Anaphora Resolution: 
A Multi.Strategy Approach 
Jaime G. Carbonell 
Ralf D. Brown 
Computer Science Department & Center for Machine Translation 
Carnegie-Mellon University 
Pittsburgh, PA 15213 
15 April 1988 
Primary topic: discourse 
Secondary topics: semantics, computational models, 
natural language interfaces, pragmatics 
Abstract 
Anaphora resolution has proven to be a very difficult problem; it 
requires the integrated application of syntactic, semantic, and 
pragmatic knowledge. This paper examines the hypothesis that 
instead of attempting to construct a monolithic method for resolving 
anaphora, the combination of multiple strategies, each exploiting a 
different knowledge source, proves more effective, theoretically and 
computationally. Cognitive plausibility is established in that human 
judgements of the optimal anaphoric referent accord with those of the 
strategy-based method, and human inability to determine a unique 
referent corresponds to the cases where different strategies offer 
conflicting candidates for the anaphoric referent. 
1, Introduction: The Complexity of Anaphora 
Resolution 
Anaphora is a pervasive phenomenon in natural language 
communication, whether it be complex multi-party human discourse 
or more constrained bilateral human-computer dialog. Whereas the 
ubiquity of the phenomenon and tire necessity to cope with it in the 
construction of friendly natural language interfaces has long been 
recognized \[13, 8, 9, 17, 15\], no truly comprehensive computational 
approaches for anaphora resolution have been proposed. The RUS 
parser \[2\], the XCALIBUR system \[7\], and other operational natural 
language systems implement very rudimentary methods. And, 
theoretical work in linguistics is primarily concerned with certain 
types of syntactic intrasentential coreference, rather than pragmatic 
intersentential anaphora. 
AnaPhors typically refer back to other constituents in the same 
sentence, or to constituents in earlier utterances in fire discourse. 
Syntactic information plays a central role in establishing appropriate 
referents for the former case, intrasentential anaphora \[17\]. But, 
semantic and pragmatic infonnation is absolutely required in the latter 
case, intersentential anaphora \[15, 9\]. This paper addresses the 
problem of intersentential anaphora resolution, integrating caseframe 
semantics \[10, 12, 5\] and more global dialog coherence structures 
\[11, 15, 14\]. Empirical studies have shown that intersentential 
anaphora I is far more frequent and more crucial in designing 
interactive natural language interfaces 2 \[8\]. 
96 
2. The Problem: Semantics and Pragmatics Dominate 
Finding the appropriate anaphoric referent has been long 
recognized as a difficult problem, requiring lnuch ~emautic and 
pragmatic lmowledge. Consider, for instance, the tbllowing two sets 
of examples: 
John took the cake from the table and ate it. 
John took the cake from the table and washed it. 
Tile robot pushed the box towards the conveyor belt. But, it 
goojSd and dropped it on its way there. 
Semantic preference constraints (e.g., \[18, 11), if pmp:~rly coded, 
suffice to resolve the first example. The pt'eferre'l object of 
ingestation is an edible substance. It is a little more difficult to 
mechanize a process that excludes things such as cakes from being 
the object of washing. One cannot simply write a "NOT(edibley 
restriction on the object case of the verb "to wash". Alter ,all, 
vegetables and fruits are occasionally washed prior to eating them. 
Peltlaps a combination of typicality judgements with pragmatic 
knowledge exla'apolating the effects of attempting to drown a cake in 
sink full of water comes into play. Or, more abstract irffemntial 
constraints are appropriate, snch as requiring that the object of wash 
be unchanged by immersion in water. Interestingly, Subjects given 
only the "...and washed it" sentence report consistently that they 
didn't even consider the cake a reasonable referent for "it". 
In the robot example, there ate four anaphoric referents, counting 
the possessive "its" and the locative "there", referring to three 
different antecedents. Although subjects report little difficulty 
ascertaining the referent for each anaphor in a consistent manner, it 
appears that sophisticated semantic~ are required. Why is the referent 
for "it" in "it goofed and dropped..." the robot rather than the box or 
