 
past(e)\] / 
E0)-5 : 
~e.\[3x3y\[shoot(x, y, e)\] ^ 
3p\[in(p, e)\] A 
past(e)\] 
\ 
E0)-~ : Ae.\[3x3y\[shoot(x,y,e)\] 
A 
past(e)\] 1 
E(x)-7 : 
:~e.\[~z ~y\[st,.oot(x, y, e)\]\] 
most general 
E(1)-4 : 
he.\[3x3y\[shoot(x, y, e)\] 
during(daylight_hours , e) 
past(e)\] / 
Figure 1: Generalization of 'John was shot in broad daylight in 
Philadelphia' 
which someone was shot in broad daylight in Philadelphia.,". This 
event description is E(7)-4 which is available in the generalization 
graph. The same is true for the pair of sentences in (11) where 
the referent of the pronoun it is E(7).7, and the pair (12) where the 
referent of the pronoun that in the second sentence is E(r)-s, both 
of which are available thru the generalization graph. 
Bauerle has proposed an alternative method for dealing with 
event reference within the framework of Disconrse Representation 
Theory (DRT) \[Kamp 1984\]. As he points out, the problem is not 
that simple because by introducing an event-argument, the possible 
referents for event-anaphora are only linked to the event-token (the 
specific event description) and not to the type (the generalized 
descriptions) \[Bauerle 1988\] (p. 21). The representation outlined 
in this paper does provide us with access to the event-token and 
its generalization allows us to obtain the types. 
4 Relationship between Pronouns and their 
Referents 
In addition to relating a particular pronoun and its referent, either 
as a specific event-token or as an event-type obtained from the 
generalization of the event-token, there are cases in which the pro- 
noun is also linked to not just an'individual event but to either a 
sequence of events or even a particular event within a sequence 
(usually the last event in the sequence). 
As described in \[Schuster 1988\], we have studied the relation- 
ship between the pronouns and their referents, within a given text 
describing a sequence of events. We focused on the use and inter- 
pretation of tim pronouns it and that when referring those events 
and/or actions, given the representation described in tbe previous 
section. Initially, we were interested in identifying tile relationship 
between a specific pronoun such as that or it and an event as its 
referent. We found out that a particular pronoun could act as a 
referent of one of the following: 
1. One event. 
2. A sequence of events, the pronoun referring to the entire 
sequence as one. 
3. The last event in a sequence. 
"4. A pair of events related by two possible relations: genera. 
tion and enablement, as proposed by \[Goldman 1970\] and 
developed by \[Pollack 1986a\]. 
We will describe each one of'these cases, along with some examples 
and relate them to the representation we introduced in section 3. 
1. One event Consider the following text: 
(13) E: Write a simple macro that does three forward char- 
aeters. Try that. 
We can represent the first sentence in the pair as described 
before: 
E(13)-I : Ae.\[\[write(U, 3fe_macro, e)\] A present(e)\]. 
Here, E03}-x can be described as 'the event in which U writes 
a simple macro that does three forward-characters, and takes 
place at the present time'. U in this case is the user interact- 
ing with the expert. Then, the referent of the pronoun that 
in the second sentence is the event represented as E03)-l. 
605 
2. A sequence of events Consider: 
(14) E:.To kill a region, the whole tiring at one time you 
should set the mark- (esc)-M-at the top of the region, 
then move the cursor down to the bottom of the region 
and type (esc)control-K. This will kill the region. 
The pronoun this refers to the entire sequence of events. 
As in the previous case, if we represent each sentence as a 
Aexpression, we have access to the various descriptions of 
the event corresponding to each sentence and we can refer 
to them via the pronoun. 
3. Last event Consider the following example, where the pronoun 
it refers to the last event in the sequence: 
(15) E: To kill a word, you have to move tbe cursor to the 
beginning of that word and type control-D. Go ahead, 
do it. 
4. Generation and Enablement In analyzing the data we'found 
the need for two important relationships: generation and 
enablement \[Pollack 1986b\]. Generation is defined as fol- 
lows: If an agent performs one action and thereby, without 
any effort on his/her part, does another, then we can say 
that his/her performance of the former action "generated" 
the performance of the latter. For example, 
(16) E: Do this: set a "mark" at some point (any 01d point) 
by typing (esc)-M. It will say "mark set", try it. 
(17) E: (esc)-M will give set-mark. Do it. 
In both cases, the referent(s) of the pronoun it can be either 
"setting the mark" or "typing (esc)-M" or even both: "setting 
the mark by typing (esc)-M". By viewing the referent in 
terms of the generation relationship, we can claim that "U 
typing (esc)-M at a given time generates U setting the mark 
at that given time". This relationship allows us to refer to 
both or either of the referents without having to make a 
distinction between the two of them. Note that generation is 
a relationship between the specific events, the event-tokens 
and not the types. 
Enablement, as opposed tO generation, has been described 
as follows: if an agent performs an action and thereby puts 
the world in a state in which a second action will generate 
a third action, then we can say that the agent's performance 
of the first action enables the generation of the third by the 
second. For example, 
(18) U: I want to move the cursor 20 characters to the right. 
How can I do it? 
E: Like all other commands in EMACS, these com- 
mands can be given arguments which cause them to be 
executed repeatedly. The way you give a command a 
repeat count is by typing control-U and then the digits 
before you type the command. For instance, control-U 
20 (RIGHT-ARROW} moves forward 20 characters. 
Go ahead, try that. 
In .this example, the pronoun that refers to the entire en- 
ablement relationship: "U typing control-U enables a given 
number (20) and the RIGHT-ARROW key to be typed which 
in term generates the cursor to move 20 characters forward". 
U typing control-U is viewed as an enablement relationship: 
if U does not type control-U and only types 20 followed by 
the RIGHT-ARROW, U's desired goal of making the cursor 
move 20 characters forward will not be accomplished. 
To summarize, for each representation of the individual events 
characterized by each sentence, we can relate the pronoun to the 
event, to a sequence of events, or to events related by either the 
generation or enablement relationships. 
5 Summary 
We have defined an approach for representing actions and events in 
discourse in order to refer to them anaphorically. The main concern 
has been to describe what aspects of the discourse give evidence of 
• events and actions and how these events and actions are represented 
in order to refer to them appropriately. This representation has 
'the advantage that it allows us to create appropriate descriptions 
of actions and events which are available for future reference in 
the discourse model. We have shown how to generalize event 
• descriptions, so that the general event descriptions can in turn be 
associated with additional event entities required by the use of 
particular anaphoric expressions. We have also related the event 
representation described here to anaphoric pronouns, given that the 
pronouns can refer to more than one event. 
Acknowledgments 
This work was supported by ARO grant DAAG29-84-K-0061, 
DARPA grant N00014-85-K-0018, and NSF-CER grant MCS82- 
19196 to the University of Pennsylvania. My thanks to Bonnie 
Webber and Dale Miller for their coments on an earlier draft. I am 
Specially grateful to Haim Levkowitz for his comments, and for 
his immense help in formatting this paper. 

