A High-Performance Coreference Resolution System  
using a Constraint-based Multi-Agent Strategy 
 
ZHOU GuoDong            SU Jian  
Institute for Infocomm Research 
21 Heng Mui Keng Terrace 
Singapore 119613 
Email: zhougd@i2r.a-star.edu.sg 
 
 
Abstract 
This paper presents a constraint-based multi-
agent strategy to coreference resolution of 
general noun phrases in unrestricted English 
text. For a given anaphor and all the preceding 
referring expressions as the antecedent 
candidates, a common constraint agent is first 
presented to filter out invalid antecedent 
candidates using various kinds of general 
knowledge.  Then, according to the type of the 
anaphor, a special constraint agent is proposed to 
filter out more invalid antecedent candidates 
using constraints which are derived from various 
kinds of special knowledge. Finally, a simple 
preference agent is used to choose an antecedent 
for the anaphor form the remaining antecedent 
candidates, based on the proximity principle. 
One interesting observation is that the most 
recent antecedent of an anaphor in the 
coreferential chain is sometimes indirectly 
linked to the anaphor via some other antecedents 
in the chain.  In this case, we find that the most 
recent antecedent always contains little 
information to directly determine the coreference 
relationship with the anaphor. Therefore, for a 
given anaphor, the corresponding special 
constraint agent can always safely filter out these 
less informative antecedent candidates. In this 
way, rather than finding the most recent 
antecedent for an anaphor, our system tries to 
find the most direct and informative antecedent. 
Evaluation shows that our system achieves 
Precision / Recall / F-measures of 84.7% / 
65.8% / 73.9 and 82.8% / 55.7% / 66.5 on MUC-
6 and MUC-7 English coreference tasks 
respectively. This means that our system 
achieves significantly better precision rates by 
about 8 percent over the best-reported systems 
while keeping recall rates.   
1 Introduction 
Coreference accounts for cohesion in texts. 
Especially, a coreference denotes an identity of 
reference and holds between two expressions, 
which can be named entities, definite noun 
phrases, pronouns and so on. Coreference 
resolution is the process of determining whether 
two referring expressions refer to the same entity 
in the world. The ability to link referring 
expressions both within and across the sentence is 
critical to discourse and language understanding in 
general. For example, coreference resolution is a 
key task in natural language interfaces, machine 
translation, text summarization, information 
extraction and question answering. In particular, 
information extraction systems like those built in 
the DARPA Message Understanding Conferences 
(MUC) have revealed that coreference resolution is 
such a crucial component of an information 
extraction system that a separate coreference task 
has been defined and evaluated in MUC-6 (1995) 
and MUC-7 (1998).  
There is a long tradition of work on 
coreference resolution within computational 
linguistics. Many of the earlier works in 
coreference resolution heavily exploited domain 
and linguistic knowledge (Carter 1987; Rich and 
LuperFoy 1988; Carbonell and Brown 1988). 
However, the pressing need for the development of 
robust and inexpensive solutions encouraged the 
drive toward knowledge-poor strategies (Dagan 
and Itai 1990; Lappin and Leass 1994; Mitkov 
1998; Soon, Ng and Lim 2001; Ng and Cardie 
2002), which was further motivated by the 
emergence of cheaper and more reliable corpus-
based NLP tools such as part-of-speech taggers 
and shallow parsers alongside the increasing 
availability of corpora and other resources (e.g. 
ontology).  
Approaches to coreference resolution usually 
rely on a set of factors which include gender and 
number agreements, c-command constraints, 
semantic consistency, syntactic parallelism, 
semantic parallelism, salience, proximity, etc. 
These factors can be either “constraints” which 
discard invalid ones from the set of possible 
candidates (such as gender and number 
agreements, c-command constraints, semantic 
consistency), or “preferences” which gives more 
preference to certain candidates and less to others 
(such as syntactic parallelism, semantic 
parallelism, salience, proximity). While a number 
of approaches use a similar set of factors, the 
computational strategies (the way antecedents are 
determined, i.e. the algorithm and formula for 
assigning antecedents) may differ, i.e. from simple 
co-occurrence rules (Dagan and Itai 1990) to 
decision trees (Soon, Ng and Lim 2001; Ng and 
Cardie 2002) to pattern induced rules (Ng and 
