Introduction to WordNet: An On-line Lexical Database
George A. Miller, Richard Beckwith, Christiane Fellbaum,
Derek Gross, and Katherine Miller
(Revised August 1993)
WordNet is an on-line lexical reference system whose design is inspired by current
psycholinguistic theories of human lexical memory. English nouns, verbs, and adjectives are
organized into synonym sets, each representing one underlying lexical concept. Different
relations link the synonym sets.
Standard alphabetical procedures for organizing lexical information put together
words that are spelled alike and scatter words with similar or related meanings
haphazardly through the list. Unfortunately, there is no obvious alternative, no other
simple way for lexicographers to keep track of what has been done or for readers to find
the word they are looking for. But a frequent objection to this solution is that finding
things on an alphabetical list can be tedious and time-consuming. Many people who
would like to refer to a dictionary decide not to bother with it because finding the
information would interrupt their work and break their train of thought.
In this age of computers, however, there is an answer to that complaint. One
obvious reason to resort to on-line dictionaries—lexical databases that can be read by
computers—is that computers can search such alphabetical lists much faster than people
can. A dictionary entry can be available as soon as the target word is selected or typed
into the keyboard. Moreover, since dictionaries are printed from tapes that are read by
computers, it is a relatively simple matter to convert those tapes into the appropriate kind
of lexical database. Putting conventional dictionaries on line seems a simple and natural
marriage of the old and the new.
Once computers are enlisted in the service of dictionary users, however, it quickly
becomes apparent that it is grossly inefficient to use these powerful machines as little
more than rapid page-turners. The challenge is to think what further use to make of
them. WordNet is a proposal for a more effective combination of traditional
lexicographic information and modern high-speed computation.
This, and the accompanying four papers, is a detailed report of the state of WordNet
as of 1990. In order to reduce unnecessary repetition, the papers are written to be read
consecutively.
Psycholexicology
Murray’s Oxford English Dictionary (1928) was compiled ‘‘on historical
principles’’ and no one doubts the value of the OED in settling issues of word use or
sense priority. By focusing on historical (diachronic) evidence, however, the OED, like
other standard dictionaries, neglected questions concerning the synchronic organization
of lexical knowledge.
- 2 -
It is now possible to envision ways in which that omission might be repaired. The
20th Century has seen the emergence of psycholinguistics, an interdisciplinary field of
research concerned with the cognitive bases of linguistic competence. Both linguists and
psycholinguists have explored in considerable depth the factors determining the
contemporary (synchronic) structure of linguistic knowledge in general, and lexical
knowledge in particular—Miller and Johnson-Laird (1976) have proposed that research
concerned with the lexical component of language should be called psycholexicology.
As linguistic theories evolved in recent decades, linguists became increasingly explicit
about the information a lexicon must contain in order for the phonological, syntactic, and
lexical components to work together in the everyday production and comprehension of
linguistic messages, and those proposals have been incorporated into the work of
psycholinguists. Beginning with word association studies at the turn of the century and
continuing down to the sophisticated experimental tasks of the past twenty years,
psycholinguists have discovered many synchronic properties of the mental lexicon that
can be exploited in lexicography.
In 1985 a group of psychologists and linguists at Princeton University undertook to
develop a lexical database along lines suggested by these investigations (Miller, 1985).
The initial idea was to provide an aid to use in searching dictionaries conceptually, rather
than merely alphabetically—it was to be used in close conjunction with an on-line
dictionary of the conventional type. As the work proceeded, however, it demanded a
more ambitious formulation of its own principles and goals. WordNet is the result.
Inasmuch as it instantiates hypotheses based on results of psycholinguistic research,
WordNet can be said to be a dictionary based on psycholinguistic principles.
