Using NOMLEX to Produce Nominalization Patterns for 
Information Extraction 
Adam Meyers, Catherine Macleod, Roman Yangarber, 
Ralph Grishman, Leslie Barrett, Ruth Reeves 
New York University 
715 Broadway, 7th Floor, NY, NY 10003, USA 
meyers~cs, nyu. edu 
Abstract 
This paper describes how NOMLEX, a dictio- 
nary of nominalizations, can be used in Informa- 
tion Extraction (IE). This paper details a pro- 
cedure which maps syntactic and semantic infor- 
mation designed for writing an IE pattern for an 
active clause (IBM appointed Alice Smith as vice 
president) into a set of patterns for nominaliza- 
tions (e.g., IBM's appointment of Alice Smith as 
vice president and Alice Smith's appointment as 
vice president). 
1 Introduction 
Although, nominalizationQ are very common in 
written text, the computational linguistics liter- 
ature provides few systematic accounts of how to 
deal with phrases containing these words. This 
paper focuses on this problem in the context of 
Information Extraction (IE). 2 Many extraction 
systems use either parsing combined with some 
form of syntactic regularization, or a meta-rule 
mechanism to automatically match variants of 
clausal syntactic structures (active main clause, 
passive, relative clause etc.), e.g., FASTUS (Ap- 
pelt et al., 1995) and the Proteus Extraction 
System (Grishman, 1995). However, this mecha- 
nism does not extend to nominalization patterns, 
which must be coded separately from the clausal 
patterns. NOMLEX, a dictionary of nominal- 
izations currently under development at NYU, 
(Macleod et al., 1997) provides a way to handle 
nominalizations more automatically, and with 
INominalizations are nouns which are related to 
words of another part of speech, most commonly verbs. 
In this paper, only verbal nominalizatious will be 
discussed. 
2The Message Understanding Colfference Scenario 
Template Task (MUC, 1995), (MUC, 1998) is ore" model 
for the kind of information that we are attempting to ex- 
tract (who does what to whom, and when and where). 
25 
greater coverage. NOMLEX includes informa- 
tion about mappings between verbs and nomi- 
nalizations that will help generalize information 
from verbal patterns to create nominalization 
patterns. This paper describes the structure 
of the dictionary and a procedure for creating 
nominalization patterns. This procedure takes 
into account lexical information about nominal- 
izations which is encoded in NOMLEX. 
The Proteus Extraction System starts with a 
semantic pattern for an active clause: 
np(C-company) vg(appoint) np(C-person) "as" 
np(C-position) 
which matches a clause beginning with a noun 
phrase headed by a noun of type COMPANY, 
followed by a verb group (verb plus auxilliaries) 
headed by appoint, a noun phrase headed by 
a noun of type PERSON, the literal as, and a 
noun phrase headed by a noun of type position, 
e.g., IBM appointed Alice Smith as vice presi- 
dent. Proteus applies meta-rules to this pattern 
to produce new patterns for other clausal types, 
e.g., a passive clause: 
np(C-person) vg-pass(appoint) "as" 
np(C-position) "by" np(C-company) 
(vg-pass is a passive verb group). This new pat- 
tern would match Alice Smith was appointed as 
vice president by IBM. When a pattern matches 
input text, the pieces of the text corresponding 
to the constituents of the pattern are used to 
build a semantic representation of the text. 
To avoid the need for having users code such 
patterns, we have developed the Proteus Ex- 
traction Tool (PET) (Yangarber and Grishman, 
1997). PET allows the user to input an example 
sentence and specify the mappings from syntac- 
tic to semantic form. The system then produces 
generalized patterns to perform these mappings. 