Cardie 2002) to centering algorithms (Grosz and 
Sidner 1986; Brennan, Friedman and Pollard 1987; 
Strube 1998; Tetreault 2001). 
This paper proposes a simple constraint-based 
multi-agent system to coreference resolution of 
general noun phrases in unrestricted English text. 
For a given anaphor and all the preceding referring 
expressions as the antecedent candidates, a 
common constraint agent is first presented to filter 
out invalid antecedent candidates using various 
kinds of general knowledge.  Then, according to 
the type of the anaphor, a special constraint agent 
is proposed to filter out more invalid antecedent 
candidates using constraints which are derived 
from various kinds of special knowledge. Finally, a 
simple preference agent is used to choose an 
antecedent for the anaphor form the remaining 
antecedent candidates, based on the proximity 
principle. One interesting observation is that the 
most recent antecedent of an anaphor in the 
coreferential chain is sometimes indirectly linked 
to the anaphor via some other antecedents in the 
chain.  In this case, we find that the most recent 
antecedent always contains little information to 
directly determine the coreference relationship 
with the anaphor. Therefore, for a given anaphor, 
the corresponding special constraint agent can 
always safely filter out these less informative 
antecedent candidates. In this way, rather than 
finding the most recent antecedent for an anaphor, 
our system tries to find the most direct and 
informative antecedent. 
In this paper, we focus on the task of 
determining coreference relations as defined in 
MUC-6 (1995) and MUC-7 (1998). In order to 
evaluate the performance of our approach on 
coreference resolution, we utilize the annotated 
corpus and the scoring programs from MUC-6 and 
MUC-7. For MUC-6, 30 dry-run documents 
annotated with coreference information are used as 
the training data. There are also 30 annotated 
training documents from MUC-7. The total size of 
30 training documents is close 12,400 words for 
MUC-6 and 19,000 for MUC-7. For testing, we 
utilize the 30 standard test documents from MUC-
6 and the 20 standard test documents from MUC-7. 
The layout of this paper is as follows: in 
Section 2, we briefly describe the preprocessing: 
determination of referring expressions. In Section 
3, we differentiate coreference types and discuss 
how to restrict possible types of direct and 
informative antecedent candidates according to 
anaphor types. In Section 4, we describe the 
constraint-based multi-agent system. In Section 5, 
we evaluate the multi-agent algorithm. Finally, we 
present our conclusions. 
2 Preprocessing: Determination of 
Referring Expressions 
The prerequisite for automatic coreference 
resolution is to obtain possible referring 
expressions in an input document. In our system, 
the possible referring expressions are determined 
by a pipeline of NLP components: 
• Tokenization and sentence segmentation 
• Named entity recognition 
• Part-of-speech tagging 
• Noun phrase chunking 
Among them, named entity recognition, part-
of-speech tagging and noun phrase chunking apply 
the same Hidden Markov Model (HMM) based 
engine with error-driven learning capability (Zhou 
and Su 2000). The named entity recognition 
component (Zhou and Su 2002) recognizes various 
types of MUC-style named entities, that is, 
organization, location, person, date, time, money 
and percentage. The HMM-based noun phrase 
chunking component (Zhou and Su 2000) 
determines various noun phrases based on the 
results of named entity recognition and part-of-
speech tagging. 
3 Coreference Types 
Since coreference is a symmetrical and transitive 
relation, it leads to a simple partitioning of a set of 
referring expressions and each partition forms a 
coreference chain. Although any two referring 
expressions in the coreference chain is 
coreferential, some of conference pairs may be 
direct while others may be indirect since they only 
become conferential via other referring expressions 
in the same coreference chain. This indicates that 
the most recent antecedent of an anaphor in the 
coreferential chain is sometimes indirectly linked 
to the anaphor via some other antecedents in the 
chain. In these indirect cases, we find that the most 
recent antecedent always contains little 
information to directly determine the coreference 
relationship with the anaphor. Generally, direct and 
informative coreference pairs are much easier to 
resolve than indirect and less informative ones. In 
the following example
1
,  
Microsoft Corp. (i) announced its (i) new CEO 
yesterday. Microsoft (i) said … 
                                                      