the conveyor belt? One could argue that the box cannot take action, 
but what allows a robot to goof and not a conveyor belt? Is it 
something as subtle as the degree to which the former can be 
anthropomolphized being greater than the degree to which the latter 
can be anthmpomorphized? 
The difficulty in anaphoric referent specification in narratives has 
been argued convincingly by many researchers including Chamiak in 
his work on children's story comprehension \[9\], where substantial 
pragmatic domain knowledge must be brought to bear, and by one of 
the authors \[4\], where knowledge of goals and personality traits is 
required to resolve difficult referents. Hence, the hypothesis that 
anaphor resolution in its fnll generality is at best a diffictflt problem, 
and at worst an almost intractable one, is well supported. 
Nevertheless, somewhat less ambitious endeavors can prove far more 
tractable, and yet be of major practical Import. Hayes \[13\] argued for 
the notion of limitod-domain anaphora in a natural language interface 
to an electronic mail system. Webber \[17\] demonstrated that 
intrasentential anaphora was more tractable than its intersentential 
counterpart, largely through the categorization of syntactic devices 
absent from larger textual or dialog segments. 
This paper explores an intemrediate position: addressing much 
larger classes of anaphors than those of Hayes \[13\] in a systematic 
mariner, but stopping short of full generality, which requires 
unbounded pragmatic knowledge and inference. We explore the 
central hypothesis that anaphora resolution may be best accomplished 
through fire combination of a set of strategies, rather than by a single 
monolithic method. The apparent complexities lie in the combination 
of these multiple strategies to produce syntactically, semantically arid 
pragmatically sound anaphoric resolutions. In the multiple examples 
analyzed, 3 unambiguous resolutions reported by human subjects 
correspond to situations where the applicable strategies concur on the 
referont of an anaphor, and disagreement on the con'eet referent by 
the human subjects corresponds to situations where the applicable 
strategies propose different candidate referents for file anaphor in 
questitm. 
3. Multiple Resolution Strategies 
In this section we propose a general framework for anaphor 
resolution ba~d on the integration of multiple knowledge sources: 
sentential syntax, case-frame semantics, dialog structure, and general 
world knowledge. The underlying theoretical tenet is: 
Anaphor resolution is not a monolithic autonomous 
process; it requires access and integration of all the 
knowledge sources necessary for dialog and text 
lnterprel'ation. These linguistic knowledge sources are 
brought to bear as constraints or preferences encoded as 
multiple resolntion strategies. 
Each source of knowledge usethl in resolving intersentential 
anaphnra is presented below, along with corresponding examples, and 
a statement of the anaphoric resolution strategy. 
3.1. Local A naphor Constraints 
Certain anaphot~ carry with them constraints (number, gender, 
case, etc.) which must be satisfied by the candidate referents. For 
instant'e, gender uniquely specifies the anaphor in: 
John at~d Mary went shopping. He bought a steak. 
\[he=John\] 
Tile strategy here is trivial: 
Eliminate from consideration all candidate referents that 
violate the local constraints of the anaphor its question. 
A variant of this strategy has been implemented in RUS and in 
XCALIBUR. 
3.2. Case-role Semantic Constraints 
Here the ease-role semantics impose constraints on what can fill 
them. If they are filled by an anaphor (which specifies few if any 
semantic features), the case role constraints must be also satisfied by 
the referent of tile anaphor, thus eliminating from consideration all 
candidate anaphor referents that violate constraints on the case role 
occupied by the anaphor. Consider our previous example, where the 
semantic constraints on the object case of "to eat" and "to wash" 
impose restrictions on the possible case fillem and prove sufficient to 
select a unique referent. 
John took the cake from the table and ate it. lit:cake\] 
John took the cake from the table and washed it. lit=table\] 
The slrategy here is also fairly simple: 
Eliminm'e from consideration all candidate referents that 
violate any case-constraint imposed on the anaphor its 