This paper shows how PET can use NOMLEX 
to create nominalization patterns as well. For ex- 
ample, given the sentence IBM appointed Alice 
Smith as vice president, human input and dictio- 
nary entries identify IBM as the employer, Alice 
Smith as the employee, and vice president as the 
position. The meta-rules add a slot for tempo- 
ral PPs which state the date (e.g., on June 1, 
1998). PET creates patterns to fill the seman- 
tic slots (employer, employee, position) from the 
gramatical roles (subject, object, NP following 
as, etc.) in the sentence. PET generates pat- 
terns to cover passive sentences, active sentences 
and relative clauses. Enhanced with NOMLEX, 
PET can also cover examples like Alice Smith's 
appointment as vice president; IBM's June 1, 
1998 appointment of Alice Smith; and the June 
1, 1998 appointment of Alice Smith by IBM. The 
correspondence between nominal and verbal po- 
sitions is determined by explicit information in 
the NOMLEX dictionary entry and by general 
linguistic constraints. 
2 Considerations for Choosing a 
Dictionary Encoding 
The primary information in a NOMLEX en- 
try is a description of a nominalizatiou's ar- 
gument structure. This information can be 
quite complex. There are several potential ar- 
gument positions, including both pre-nominal 
(the bomb ezplosion, the bomb's explosion) and 
post-nominal (the ezplosion of the bomb), and 
a given verbal argument may appear in one of 
several positions. 3 In general, individual argu- 
ments may be omitted, although there are some 
co-occurrence constraints, which we shall con- 
sider below. Furthermore, vhether or not one 
position is filled may affect the interpretation 
of other positions; thus, in Rome's destruction, 
Rome is the object, whereas in Rome's destruc- 
tion of Carthage, Rome is the subject. 
In seeking an appropriate representation for 
SThese positions may be filled by non-arguments as 
well. For example, the prenominal positions may be filled 
by temporal NPs (NTIME1 and NTIME2 in COMLEX) 
like Yesterday(but not John), e.g., Yesterday's appoint- 
ment of the Prime Minister and The June I, 1987 ap- 
pointment of the Prime Minister. These positions corre- 
spond to temporal modifiers of clauses, e.g., .\" appointed 
the Prime Minister Yesterday/June I, 1987. For further 
discussion, see Section 5. 
26 
this information, one can compare the situation 
with that of English verbal complements, which 
have been extensively studied and recorded. In 
English, verbal complements are relatively fixed 
in composition and order. As a result, the com- 
mon practice (adopted, for example, in OALD 
(Hornby, 1980), LDOCE (Proctor, 1978), and 
COMLEX Syntax (Macleod et al., forthcoming) 
is to enumerate and name the possible subcat- 
egorizations, where in general each subcatego- 
rization represents a fixed sequence of syntactic 
elements. 4 For example, in COMLEX (Wolff et 
al., 1994), NP-PP consists of a Noun Phrase fol- 
lowed by a Prepositional Phrase as in put the 
milk in the refrigerator, where *put the milk, 
*put in the refrigerator and *put in the refrig- 
erator the milk are not acceptable. Such an ap- 
proach would be unwieldy for nominalizations, 
where an argument may appear in several posi- 
tions and may also be omitted. As a result, even 
a simple nominatization may entail a large num- 
ber of subcategorization frames. If these were 
listed explicitly, the entry would be difficult to 
create and to read. 
On the other hand, a representation which 
separately listed all the complement structures 
which could occur with a nominalization, as- 
suming they could freely co-occur, would fail 
to capture many crucial constraints between 
complements. For example, the nominaliza- 
tion confirmation has both THAT-S (His con- 
firmation THAT HE WOULD GO) and WH-S 
complements (His confirmation of WHETHER 
HE WOULD GO.). However, these com- 
plements cannot co-occur (*His confirmation 
THAT HE WOULD GO of WHETHER HE 
IVOULD GO.). Also in the case where the asso- 
ciated verb has an NP-AS-NP complement (She 
treated them as inferiors) and no AS-NP comple- 
ment (She emerged as their main competitor) the 
nominalization cannot have a bare AS-NP. Thus 
we have The consideration of HIM AS A CAN- 
DIDATE and HIS consideration AS A CANDI- 
DATE but not *The consideration AS A CAN- 
DIDATE. 