1
 The italic markables with the same identification 
symbol are coreferential. 
“Microsoft Corp.”, “its” and “Microsoft” form a 
coreference chain. Among the three coreference 
pairs in the chain,  
1) The coreference pair between “Microsoft 
Corp.” and “Microsoft” is direct.  
2) The coreference pair between “Microsoft 
Corp.” and “its” is direct. 
3) The coreference pair between “its” and 
“Microsoft” is indirect. This coreference pair 
only becomes coreferential via another 
referring expression “Microsoft Corp.” Direct 
resolution of this coreference pair is error-
prone and not necessary since it can be 
indirectly linked by the other two coreference 
pairs in the coreference chain.  
Therefore, for a given anaphor, we can always 
safely filter out these less informative antecedent 
candidates. In this way, rather than finding the 
most recent antecedent for an anaphor, our system 
tries to find the most direct and informative 
antecedent. This also suggests that we can classify 
coreference types according to the types of 
anaphors and restrict the possible types of 
antecedent candidates for a given anaphor type as 
follows: 
• Name alias coreference 
This is the most widespread type of coreference 
which is realised by the name alias phenomenon. 
The success of name alias coreference resolution is 
largely conditional on success at determining when 
one referring expression is a name alias of another 
referring expression. Here, the direct antecedent 
candidate of a named entity anaphor can only be 
the type of named entity. For example, 
Microsoft Corp. (i) announced its new CEO 
yesterday. Microsoft (i) said … 
• Apposition coreference 
This is the easiest type of coreference. A typical 
use of an appositional noun phrase is to provide an 
alternative description for a named entity. For 
example 
Julius Caesar (i), the well-known emperor (i), 
was born in 100 BC. 
• Predicate nominal coreference 
Predicate nominal is typically coreferential with 
the subject. For example, 
George W. Bush (i) is the president of the 
United States (i). 
• Pronominal coreference 
This is the second widespread type of coreference 
which is realised by pronouns. Pronominal 
coreference has been widely studied in literature of 
traditional anaphora resolution. The direct 
antecedent candidate of a pronoun anaphor can be 
any type of referring expressions. For example, 
Computational linguistics (i) from different 
countries attended the tutorial. They (i) took 
extensive note. 
• Definite noun phrase coreference 
This is the third widespread type of coreference 
which is realised by definite noun phrases. It has 
also been widely studied in the literature of 
traditional anaphora resolution. A typical case of 
definite noun phrase coreference is when the 
antecedent is referred by a definite noun phrase 
anaphor representing either same concept 
(repetition) or semantically close concept (e.g. 
synonyms, super-ordinates). The direct antecedent 
candidate of a definite noun phrase anaphor can be 
any type of referring expressions except pronouns. 
For example, 
Computational linguistics (i) from different 
countries attended the tutorial. The 
participants (i) took extensive note. 
• Demonstrative noun phrase coreference 
This type of coreference is not widespread. Similar 
to that of definite noun phrase coreference, the 
direct antecedent candidate of a demonstrative 
noun phrase anaphor can be any type of referring 
expressions except pronouns. For example, 
Boorda wants to limit the total number of 
sailors on the arsenal ship (i) to between 50 
and 60. Currently, this ship (i) has about 90 
sailors. 
• Bare noun phrase coreference 
The direct antecedent candidate of a bare noun 
phrase anaphor can be any type of referring 
expressions except pronouns. For example, 
The price of aluminium (i) siding has steadily 
increased, as the market for aluminium (i) 
reacts to the strike in Chile. 
4 Constraint-based Multi-Agent System 
for Coreference Resolution 
In accordance with the above differentiation of 
coreference types according to the anaphor types, a 
constraint-based multi-agent system is developed.  
4.1 Common Constraint Agent 
For all coreference types described in Section 3, a 
common constraint agent is applied first using 
following constraints:  
Morphological agreements 
These constraints require that an anaphor and its 
antecedent candidate should agree in gender and 
number. These kinds of morphological agreements 
has been widely used in the literature of anaphora 
resolution 
Semantic consistency 
This constraint stipulates that the anaphor and its 
antecedent candidate must be consistent in 
semantics. For example, the anaphor and its 
antecedent candidate should contain the same 
sense or the anaphor contains a sense which is 
parental to the antecedent candidate. In this paper, 
WordNet (Miller 1990) is used for semantic 
consistency check. 
For example, 
IBM (i) announced its new CEO yesterday. 
The company (i) said … 
4.2 Special Constraint Agents 
For each coreference type described in Section 3, a 
special constraint agent is applied next using some 
heuristic rules mainly based on the accessibility 
space, which is learnt from the training data as 
follows:  
For a given coreference type and a given valid 
antecedent type, all the anaphors of the given 
coreference type are identified first from left to 
right as they appear in the sentences. For each 
anaphor, its antecedent is then determined using 
the principle of proximity. If the most recent 
antecedent candidate has the given antecedent 
type, meet the morphological agreements and 