question~ Prefer those candidates that accord with typical 
ease fillers, in the absence of hard constraints. 
XCALIBUR implements this strategy directly though use of its case- 
frame grammar. With the I-rule mechanism, it was possible to 
implement an ad-hoc variant of this strategy in RUS as well. 
3.3. Preconttition/Postcondition Constraints 
Using real-world knowledge and pragmatics, it is possible to say 
that a candidate antecedent cannot be the referent of an anaphor 
because some action occurring betwee n the referent and the anaphor 
invalidates the assumption that they denote one and the same object 
or event. 
John gave Tom an apple. He ate the apple. \[he=Tom\] 
Here, "he" refers to Tom, as Jolm no longer has the apple. The 
postcondition on give is that the actor no longer have the object being 
given, which ,:onfiicts with the precondition on eat that the actor have 
the item being eaten, if the actor is assumed to be John. 
The strategy is simple, but requires a fairly large amount of 
knowledge to be useful for a broad range of cases: 
Eliminate from consideration all candidate referents 
associated with actions whose postconditions violate the 
preconditions of the action containing the anaphor. 
3.4. Case.role Persistence Preference 
We observe a pervasive form of "linguistic inertia" that manifests 
as a preference to assign the referent of an anaphor to the linguistic 
entity in the discourse context that filled the corresponding semantic 
case role in an earlier utterance. This is a generalized form of ease- 
role parallelism, which has proven crucial in ellipsis resolution 
\[8, 7, 5\], although in anaphora resolution it is demoted from the 
status of a categorical constraint to that of a preference. 
Mary gave an apple to Susan. John also gave her an 
orange. \[her=Susan\] 
Mary gave an apple to Susan. She also gave John an 
orange. \[she=Mary\] 
The first anaphor relers to Susan, whereas the second anaphor refers 
to Mary. Clearly it is not a matter of primacy or recency, as the 
sentence structures are identical. Rather it is a case of structural 
parallelism. And, the semantic structnre dominates over the syntactic 
one. For instance, in the first example, "Susan" is the object of the 
"to" prepositional phrase, whereas the corelerent anaphor is in the 
indirect ol~iect position: two different syntactic roles that map into the 
same semantic case, recipient. In the second example above, both 
syntactic mad semantic structures coincide, and therefore the 
preference is stronger. Note, moreover, that the subject or direct- 
object form of the pronoun ("she" vs "her") is not the primary source 
of discriminant knowledge. For instance, in the example below, one 
has only the anaphor "it", but the same referent discrimination occurs 
by semantic case-role parallelism: 
The robot gave the dog a bone. John also gave it some 
water, lit=dog\] 
The robot gave the dog a bone. It also gave John some 
water, lit=robot\] 
To provide more ammunition in support of semantic case role 
persistence, consider the following final example, with three possible 
referents to the anapher "him". It is clear that "Peter" is the preferred 
referent, once again due to the persistence of the underlying semantic 
recipient case. 
John carried the box of papers from Bill to Peter. 
He also sent him Mary's books. \[he=John, him=Peter\] 
The semantic preference strategy can be stated as follows: 
Search first for acceptable referents in the antecedent 
phrase (or phrases) that occur in the same semantic case 
role as the attaphor, lf a match satisfying all constraints 
is found, look no further; else search the other case roles. 
To our knowledge, this preference strategy has been neither proposed 
nor implemented prior to our work on the Universal Parser (reported 
below), yet it counts for a large number of anaphor resolutions in our 
sample set. 
3.5. Semantic Alignment Preference 
A form of pragmatic "Occam's razor" exists in not postulating extra 
roles for the same objects in different sentences in the discourse. This 
preference is a more gcner~d and looser form of case role inertia, 
discussed above, in that the we have inmtia of the underlying action. 
For instance, in the example below, this preference manifests as 
preferring all departures to be from the park, and all arrivals m be at 
the club: 
Mary drove from the park to the club. Peter went there too. 
\[there=chth\] 