Guided by these considerations, we chose an 
approach in which we first determine which 
COMLEX verbal complements can correspond 
4 In COMLEX Syntax, some symbols designate sets of 
alternative complement structures, e.g., the ditransitive 
alternation. 
to phrases containing nominalizations and then 
we specify how these complements can be 
mapped to arguments of the nominalizations. 
The resulting COMLEX-based encoding does 
not permit incompatible complement phrases to 
co-occur, e.g., confirmation would not simulta- 
neously take both THAT-S and WH-S comple- 
ments. Optionality, obligatoriness and alterna- 
tive positions of phrases is stated in a simple 
notation, e.g., it can be stated in the entry for 
consideration that the verbal object for the NP- 
AS-NP complement of consider maps to either 
the DET-POSS position (HIS consideration as a 
candidate) or the PP-OF position (The consid- 
eration OF HIM as a candidate) and that this 
object is obligatory for mappings of NP-AS-NP, 
i.e., if the object is not present in the phrase 
containing consideration, then the phrase can- 
not be mapped to the NP-AS-NP complement, 
although other complements are possible. 
Our representation also accounts for the dif- 
ference in behavior of the core arguments (the 
subject, the object, and the indirect object) and 
the other arguments, which we shall refer to as 
oblique complements. The core arguments, as 
we have noted, can appear in several positions 
in the nominalization, and may be independently 
omitted or included. The oblique complements 
of the verb, on the other hand, generally translate 
directly into nominalization complements, either 
unchanged or occasionally with the addition of a 
preposition or a "that" complementizer. 
3 What is a NOMLEX Entry 
NOMLEX entries are organized as typed fea- 
ture structures and written in a Lisp-like no- 
tation (Figures 1 and 2). Each entry lists the 
nominalization (:ORTH) and the associated verb 
(:VERB). The :NOM-TYPE feature specifies the 
type of nominalization: VERB-NOM for nomi- 
nalizations which represent the action (destruc- 
tion) or state (knowledge) of the associated verb; 
VERB-PART for nominalizations which incor- 
porate a verbal particle (takeover); SUBJECT 
for nominalizations which represent the subject 
of the verb (teacher), and OBJECT for nom- 
inalizations which represent the object of the 
verb (appointee). The :NOUN keyword includes 
information about whether the word has non- 
nominalization noun senses (and may include 
some frequency information). For example, ap- 
27 
pointment has a sense which means something 
like "date to do something". We are only inter- 
ested in the nominalization sense in this paper. 5 
The heart of the entry is a list of verb subcat- 
egorizations, :VERB-SUBC, taken from COM- 
LEX Syntax. The name for each subcatego- 
rization is prefixed by NOM- (such as NOM- 
NP or NOM-NP-AS-NP) and, for subcatego- 
rizations involving prepositions, :PVAL specifies 
those prepositions. The COMLEX complements 
in these lexical entries include: 
• NP, a noun phrase complement, e.g., IBM 
appointed Mary 
• NP-PP, a complement consisting of a noun 
phrase and prepositional phrase, e.g., IBM 
appointed Mary for the vice presidency 
• NP-TO-INF-OC, a complement consisting 
of a noun phrase object and an infinitive 
clause, where the subject of the infinitive 
corresponds to the object of the main clause, 
e.g., IBM appointed Mary to do the job 
• NP-AS-NP, a complement consisting of a 
noun phrase object, the word "as" and a 
second noun phrase, e.g., IBM appointed 
Mary as vice president 
For each verb complement, the entry lists the as- 
sociated nominalized structure, if different from 
the verbal complement. The entry also lists the 
positions in which the object (:OBJECT) may 
appear. For appointment, these positions include 
the following for most complements: 
• DET-POSS, a possessive determiner, e.g., 
Alice Smith's appointment as vice president 
• N-N-MOD, a nominal prenominal modifier, 
e.g., the Alice Smith appointment for vice 
president 
• PP-OF, object of the preposition of, e.g., 
the appointment off Alice Smith 
SWhen two or more argument positions are frilled, the 
semantic classes of the arguments in the examples limit 
our patterns to the nominalization senses. However, pat- 
terns in which only one argmnent position is filled may 
match phrases that are ambiguous, e.g., Alice's appoint- 
ment can refer to either a dental appointment or an ap- 
pointment to the vice presidency. These cases are han- 
dled by other modules of Proteus, such as inference rules 
or reference resolution. 