semantic consistency and is in the same 
coreference chain as the anaphor, this coreference 
pair is counted as a correct instance for the given 
conference type and the given antecedent type. 
Otherwise, it is counted as an error instance. In this 
way, the precision rates of the coreference type 
over different valid antecedent types and different 
accessibility spaces are computed as the percentage 
of the correct instances among all the correct and 
error instances. Finally, the accessibility space for 
a given coreference type and a given antecedent 
type is decided using a precision rate threshold 
(e.g. 95%).  
• Agent for name alias coreference 
A named entity is co-referred with another named 
entity when the formal is a name alias of the latter. 
This type of coreference has an accessibility space 
of the whole document. In this paper, it is tackled 
by a named entity recognition component, as in 
Zhou and Su (2002), using the following name 
alias algorithm in the ascending order of 
complexity: 
1) The simplest case is to recognize full identity 
of strings. This applies to all types of entity 
names. 
2) The next simplest case is to recognize the 
various forms of location names. Normally, 
various acronyms are applied, e.g. “NY” vs. 
“New York” and “N.Y.” vs. “New York”. 
Sometime, partial mention is also applied, e.g. 
“Washington” vs. “Washington D.C.”. 
3) The third case is to recognize the various 
forms of personal proper names. Thus an 
article on Microsoft may include “Bill Gates”, 
“Bill” and “Mr. Gates”. Normally, the full 
personal name is mentioned first in a document 
and later mention of the same person is 
replaced by various short forms such as 
acronym, the last name and, to a less extent, 
the first name, of the full person name. 
4) The most difficult case is to recognize the 
various forms of organizational names. For 
various forms of company names, consider a) 
“International Business Machines Corp.”, 
“International Business Machines” and “IBM”; 
b) “Atlantic Richfield Company” and 
“ARCO”. Normally, various abbreviation 
forms (e.g. contractions and acronym) and 
dropping of company suffix are applied. For 
various forms of other organizational names, 
consider a) “National University of 
Singapore”, “National Univ. of Singapore” and 
“NUS”; b) “Ministry of Education” and 
“MOE”. Normally, acronyms and 
abbreviations are applied. 
• Agent for apposition coreference 
If the anaphor is in apposition to the antecedent 
candidate, they are coreferential. The MUC-6 and 
MUC-7 coreference task definitions are slightly 
different. In MUC-6, the appositive should be a 
definite noun phrase while both indefinite and 
definite noun phrases are acceptable in MUC-7.  
• Agent for predicate nominal coreference 
If the anaphor is the predicate nominal and the 
antecedent candidate is the subject, they are 
coreferential. This agent is still under construction.  
• Agent for pronominal coreference 
This agent is applied to the most widely studied 
coreference: pronominal coreference. 6 heuristic 
rules are learnt and applied depending on the 
accessibility space and the types of the antecedent 
candidates: 
1) If the anaphor is a person pronoun and the 
antecedent candidate is a person named entity, 
they are coreferential over the whole 
document. 
2) If the anaphor is a neuter pronoun and the 
antecedent candidate is an organization named 
entity, they are coreferential when they are in 
the same sentence. 
3) If the anaphor is a neuter plural pronoun and 
the antecedent candidate is a plural noun 
phrase, they are coreferential over the whole 
document. 
4) If both the anaphor and the antecedent 
candidate are third person pronouns, they are 
coreferential over the whole document. 
5) If both the anaphor and the antecedent 
candidate are first or second person pronouns, 
they are coreferential when they are in the 
same paragraph. 
6) If both the anaphor and the antecedent 
candidate are neuter pronouns, they are 
coreferential when they are in the same 
paragraph or the antecedent candidate is in the 
previous paragraph of the anaphor. 
• Agent for definite noun phrase coreference 
The agent for definite noun phrase coreference is 
mainly based on the accessibility space. This agent 
is based on the following 3 heuristic rules: 
1) The definite noun phrase will be coreferential 
with a named entity if they are in same 
paragraph or the entity name is in the previous 
paragraph of the definite noun phrase. 
2) The definite noun phrase will be coreferential 
with a named entity if the head word of the 
definite noun phrase is only modified by the 
determiner “the”. That is, the definite noun 
phrase is of type “the HEADWORD”, e.g. “the 
company”. 
3) The definite noun phrase will be coreferential 
with a definite/demonstrative/indefinite noun 
phrase if they string-match
2
. 
• Agent for demonstrative noun phrase 
coreference 
The agent for demonstrative noun phrase 
coreference is similar to the agent for definite noun 
phrase coreference except that the anaphor is a 
demonstrative noun phrase. 
• Agent for base noun phrase coreference 
This is the most complicated and confusing 
coreference in MUC coreference task definitions. 
Although this type of coreference occupies a large 
portion, it is hard to find heuristic rules to deal 
with it. In our system, only one heuristic rule is 
applied: If the anaphor and the antecedent 
candidate string-match and include at least two 
words except the determiner, they are coreferential 
over the whole document.  
                                                      