Mary drove from the park to the chub. Peter left there too. 
\[there=park\] 
The locative anaphor "there" refers to "the club" in the first example 
above, but refers to "the park" in the second example, yet both 
sentences share the identical syntactic structure and the same basic 
underlying semantic case structure. However, discourse cohesion 
97 
prefers to make the sentences coreferential (pragmatically parallel) 
with respect to the same underlying action (leaving the pink and 
going to the club). Therefore, the former aligns with the second 
(destination) part, whereas the latter aligns with the first (source) part. 
The strategy here is a bit more difficult to state, and certainly has not 
been implemented in any system to date: 
If the clause in which the anaphor is embedded aligns 
with a previous clause ("aligns" means that it can 
represent the same underlying action, perhaps with 
d~fferent instantiated case fillers), or with part of a 
previous clause, search first for referents of the anaphor 
in that clause. If there are no allowable re#rents in the 
semantically aligned clause, expand the search to other 
antecedent clauses; else halt the search. 
3.6. Syntactic paralielism preference 
Although semantic and pragmatic parallelism (case-persistence, 
and alignment, respectively, in the discussion above) appear to 
dominate over syntactic parallelism, the latter plays an important role 
if two clauses are directly contrasted (e.g., in a coordinate structure, 
or by means of explicit discourse cohesion markers \[14\]). Consider 
the following examples: 
The girl scout leader paired Mary with Susan, but she had 
paired her with Nancy last time. \[she=leader, her=Mary\] 
The girl scout leader paired Mary with Susan, but she had 
paired Nancy with her last time. \[she=leader, her=Susan\] 
There is no reason to prefer different referents for the pronoun "her" 
in each sentence above, other than retaining as much as possible the 
surface syntactic order from the first coordinate clause in the second 
clause. The strategy here is summarized as follows: 
In coordinated clauses, adjacent sentences or explicitly 
contrasted sentences, prefer the anaphoric referent that 
preserves the surface syntactic role from the first clause. 
3.7. Syntactic Topicalization Preference 
Topicalized structures are searched first for possible anaphoric 
referents. Consider, for instance, the following pseudo-cleft 
constmctions: 
It was Mary who told Jane to go to New York. Why did site 
do it? \[she=Mary\] 
It was Jane who went to New York at Mary's bidding. Why 
did she do it? \[she=Jane\] 
It was Mary who told Peter to go to New York. Why did he 
do it? \[he=Peter\] 
It was Peter who went to New York at Mary's bidding. Why 
did he do it? \[he=Peter\] 
In the first set of examples, describing essentially the same tcaderlying 
action, the topicalized person becomes the referent of the anaphor 
"she:" "Mary" in the first sentence, "Jane" in the second. And, the 
action associated with that person become the r~ferent of "it." 
However, to stress that topicalization is a preferential rather than 
categorical strategy, consider the second set of examples above. The 
exact same semantic and syntactic structures yield "Peter" both times 
as the referent of "lie", because localized constraints so dictate, 
regardless of who is topiealized. Thus, it is important to distinguish 
constraints from preferences in anaphora resolution. The 
topicalization strategy may be stated as follows: 
Search first a syntactically topiealized part of the 
candidate antecedent clause (or clauses) for the referent 
of the anaphor. If an acceptable referent is found, search 
no further; else search the rest of the clause(s). 
This strategy surprisingly enough has not been exploited h~ any 
system to our knowledge, although it is easy to establish syntactic 
topiealization (indicated by linguistic devices such as fronting, and 
cleft constructions). In contrast, the much more complex phenomenon 
of pragmatic topiealization by dialog focus or actor focus (discussed 
below) was suggested by Sidner \[lS\] We also believe that dialog 
98 
l:'oeus can yield a useful preference for anapnmac reference selection, 
but lacking a computationally-adequate theory for dialog-level focus 
trackh~g (Sidner's is a partial theory), we could not yet implement 
such a strategy. 
3.8. Intersentential Recency Preference 