(NOM :ORTH "appointment" 
:VERB "appoint" 
:PLURAL "appointments" 
:NOUN (exists) 
:NOM-TYPE (VERB-NOM) 
:VERB-SUBJ ((N-N-MOD) (DEW-BOSS)) 
:SUB J-ATTRIBUTE (COMMUNICATOR) 
:OBJ-ATTRIBUTE (NHUMAN) 
:VERB-SUBC 
((NOM-NP :OBJECT ((DEW-BOSS) (N-N-MOD) (PP-OF)) 
:REQUIRED ((OBJECT))) 
(NOM-NP-PP :OBJECT ((DEW-BOSS) (N-N-MOD) (PP-OF)) 
:PVAL ("for" "to"):REQUIRED ((OBJECT))) 
(NOM-NP-TO-INF-OC :OBJECT ((DEW-BOSS) (PP-OF)) 
:REQUIRED ((OBJECT))) 
(NOM-NP-AS-NP :OBJECT ((DEW-BOSS) (PP-OF)) 
:REQUIRED ((OBJECT)))}) 
Figure 1: NOMLEX entry for appointment 
(NOM :ORTH "appointee" 
:VERB "appoint" 
:PLURAL "appointees" 
:NOM-TYPE (OBJECT) 
:VERB-SUBJ ((PP-OF)(NOT-PP-BY)(N-N-MOD) (DEW-BOSS)) 
:SUB J-ATTRIBUTE (COMMUNICATOR) 
:OBJ-ATTRIBUTE (NHUMAN) 
:VERB-SUBC 
((NOM-NP) 
(NOM-NP-PP :P\(A.L ("for" "to")) 
(NOM-NP-AS-NP))) 
Figure 2: NOMLEX entry for appointee 
However, NOM-NP-AS-NP does not allow tile 
N-N-MOD position (* the Alice Smith appoint- 
ment as vice president). The :OBJECT is not 
indicated for the :VERB-SUBC of appointee be- 
cause the nominalization itself corresponds to the 
verbal object (it is :NOM-TYPE ((OBJECT))). 
Because a subject argument can appear with 
any verbal complement, we include, at the top 
level, a list of positions for the subject (:VERB- 
SUB J). This list can be further restricted for 
a particular complement by including a :SUB- 
JECT feature under that complement in the 
NOMLEX entry. As a default, it is assumed 
that subjects always can map to prepositional by 
phrases. Exceptions are marked with NOT-PP- 
BY, as in the entry for appointee ( *the appointee 
by IBM (for vice president)). 
Typically, a nominalization will list multiple 
28 
positions for each core argument. This doesn't 
mean, however, that all combinations of the po- 
sitions are possible. Several constraints limit 
the possible role assignments; some of these con- 
straints are general, and some are based on par- 
ticular lists in each entry: 
• The uniqueness constraint says that any 
verbal role may only be filled once. For ex- 
ample, in Leslie's appointment o/Alice, the 
PP-OF position filled by Alice must map 
into the object role. As a result, Leslie can- 
not fill the object role and therefore must 
fill the subject role. 6 
6This constraint is based on the stratal uniqueness 
theorem of (Johnson and Postal, 1980) and related work 
in Relational Grammar, which is assumed to be a con- 
straint across all languages. 
• The ordering constraint says that, if there 
are multiple pre-nominal modifiers, they 
must appear in the order subject, object, 
indirect object, and oblique; thus, for ex- 
ample, John Smith's school board appoint- 
ment cannot mean that the school board 
appointed John Smith to some position, z 
• Some entries contain :SUB&ATTRIBUTE 
and :OBJ-ATTRIBUTE features, selec- 
tional constraints which are useful in select- 
ing role assignments. In Figures 1 and 2, 
the attributes COMMUNICATOR (organi- 
zation, person, or other entity capable of 
communicating) and NHUMAN (a human) 
are used. 