2
 The determiners, e.g. “a”, “an” and “the”, are removed 
from the strings before comparison. Therefore, “the 
company” string-matches “a company”. 
4.3 Common Preference Agent 
For a given anaphor, invalid antecedents are first 
filtered out using the above common constraint 
agent and the special constraint agent. Then, the 
strategy has to choose which of the remaining 
candidates, if any, is the most likely antecedent 
candidate. In our strategy, this is done through a 
common preference agent based on the principle of 
proximity. That is, our common preference agent 
takes advantages of the relative locations of the 
remaining antecedent candidates in the text. 
Among the antecedent candidates: 
1) First it looks for those occurring earlier in the 
current sentence, preferring the one that occurs 
earliest in the natural left-to-right order. 
2) If there are no antecedent candidates occurring 
earlier in the current sentence, look to those 
occurring in the immediately preceding 
sentence of the same paragraph, again 
preferring the one that occurs earliest in that 
sentence in left-to-right order. 
3) If nothing comes up, look back at those 
occurring in the earlier sentences of the same 
paragraph, moving back a sentence at a time, 
but now, within a given sentence preferring the 
most rightward candidate that occurs later in 
the sentence. 
4) Finally, if the scope extends back beyond a 
paragraph boundary, it looks to those that 
occur in the sentences of the preceding 
paragraph, again preferring later to earlier 
occurrences. 
4.4 Multi-Agent Algorithm 
The coreference resolution algorithm is 
implemented based on the previous multi-agents. 
First, all the anaphors are identified from left to 
right as they appear in the sentences. Then, for a 
given anaphor,  
1) All the referring expressions occurred before 
the anaphor are identified as antecedent 
candidates. 
2) The common constraint agent is applied to 
filter out the invalid antecedent candidates 
using various general constraints, such as 
morphological agreements and semantic 
consistency constraints. 
3) The corresponding special constraint agent (if 
exists) is recalled to first filter out indirect and 
less informative antecedent candidates and 
then check the validity of the remaining 
antecedent candidates by using some heuristic 
rules. In this way, more invalid antecedent 
candidates are discarded using various special 
constraints, such as the accessibility space. 
4) The antecedent is chosen from the remaining 
antecedent candidates, if any, using the 
common preference agent based on the 
principle of proximity. 
5 Experimentation 
Table 1 shows the performance of our constraint-
based multi-agent system on MUC-6 and MUC-7 
standard test data using the standard MUC 
evaluation programs while Table 2 gives the 
comparisons of our system with others using the 
same MUC test data and the same MUC evaluation 
programs. Here, the precision (P) measures the 
number of correct coreference pairs in the answer 
file over the total number of coreference pairs in 
the answer file and the recall (R) measures the 
number of correct coreference pairs in the answer 
file over the total number of coreference pairs in 
the key file while F-measure is the weighted 
harmonic mean of precision and recall: 
PR
RP
F
+
+
=
2
2
)1(
β
β
 with =1.  
2
β
Table 1: Results of our baseline multi-agent coreference resolution system on MUC-6 and MUC-7 
MUC-6 MUC-7 Performance 
R P F R P F 
Overall 65.8 84.7 73.9 55.7 82.8 66.5
• Agent for name alias coreference 32.7 (35) 92.3 - 33.6 (36) 89.0 - 
• Agent for apposition coreference  4.3 (5) 95.5 -   2.6 (3) 84.6 - 
• Agent for predicate nominal coreference
3
 