Thus far we have focused on the problem of selecting the best 
anaphoric referent among several candidates, all from a single 
previous sentence (or coordinated clause). When prior context 
contains many sentences, the question naturally ari~s of how far back 
to search for the anaphoric referent, and how to prioritize that search. 
At the paragraph (or dialog) level level, we advocate searching 
sentences in reverse chronological ordm, applying all the constraints 
and preferences to select among possible candidates within each 
sentence. If there are no satisfactory candidates in the previous 
sentence, then the one before that is considered, and so on. Although 
we are investigating more sophisticated tectmiques, these await a 
more comprehensive (non-linear) theory of discourse structure - and 
one that is precise enough to permit implementation. 
4. Integrating the Strategies 
In order to apply a diverse set of strategies, such as those presented 
in this paper, one needs to make a distinction between constraints 
(which cannot be violated), and preferences (which discriminate 
among candidates satisfying all constraints). The latter may be 
ranked in a partial order (as the goals trees in \[4\]), or may be offered a 
voting scheme where the stronger preferences get more votes, and 
where conflicting preferences of equal voting power indicate true 
ambiguity. 
Our resolution method works by applying the constraints first to 
reduce the number of candidate referents for the anaphor in question. 
Then, the preferences are applied to each of the remaining candidates. 
If more than one preference applies, and each Suggests different 
candidate referents for the anaphor in question, 'all of which have 
passed the constraint tests, then we consider the anaphor to have a 
truly ambiguous referent. Thus, when faced with conflicting 
knowledge sources of equal strength, we simply reduce the space of 
possible anaphoric referents to those that are accepted by constraints 
and indicated as preferred by one or more preferences. Earlier hand 
simulations of a slightly different method 4 on 70 examples (including 
those presented earlier in this paper) yielded 49 unique resolutions, 17 
conflicting possibilities, and 4 anomalous cases. Human judgements 
correlate very well in terms of identifying the same referent as that 
suggested by the system in the 49 unique cases. 5 Moreover, the 
majority of the 17 multiple-referent cases were judged ambiguous by 
our subjects (the rest required complex world knowledge to establish 
a unique referent). Therefore, we believe that one can indeed achieve 
human-like performance with the multi-strategy method of 
determining referents to anaphors using different sources of linguistic 
knowledge in a semi-modular fashion. 
5. A Practical Implementation 
We have developed an anaphor resolver using Local Constraints, 
Case Role Semantic Constraints, Pre/Postcondition Constraints, Case 
Role Persistence, Intersentential Recency Preference, and Syntactic 
Topiealization Preference. The implementation occurs in tile context 
of the Universal Parser (UP) project \[6, 16\] at tile Center for Machine 
Translation at Camegie..Mellon University. The UP uses a modified 
form of lexical-functional grammar\[3\] unifying symactie and 
semantic knowledge sources to produce a complete parse of each 
sentence. The anaphor resolver operates post facto on the set of 
instantiated semantic case frames and syntactic trees, attempting to 
resolve anaphors in the parse of the newest sentence using earlier 
parses (semantic and syntactic) as context to mine for candidate 
referents. We expect the resolver to become an integral part of our 
multi-lingual machine translation effort. 
Candidate ~'cferents are derived by extracting the noun phrases from 
the most-receipt previous sentences that the resolvcr has processed. 
The number of sentences examined may be changed, allowiug the 
future addition of discourse phenomena to further restrict the 
sentenees which are examined for candidate referents. 
The pmfere,Lces use a voting method to detennine which candidate 
referent is most preferred. Each preference strategy is given an 
individual weight, and may vote with less than its fuU weight for less- 
preferred candidates, such as case role persistence in a referent 
several sentences removed from the anaphor. 
In addition to ailing out candidates, the case-role and local anaphor 