References 

Bauerle, R. 1988. Discourse Representation 
Theory and Event Reference. In: Manfred 
Pinkal and Bemd Gregor, Eds., Unification 
in Natural Language Analysis. MIT Press. 

Comrie, B. 1976. Aspect. Cambridge Uni- 
versity Press, Cambridge, Great Britain. 

Davidson, D. 1967. The Logical Form of 
Action Sentences. In: N. Rescher, Ed., The 
Logic of Decision and Action. University of 
Pittsburgh Press, Pittsburgh, PA: 81-95. 

Dowty, D. 1986. The Effects of Aspectnal 
Class on the Temporal Structure of Discourse: 
Semantics or Pragmatics. Linguistics and Phi- 
losophy, 9(1):37-61. 

Goldman, A. I. 1970. A Theory of Human 
Action. Prentice-Hall, Englewood Cliffs, N.J. 

Helm, I. 1982. The Semantics of Definite and 
Indefinite Noun Phrases. PhD thesis, U. of 
Massachusetts, Amherst. 

Hinrichs, E. 1986. Temporal Anaphora in 
Discourses of English. Linguistics and Phi- 
losophy, 9(1):63-82. 

Hobbs, J. 1985. Ontological Promiscu- 
ity. In: 23rd Annual Meeting of the Asso- 
ciation for Computational Linguistics, ACL, 
Chicago, Ill." 61-69. 

Jackendoff, R. 1983. Semantics and Cog- 
nition. Current Studies in Linguistics Series, 
MIT Press, Cambridge, MA. 

Kamp, H. 1984. A Theory of Truth and Se- 
mantic Representation. In: T. M.V. Janssen~ 
J. Groenendijk and M. Stokoff, Eds., Truth, 
Interpretation and Information. Foris Publi- 
cations, Dordrecht, Holland: 141. 

Miller, D. and Nadathur, G. 1986. Some 
Uses of Higher-Order Logic in Computational 
Linguistics. In: Proceedings ofACL, ACL, 
New York. 

Moens, M. and Steedman, M. 1987. Temporal 
Ontology. In: Proceedings of the 25th Annual 
Meeting of the ACL, ACL, Stanford, CA. 

Moore, R. 1981. Problems in Logical Form. 
In" Proceedings ofACL, ACL, Stanford Uni- 
versity: 117-124. 

Mourelatos, A. 1978. Events, Processes and 
States. Linguistics and Philosophy, 2(3):415- 
434. 

Neale, S. 1987. Events and LF. Linguistics 
and Philosophy, forthcoming, TINLUNCII 1- 
15-87. 

Passonneau, R. 1987. Situations and Inter- 
vals. In: Proceedings of the 25th Annual 
Meeting of the ACL, ACL, Stanford, CA. 

Pollack, M. 1986. Inferring Domain Plans in 
Question-Answering. PhD thesis, University 
of Pennsylvania. 

Pollack, M. 1986. A Model of Plan Inference 
that Distinguishes between the Beliefs of Ac- 
tors and Observers. In: Proceedings of the 
24th Annual Meeting of the ACL, ACL, New 
York, NY: 207-214. 

Schuster, E. 1988. Pronominal Reference to 
Events andActions: Evidence from Naturally- 
Occurring Data. Technical Report MS-CIS- 
88-13, University of Pennsylvania, Philadel- 
phia, PA, Revised April 1988. 

Sidner, C. L. 1982. Focusing in the Compre- 
hension of Definite Anaphora. In: Michael 
Brady and Robert C. Berwiek, Eds., Com- 
putational Models of Discourse. MIT Press, 
Cambridge, MA: 267-330. 

Vendler, Z. 1967. Linguistics in Philosophy. 
Comell University Press, Ithaca. 

Webber, B. 1982, So What Can We Talk 
about Now? In: M. Brady and R. Berwick, 
Eds., Computational Models of Discourse. 
MIT Press, Cambridge, MA: 331-371. 