- (2) - - - (3) - - 
• Agent for pronominal coreference 18.6 (22) 77.5 - 10.8 (16) 72.3 - 
• Agent for definite noun phrase coreference  9.4 (15) 80.0 -   7.0 (20) 85.0 - 
• Agent for demonstrative noun phrase coreference  0.1 (2) 50.0 -   0.2 (2) 66.7 - 
• Agent for bare noun phrase coreference  1.9 (19) 63.0    1.7 (20) 61.1 - 
 
Table 2: Comparison of our system with the best-reported systems on MUC-6 and MUC-7 
MUC-6 MUC-7 Performance Comparison 
R P F R P F 
Ours 65.8 84.7 73.9 55.7 82.8 66.5 
Ng and Cardie 2002 (C4.5) 64.1 74.9 69.1 57.4 70.8 63.4 
Ng and Cardie 2002 (RIPPER) 64.2 78.0 70.4 55.7  72.8 63.1 
 
 
Table 1 shows that our system achieves F-
measures of 73.9 and 66.5 on MUC-6 and MUC-7 
standard test data, respectively. The figures outside 
the parentheses show the contributions of various 
agents to the overall recall while the figures inside 
the parentheses show the frequency distribution of 
various coreference types in the answer file. It 
shows that the performance difference between 
MUC-6 and MUC-7 mainly comes from the 
significant distribution variation of pronominal 
coreference. It also shows that there are much 
room for improvement, especially for the types of 
pronominal coreference and definite noun pronoun 
resolution. Table 2 shows that our system achieves 
significantly better F-measures by 3.1~4.8 percent 
over the best-reported systems (Ng and Cardie 
2002). Most of the contributions come form 
precision gains. Our system achieves significantly 
better precision rates by 6.7~10.0 percent over the 
best-reported systems (Ng and Cardie 2002) while 
keeping recall rates. One reason behind such high 
performance is the restriction of indirect and less 
informative antecedent candidates according to the 
type of the anaphor. Another reason is 
differentiation of various types of coreference and 
the use of multi-agents. In this way, various types 
of coreference are dealt with effectively by 
different agents according to their characteristics. 
The recall difference between our system and the 
RIPPER system in (Ng and Cardie 2002) maybe 
come from the predicate nominal coreference, 
which can be easily resolved using a machine 
learning algorithm, e.g. (Cohen 1995). Completion 
of the agent for predicate nominal coreference can 
easily fill the difference. 
6 Conclusions 
This paper presents a constraint-based multi-agent 
strategy to coreference resolution of general noun 
phrases in unrestricted English text. 
The first contribution of this paper comes from 
the high performance of our system and its easy 
                                                      
3
 The agent for predicate nominal coreference is still under construction. 
implementation. The second contribution is to 
filter out indirect and less informative antecedent 
candidates according to the anaphor type. The third 
contribution is the differentiation of various 
coreference types according to the anaphor types 
and the use of multi-agents.  
Future work includes: 
• The exploration of new constraints to improve 
the precision and new coreference types to 
increase the recall. 
• The problem of type coercion or metonymy 
which is a general problem and accounts for 
much of the overall missing recall. 
• The problem of cataphora, which is not 
handled in the current mechanism. 