constraints may also cast votes tot those allowable candidates which 
are most clo,~ely matched to the anaphor or con'espond to typical 
fillers. In elf,',ct, fllese strategies indicate a preference in the absence 
of hard conso'aints. For ex~unple, ti~e gender constraint would prefer 
a candidate reference of female gender over one of indeterminate 
gender when resolving an auaphor of female gender, while at the 
same time eliminating all candidates of male gender. 
After applying the preferences, the most preferred candidate 
referent is unified with the reference to restrict the range of possible 
values as mu~:h as possible. For example, if she is determined to refer 
to doctor, all future anaphorie references to the doctor will be 
required to have female or unknown gender. However, if multiple 
candidates have received nearly the same number of votes, the 
anaphor is coasidered to be anthiguous. 
Ttle anaphor resolver i~ able to resolve partially-specified definite 
noun phrases with an antecedent noun phrase. To do so, along with 
the other lo(-al constraints, the head nouns ,'uld the remaining slots in 
the noun ph~a.~c are checked for agreement with the reference. The 
head noun ol the candidate must be the samc as, or an instance of, the 
head noun o(" the reference. For the remaining slots, it suffices for 
corresponding slots to be uniliable with each other or missing from 
either the d~,,finite noun phrase or the candidate referent. Unlike 
anaphors, which must have a suitable referent, it is not considered an 
error if there are no referents which pass all constraints. We believe 
that the ability to resolve definite noun phrases with basically the 
saute approach as anaphors is an indication of the generality of our 
strategies anal their implementation exploiting semantic and syntactic 
constraint ut~ification methods. 
The curt'cut test suite consists of ten examples, totalling 3l 
,sentences (:outaining 27 anaphors and three definite noun phrases 
with prior reii~rents. 6 The anaphor resolver correctly resolves "all but 
four of the anapho~s, ,'mr determines the correct referent for all of the 
definite noun ptu'ases; In two of tbe four problematic cases, the 
anaphor is an it referring to an action only indirectly mentioned, 
which is beyond the scope of the resolver. Tile remaining two 
anaphors are in the example 
John carried the box from Bill to Peter. He also sent him 
Macy's books. 
Here, him remains an~biguous, and he also remains ambiguous 
between John and Bill (with the current voting scheme, John is 
preferred over Bill). 
The follo,~eing rtm of the anaphor rcsolver (edited to save space) 
illustrates several of the strategies. Each candidate referent is tagged 
with a number indicating how many votes it has received so far. The 
intersentential recency preference is applied at the same time that the 
candidates a~e collected and tagged because of its computational 
efficiency; l ttus, the initial list of candidates already includes the votes 
from intersentential recency. The ease-role persistence preference is 
applied between pre/postcenditlon constraints and local constraints, 
because removal of eliminated candidates (in this implementation) 
also removes tim information on which previous sentence a candidate 
originates from. Then, case-role constraints are applied, and if 
multiple candidates remain, the rem~fining preferences (currently only 
syntactic topicalizatio10 are applied. 
; sentence 6: The doctor gave John a glass of 
water 
(SENT6 
(IS-A *GIVE) (:TIME *PAST) (:AGENT *DOCTOR) 
(:OBJECT OBJECT6) (:RECIPIENT *JOHN)) 
(*DOCTOR 
(IS-A *PERSON) ) \[unb~own gender\] 
(OBJECT6 
(IS-A *DRINKING-WATER) ( :AMOUNT GLASS i) ) 
( * JOHN 
(IS-A *PERSON) (:GENDER M) 
( :NUMBER *SINGULAR) ) 
frame = (:RECIPIENT *JOHN) 
No referents for definite NP 
frame = (:OBJECT OBJECT6) 
No referents for definite NP 
frame = (:AGENT *DOCTOR) 
No referents for definite NP 
\[the frames are unchanged after resolution\] 
; sentence 7: John drank it \[it=glass of water\] 
(SENT7 
(IS-A *INGEST-FOOD) (:TIME *PAST) 
(:AGENT eJOHN) (:OBJECT OBJECTT)) 
(* JO~L~ 
(TS-A *PERSON) ( :GENDER M) 
( :NUMBER *SXNGULAR) ) 
(OBJECTS! 
(IS-A *LIQUID)(:PRO +)(:NUMBER *SINGULAR)) 
frame = (:OBJECT OBJECT7) 
Candidates : ( (i :AGENT *DOCTOR) 
(I :OBJECT OBJECT6) 
(1 :RECIPIENT *JOHN) ) 
after pze-post-cond: ( (i :AGENT *DOCTOR) 
(I :OBJECT OBJECT6) 