• Obligatoriness constraints are assumed for 
the mappings associated with each com- 
plement in each entry. As a default, it 
is assumed that only subject and object 
are optional. Therefore, Mary Smith's ap- 
pointment would be associated with the 
NOM-NP complement, but not the NOM- 
NP-AS-NP complement. Furthermore, ob- 
jects are obligatory for a particular com- 
plement NP-X for a particular nominal- 
ization N, if N takes both NP-X and 
X as complements, where NP-X includes 
all the phrases in X plus an object (e.g., 
NOM-NP vs. NOM-INTRANS, NOM-NP- 
PP vs. NOM-PP, NOM-NP-THAT-S vs. 
NOM-THAT-S, etc.). These defaults can be 
overridden in the dictionary with attributes 
on specific complements specifying which 
roles are :OPTIONAL or :REQUIRED. For 
example, appointment takes a NOM-NP 
complement, but no corresponding NOM- 
INTRANS. The object is obligatory con- 
trary to our defaults, e.g., John's appoint- 
merit must have the interpretation that John 
is the object of appoint. Thus, our en- 
try for appointment is marked :REQUIRED 
((OBJECT)).s 
4 Our Procedure for Generating 
Norninalization Patterns 
Figure 3 diagrams how nominalization patterns 
are derived. The rectangles are modules of our 
~This ordering constraint is assumed to hold for all 
nominalizations in English. 
8Our required/optional settings only apply where 
some argument is present in a nominalization. 
29 
algorithm, the ovals are data structures passed 
between modules and the dotted lines connect 
the ovals with examples of what the data struc- 
tures might contain given the sample active 
clause IBM appointed Alice Smith. Due to space 
limitations, the figure does not include patterns 
with constituents for the tempOral adverbial NP 
positions (Section 5), e.g., Mary Smith's June 1, 
1998 appointment by IBM and Yesterday's ap- 
pointment of Mary Smith by IBM. There are an 
additional five such mappings for appointee and 
an additional twenty-three for appointment. 
First PET analyzes the sample sentence and 
identifies the main verb and its arguments (e.g., 
subject, direct object, etc.). Then it searches 
NOMLEX for any nominalizations which cor- 
respond to the main verb. Our example verb 
appoint has at least two nominalizations: ap- 
pointment and appointee. Next the procedure 
examines the set of :VERB-SUBC classes in each 
nominalization entry (Figures 1 and 2) and iden- 
tifies the set of classes which are compatible with 
the set of arguments in the input. A class is 
compatible if it allows all the input arguments, 
and none of its required arguments are missing. 
For the example sentence, only NOM-NP is cho- 
sen for each nominalization. The other phrases 
all require some phrase in addition to the ob- 
ject, e.g., NOM-NP-AS-NP requires an AS-NP 
phrase (e.g., as vice president). Next the per- 
missible role mappings are generated. By de- 
fault, the subject and object are optional, but 
the object is obligatory for appointment due to 
the :REQUIRED feature of its NOMLEX en- 
try. Prepositional phrases are assumed to oc- 
cur ill all orders, so that both (object: of, sub- 
ject: by) and (subject: by, object: of) are listed 
in Figure 3. The uniqueness constraint must 
be obeyed (we cannot have two subjects or two 
objects). Finally, the syntax of noun phrases 
only permits the N-N-MOD slot to be filled more 
than once (The IBM Alice Smith Appointment), 
and ill that case our ordering constraint would 
have to be obeyed. This rules out an inter- 
pretation of The Alice Smith IBM Appointment 
where Alice Smith is the appointee and IBM is 
the appointer. 9 
9Given a clausal pattern for an example sentence 
like They appointed Alice Smith to IBM, the NOM-NP- 
PP class would be matched and nominalization patterns 
would be generated in which IBM (the indirect object) 
S  ..................... IBM Alice Smith appointed 
............... IBM = Subject, Alice Smith = Object 
S 
~ "'"" / /AA pP ~inn tt ~ nt • I: ~ ~i:cCl:- ~e0t ° ~sb!e:l~j enct?~m. :.din) o(~ bJ ec t: det-p°s s' 
. (subject:by, object: of) 
°°•• 
. 