References 

Brennan S. E. Friedman M. W. and Pollard C. J. 
1987. A centering approach to pronouns. 
Proceedings of the 25th Annual Meeting of the 
Association for Computational Linguistics 
(ACL’1987), pages 155-162. 

Carbonell J. and Brown R. 1988. Anaphora 
resolution: a multi-strategy approach. 
Proceedings of the 12th International Conference 
on Computational Linguistics (COLING’1988), 
pages 96-101, Budapest, Hungary. 

Carter D. M. 1987. Interpreting Anaphors in 
Natural Language Texts. Ellis Horwood, 
Chichester, UK. 

Cohen W. 1995. Fast effective rule induction. 
Proceedings of the Twelfth International 
Conference on Machine Learning (ICML’1995). 
pages 115-123. Tahoe City, CA.   

Dagan I. and Itai A. 1990. Automatic processing of 
large corpora for the resolution of anaphora 
references. Proceedings of the 13th International 
Conference on Computational Linguistics 
(COLING’1990), pages 1-3, Helsinki, Finland. 

Grosz B. J. and Sidner C. L. 1986. Attention, 
intentions and the structure of discourse. 
Computational Linguistics, 12(3):175-204. 

Lappin S. and Leass H. 1994. An algorithm for 
pronominal anaphora resolution. Computational 
Linguistics. 20(4):535-561. 

Miller G.A. 1990. WordNet: An online lexical 
database. International Journal of Lexicography. 
3(4):235-312. 

Mitkov R. 1998. Robust pronoun resolution with 
limited knowledge. Proceedings of the 36th 
Annual Meeting for Computational Linguistics 
and the 17th International Conference on 
Computational Linguistics 
(COLING/ACL’1998), pages 869-875, 
Montreal, Canada. 

MUC-6. 1995. Proceedings of the 6th Message 
Understanding Conference (MUC-6). Morgan 
Kaufmann, San Francisco, CA. 

MUC-7. 1998. Proceedings of the 7th Message 
Understanding Conference (MUC-7). Morgan 
Kaufmann, San Mateo, CA. 

Ng V. and Cardie C. 2002. Improving machine 
learning approaches to coreference resolution. 
Proceedings of the 40th Annual Meeting of the 
Association for Computational Linguistics 
(ACL’2002), pages 104-111, Philadelphia, Penn. 

Rich E. and LuperFoy S. 1988. An architecture for 
anaphora resolution. Proceedings of the 2nd 
Conference on Applied Natural Language 
Processing (ANLP’1988), pages 18-24, Austin, TX. 

Soon W. M.., Ng H. T. and Lim C. Y. 2001. A 
machine learning approach to coreference 
resolution of noun phrases. Computational 
Linguistics, 27(4):521-544. 

Strube M. 1998. Never look back: An alternative to 
centering. Proceedings of the 36th Annual 
Meeting of the Association for Computational 
Linguistics and the 17th International Conference 
on Computational Linguistics, pages 1251-1257. 

Tetreault J. R. 2001. A corpus-based evaluation of 
centering and pronoun resolution. Computation 
Linguistics, 27(4):507-520.  

Zhou G. D. and Su Jian, 2000. Error-driven HMM-
based chunk tagger with context-dependent 
lexicon. Proceedings of the Joint Conference on 
Empirical Methods on Natural Language 
Processing and Very Large Corpus (EMNLP/ 
VLC'2000). Hong Kong.  

Zhou G. D. and Su Jian. 2002. Named Entity 
Recognition Using a HMM-based Chunk 
Tagger, Proceedings of the 40th Annual Meeting 
of the Association for Computational Linguistics 
(ACL’2002). Philadelphia.  