(i :RECIPIENT *JOHN) ) 
after local constr: ((3 :OBJECT OBJECT6)) 
after case-role constr : ( (3 :OBJECT OBJ~ICT6) ) 
referent = (:OBJECT OBJECT6) 
f~me = (:AGENT ~JOHN) 
Candidates : ( (i :AGENT *DOCTOR) 
(i :OBJECT OBJECT61) 
(i :RECIPIENT *JOHN) ) 
after pa'e-post-cond: ((I :OBJECT OBJECT61) 
(I :RECIPIENT *JOHN) ) 
after N~ agreement: ((9 :RECIPIENT *JOBN)) 
after local constr: ((12 :RECIPIENT *JOHN)) 
after case-role constr: ((12 :RECIPIENT *JOHN) ) 
referent = (:RECIPIENT *JOHN) 
\[both "John"s are coreferential\] 
(SENT7 
(IS-A eINGEST-FOOD) (:TIME *PAST) 
(:AGENT *JOHN) (:OBJECT OBJECT61)) 
(*JOHN 
(IS-A *PERSON) (:GENDER M) 
(:NUMBER *SINGULAR) ) 
(OBJECT61 
(:NUMBER *SINGULAR) (:AMOUNT GLASS i) 
(IS-A OBJECT6) ) 
; sentence 8: He gave him an aspirin 
\[he=doctor, him=John\] 
(SENT8 
(IS-A eGIVE) (:TIME *PAST) (:AGENT *HE) 
(:OBJECT OBJECT8) (:RECIPIENT *HE)} 
(*HE 
(IS-A *PERSON) (:GENDER M) 
(:NUMBER *SINGULAR) (:PRO +)) 
(0SJECT8 
(IS~A *ASPIRIN) (QUANTITY i)) 
99 
frame = (:RECIPIENT *HE) 
Candidates : ( (i :AGENT *JOHn) 
(I :OBJECT OBJECT61) 
(0 :AGENT *DOCTOR) 
(0 :RECIPIENT *JOHN) ) 
after pre-post-cond: ( (I :AGENT *JOHN) 
(I :OBJECT OBJECT61) 
(0 :AGENT *DOCTOR) 
(I. 6 :RECIPIENT *JOHN) ) 
after local constr: ((4.6 :RECIPIENT *JOHN) 
(2 :AGENT *DOCTOR) 
(4 :AGENT *JOHN) ) 
after case-role constr: ((4.6 :RECIPIENT *JOHN) 
(2 :AGENT *DOCTOR) 
(4 :AGENT *JOHN) ) 
referent = (:RECIPIENT *JOHN) 
frame = (:OBJECT OBJECT8) 
Candidates : ( (i :AGENT *JOHN) 
(I :OBJECT OBJECT61) 
(0 :AGENT *DOCTOR) 
(0 :RECIPIENT *JOHN) ) 
after pre-post-cond: ( (i :AGENT *JOHN) 
(i :OBJECT OBJECT61) 
(0 :AGENT *DOCTOR) 
(0 :RECIPIENT *JOHN) ) 
after NP agreement : NIL 
after local constr: NIL 
No referents for definite NP 
frame = (:AGENT *HE) 
Candidates : ( (I :AGENT *JOHN) 
(I :OBJECT OBJECT61) 
(0 :AGENT *DOCTOR) 
(0 :RECIPIENT *JOHN) ) 
after pre-post-cond: ( (i :AGENT *JOHN) 
(1 :OBJECT OBJECT61) 
(1.6 :AGENT *DOCTOR) 
(0 :RECIPIENT *JOHN) ) 
after local constr: ((3 :RECIPIENT *JOHN) 
(3.6 :AGENT *DOCTOR) 
(4 :AGENT *JOHN) ) 
after case-role constr: ((3 :RECIPIENT *JOHN) 
(3.6 :AGENT *DOCTOR) 
(4 :AGENT *JOHN) ) 
referent = (iAGENT *DOCTOR) 
(SENT8 
(IS-A *GIVE) (:TIME *PAST) ( :AGENT *DOCTOR4) 
(:OBJECT OBJECT8) (:RECIPIENT *JOHN)) 
(*DOCTOR4 
( :NUMBER *SINGULAR) ( :GENDER M) 
(IS-A *DOCTOR) ) 
\[note that the gender is now known\] 
(OBJECT8 
(IS-A *ASPIRIN) (QUANTITY I)) 
(*JOHN 
(IS-A *PERSON) (:GENDER M) 
( :NUMBER *SINGULAR) ) 
Notes 
llnterclausal anaphora in coordinate constructions behaves much 
like a constrained version of intersentential anaphora, where syntactic 
parallelism (between the coordinated clauses) plays a more dominant 
role. 
2No claim;;, however, are made for file relative frequency or utility 
of resolving intersentential vs intrasentential anaphors in processing 
narrative or expository texts. 
3Although many of our anaphora instances come from actual user 
utterances in our experience with domain-oriented human-computer 
interfaces, we expect that the strategies developed here am of more 
general applicability. For clarity of exposition in this paper, we have 
selected exmnples not from our human-computer dialogs, but from 
everyday events. 
'*Using preferenccs to determine whict* candidates are tested against 
the constrain~ s 
5Olten, more than one slrategy suggested the same referent, 
increasing or.r confidence. Language is redundant, and it may prove 
useful to exp'loit that redundancy. 
6The sentences in our corpus used to test the implementation are: 
John gave Mary two aspirin. She took them from him. 
Mary had a h,mdache. John gave her two aspirin tablets. She took 
them. 
The doctor gme John a glass of water. John drank it. He gave him 
an aspirin. ~Ie took it with another glass of water. 
Mary gave art apple to Susan. John also gave her an orange. 
Mary gave arl apple to Susan. She also gave John an orange. 
John took the cake from the table. He ate it. 
Jotm took the cake from the table. He washed it. 
John took the cake from the table \[ambig\]. He washed it. 
John carried the box from Bill to Peter. He also sent him Mary's 
books. 
It was Mary who told Jane to go to New York. Why did she do it? 
It was Jane who went to New York at Mary's bidding. Why did she 
do it? 
Jotm gave Peler an apple. He ate it. 
Jack (age 10) went up the hill. John (age 32) went up the hill. 
The boy fell down. 
Jack went up the hill. The boy fell down. 
i01 