.... °-'" 
q/ " 
o• 
.°" 
• •'° •• •° 
• • • •• 
° • 
°° •• 
° 
(object: of, subject: by) 
(subject:det-poss) (object: det-poss) 
(object: n-n-mod) (object: of) 
(subject: by) (subject:n-n-mod) 
Get Permissible Role Mappings -'"'i'" "" -" " 
\ i ..: 
• ..... 
.•-" 
@minalization Pattems~ .... 
°'''-.. 
-° .. 
*° 
Det n(appointee) of np(C-company) The appointee of IBM Det np(C-company) n(appointee) The IBM appointee 
np(C-company) 's n(appointee) IBM's appointee 
np(C-company) 's np(C-person) n(C-appointment) IBM's Alice Smith appointment 
np(C-company)'s n(C-appointment) of np(C-person) IBM's appointment of Alice Smith 
Det np(C-company) np(C-person) n(C-appointment) 
The IBM Alice Smith appointment 
Det np(C-company) n(C-appointment) of np(C-person) The IBM appointment of Alice Smith 
np(C-person) 's n(C-appointment) by np(C-company) 
Alice Smith's appointment by IBM Det np(C-person) n(C-appointment) by np(C-company) 
The Alice Smith appointment by IBM Det n(C-appointment) of np(C-person) by np(C-company) 
The appointment of Alice Smith by IBM Det n(C-appointment) by np(C-company) of np(C-person) 
The appointment by IBM of Alice Smith np(C-company)'s n(C-appointment) IBM's appointment 
rip(C-person) 's n(C-appointment) Alice Smith's appointment Det np(C-person) n(C-appointment) The Alice Smith appointment 
Det n(C-appointment) of np(C-person) The appointment of Alice Smith 
Det n(C-appointment) by np(C-company) The appointment by IBM Det rip(C-company) n(C-appointment) The IBM appointment 
Figure 3: Deriving Nominalization Patterns with PET 
30 
PET can then use these mappings to gener- 
ate patterns, as it does for the various types of 
clauses. Using pattern matching and dictionary 
look-up, PET associates the verbal arguments 
with semantic classes. In our example, the sub- 
ject is a company and the objec t is a person. 
This information can be applied to each map- 
ping to produce a pattern. The nominalization 
patterns in Figure 3 are generated from the role 
mappings listed using this semantic information 
and interpretting the nominal role labels. For 
example, the mapping (SUBJECT: DET-POSS, 
OBJECT: PP-OF) generates the nominalization 
pattern: 
np(C-company) 's n(appointment)of 
np(C-person) 
(IBM's appointment of Alice Smith). 
5 Adjunct Mappings 
The preceding section gave a simplified account 
of mapping nominalization patterns. We must 
also handle certain adjuncts. Temporal PPs that 
can occur in clauses can usually occur in nom- 
inalizations as well. The positions DET-POSS 
and N-N-MOD may be occupied by temporal 
NPs (Yesterday's appointment of Alice Smith by 
IBM, The January 3, 1998 appointment by IBM 
of Alice Smith). When an NP is temporal and 
occupies either of these positions it may fill a 
temporal slot in an IE pattern. Since temporal 
NPs are neither companies, nor people, they will 
not fill the object or subject slots in the IE pat- 
terns above. Therefore, the possibility of filling 
temporal slots from DET-POSS and N-N-MOD 
positions should cause no conflicts for appoint- 
ment. 
6 Related Work 
Other computational linguistics work on decod- 
ing nominalizations includes (Hobbs and Grish- 
man, 1976), (DaM et al., 1987) and (Hull and 
Gomez, 1996). (Hull and Gomez, 1996) is the 
most similar to our own in that their ultimate 
goal is to extract information from the World 
Book Encyclopedia. That task is defined differ- 
ently than for our MUC-related work. The lex- 
ical entries created by Hull and Gomez include 
would follow Afice Smith (the direct object). These pat- 
terns would match The Alice Smith IBM appointment (or 
Alice Smith's IBM appointment) and give it a very sim- 
ilar interpretation to one in which IBM is the appointer. 
31 
selectional constraints tied to WordNet classes. 
Their procedure for converting nominalizations 
into predicate argument structure relies on this 
semantic information, which they use to distin- 
guish nominalizations from nouns and arguments 
from adjuncts. Their coverage of arguments is 
limited to subjects, objects, and prepositional 
phrases, whereas NOMLEX provides detailed 
coverage of all core and all oblique arguments. 
7 Concluding Remarks 
We have been working on NOMLEX for one year 
with a staff of two part-time graduate students, 
one full-time staff member and one part-time 
staff member. We currently have 700 entries 
and expect to have 1000 entries by Fall of 1998. 
After testing, we intend to distribute an alpha 
version of NOMLEX via our FTP site. This pa- 
per describes one of the applications for which 
NOMLEX proves useful. Our hope is that other 
researchers will apply NOMLEX to new applica- 
tions. Furthermore, comments from users should 
prove helpful for updating and revising this re- 
source. 

References 
Douglas Appelt, Jerry Hobbs, John Bear, David 
Israel, Megumi Kameyama, Andy Kehler, 
David Martin, Karen Meyers, and Mabry 
Tyson. 1995. SRI International FASTUS Sys- 
tem: MUC-6 Test Results and Analysis. In 
Proceedings of the Sixth Message Understand- 
ing Conference. 
Debroah Dahl, Martha Palmer, and Rebecca 
Passonneau. 1987. Nominalizations in PUN- 
DIT. Ill Proceedings of the 25th Annual Meet- 
in 9 of the Association for Computational Lin- 
guistics. 
Ralph Grishman. 1995. The NYU system for 
MUC-6 or where's the syntax? In Proceedings 
of the Sixth Message Understanding Confer- 
ence. 
Jerry R. Hobbs and Ralph Grishman. 1976. The 
Automatic Transformational Analysis of En- 
glish Sentences: An Implementation. Inter- 
national Journal of Computer Mathematics, 
5:267-283. 
A. S. Hornby, editor. 1980. Oxford Advanced 
Learner's Dictionary of Current English. Ox- 
ford University Press, Oxford. 
Richard D. Hull and Fernando Gomez. 1996. 
Semantic Interpretation of Nominalizations. 
In Proceedings of the Thirteenth National 
Conference on Artificial Intelligence and the 
Eighth Innovative Applications of Artificial 
Intelligence Conference. 
David E. Johnson and Paul M. Postal. 1980. Arc 
Pair Grammar. Princeton University Press, 
Princeton. 
Catherine Macleod, Adam Meyers, Ralph Grish- 
man, Leslie Barrett, and Ruth Reeves. 1997. 
Designing a Dictionary of Derived Nominals. 
In Proceedings of Recent Advances in Natural 
Language Processing, Tzigov Chark, Bulgaria. 
Catherine Macleod, Ralph Grishman, and Adam 
Meyers. forthcoming. COMLEX Syntax: A 
Large Syntactic Dictionary for Natural Lan- 
guage Processing. Computers and the Hu- 
manities. 
1995. Proceedings of the Sixth Message Un- 
derstanding Conference. Morgan I(aufnmn. 
(MUC-6). 
1998. Proceedings of the SeveT~th Message UI~- 
derstanding Conference. Morgan Kaufman. 
(MUC-7). 
P. Proctor, editor. 1978. Longman DictioT~ary 
of Contemporary English. Harlow, Essex. 
Susanne Rohen Wolff, Catherine Macleod, and 
Adam Meyers, 1994. Comlex IVord Classes 
Manual. Proteus Project, New York Univer- 
sity. 
Roman Yangarber and Ralph Grishman. 1997. 
Customization of Information Extraction Sys- 
tems. In Proceedings of the International 
Workshop on Lexically Driven I~formation 
Eztraction, Frascati, Italy. 