References 

\[1\] Bimbaum, L. and Selfridge, M. 
Conceptual Analysis in Natural Language. 
In R. Schank and C. Riesbeck (editors), Inside Computer 
Understanding, pages 318-353. New Jersey: Erlbaum 
Assoc., 1980. 

\[2\] Bobrow, R. 
The RUS System. 
In Research in Natural Langauge Understanding. BBN 
Report No. 3837, 1978. 

\[3\] Bresnan, J. and Kaplan, R. 
Lexical-Functional Grammar: A Formal System for 
Grammatical Representation. 
The Mental Representation of Grammatical Relations. 
MIT Press, Cambridge, Massachusetts, 1982, pages 173-281. 

\[4\] Carbonell, L G. 
Towards a Process Model of Human Personality Traits. 
AI 15(1,2):49-74, November, 1980. 

\[5\] Carbonell, L G. and Hayes, P. J. 
Natural Language Understanding. 
In Shapiro, S. C. (editor), Encyclopedia of Arttficial 
Intelligence, pages 660-677, Wiley & Sons, New York, 
NY, 1987. 

\[6\] Carbonell, J. G., and Tomita, M. 
Knowledge-Based Machine Translation, The CMU Approach. 
In Nirenberg, S. (editor), Machine Translation: Theoretical 
and Methodological Issues. Cambridge, U. Press, 1987. 

\[7\] Carbonell, L G., Boggs, W. M., Mauldin. M. L. and Anick, 
P.G. 
The XCALIBUR Project, A Natural Language Interface to 
Expert Systems and Data Bases. 
In S. Andriole (editor), Applications in Artificial Intelligence. 
PetroceUi Books Inc., 1985. 

\[8\] Carbonell, 1. G. 
Discourse Pragmatics in Task-Oriented Natural Language 
Interfaces. 
In Proceedings of the 21st annual meeting of the Association 
for Computational Linguistics. ACL-83, 1983. 

\[9\] Charniak, E. 
Towards a Model of Children's Story Comprehension. 
PhD thesis, M.I.T., 1972. 

\[10\] Fillmore, C. J. 
The Case for Case. 
In Bach, E. and Harms, R. T. (editors), The Universals of 
Linguistic Theory, pages 1-88. Holt, Rinehart and 
Winston, New York, 1968. 

\[11\] Grosz, B. J. 
The Representation and Use of Focus in Dialogue 
Understanding. 
PhD thesis, University of California at Berkeley, 1977. 
SRI Tech. Note 151. 

\[12\] Hayes, P. J. and Carbonell, J. G. 
A Natural Language Processing Tutorial. 
Technical Report, Carnegie-Mellon University, Computer 
Science Department, 1983. 

\[13\] Hayes, P. J. 
Anaphora for Limited Domain Systems. 
In Proceedings of the Seventh IJCAI, pages 416-422. 
Vancouver, BC, 198 I. 

\[14\] Hobbs, J. R. 
A Computational Approach to Discourse Analysis. 
Technical Report 76-2, Department of Computer Science, City 
College, City U. of NY, 1976. 

\[15\] Sidner, C. L. 
Focusing for Interpretation of Pronouns. 
Journal of Computational Linguisties 7:217-231, 1981. 

\[16\] Tomita, M. and Carbonell, J. G. 
The Universal Parser Architecture for Knowledge-Based 
Machine Translation. 
In Proceedings oflJCAI-87. Milan, Italy, 1987. 

\[17\] Webber, B. and Reiter, R. 
Anaphora and Locial Form: On Formal Meaning 
Representations for Natural Langauge. 
In Proceedings of the Fifth IJCAI, pages 121-131. 
Cambridge, MA, 1977. 

\[18\] Wilks, Y. 
Knowledge Structures and Language Boundaries. 
In Proceedings of the Fifth International Joint Conference on 
Art~ciallntelligence, pages 151-157. IJCAI-V, 1977. 