How the leading psycholinguistic theories should be exploited for this project was
not always obvious. Unfortunately, most research of interest for psycholexicology has
dealt with relatively small samples of the English lexicon, often concentrating on nouns
at the expense of other parts of speech. All too often, an interesting hypothesis is put
forward, fifty or a hundred words illustrating it are considered, and extension to the rest
of the lexicon is left as an exercise for the reader. One motive for developing WordNet
was to expose such hypotheses to the full range of the common vocabulary. WordNet
presently contains approximately 95,600 different word forms (51,500 simple words and
44,100 collocations) organized into some 70,100 word meanings, or sets of synonyms,
and only the most robust hypotheses have survived.
The most obvious difference between WordNet and a standard dictionary is that
WordNet divides the lexicon into five categories: nouns, verbs, adjectives, adverbs, and
function words. Actually, WordNet contains only nouns, verbs, adjectives, and adverbs.
1
The relatively small set of English function words is omitted on the assumption
(supported by observations of the speech of aphasic patients: Garrett, 1982) that they are
probably stored separately as part of the syntactic component of language. The
realization that syntactic categories differ in subjective organization emerged first from
studies of word associations. Fillenbaum and Jones (1965), for example, asked English-
1
A discussion of adverbs is not included in the present collection of papers.
- 3 -
speaking subjects to give the first word they thought of in response to highly familiar
words drawn from different syntactic categories. The modal response category was the
same as the category of the probe word: noun probes elicited nouns responses 79% of the
time, adjectives elicited adjectives 65% of the time, and verbs elicited verbs 43% of the
time. Since grammatical speech requires a speaker to know (at least implicitly) the
syntactic privileges of different words, it is not surprising that such information would be
readily available. How it is learned, however, is more of a puzzle: it is rare in connected
discourse for adjacent words to be from the same syntactic category, so Fillenbaum and
Jones’s data cannot be explained as association by continguity.
The price of imposing this syntactic categorization on WordNet is a certain amount
of redundancy that conventional dictionaries avoid—words like back, for example, turn
up in more than one category. But the advantage is that fundamental differences in the
semantic organization of these syntactic categories can be clearly seen and systematically
exploited. As will become clear from the papers following this one, nouns are organized
in lexical memory as topical hierarchies, verbs are organized by a variety of entailment
relations, and adjectives and adverbs are organized as N-dimensional hyperspaces. Each
of these lexical structures reflects a different way of categorizing experience; attempts to
impose a single organizing principle on all syntactic categories would badly misrepresent
the psychological complexity of lexical knowledge.
The most ambitious feature of WordNet, however, is its attempt to organize lexical
information in terms of word meanings, rather than word forms. In that respect,
WordNet resembles a thesaurus more than a dictionary, and, in fact, Laurence Urdang’s
revision of Rodale’s The Synonym Finder (1978) and Robert L. Chapman’s revision of
Roget’s International Thesaurus (1977) have been helpful tools in putting WordNet
together. But neither of those excellent works is well suited to the printed form. The
problem with an alphabetical thesaurus is redundant entries: if word W
x
and word W
y
are
synonyms, the pair should be entered twice, once alphabetized under W
x
and again
alphabetized under W
y
. The problem with a topical thesaurus is that two look-ups are
required, first on an alphabetical list and again in the thesaurus proper, thus doubling a
user’s search time. These are, of course, precisely the kinds of mechanical chores that a
computer can perform rapidly and efficiently.
WordNet is not merely an on-line thesaurus, however. In order to appreciate what
more has been attempted in WordNet, it is necessary to understand its basic design
(Miller and Fellbaum, 1991).
The Lexical Matrix
Lexical semantics begins with a recognition that a word is a conventional
association between a lexicalized concept and an utterance that plays a syntactic role.
This definition of ‘‘word’’ raises at least three classes of problems for research. First,
what kinds of utterances enter into these lexical associations? Second, what is the nature
and organization of the lexicalized concepts that words can express? Third, what
syntactic roles do different words play? Although it is impossible to ignore any of these
questions while considering only one, the emphasis here will be on the second class of
- 4 -
problems, those dealing with the semantic structure of the English lexicon.
Since the word ‘‘word’’ is commonly used to refer both to the utterance and to its
associated concept, discussions of this lexical association are vulnerable to
terminological confusion. In order to reduce ambiguity, therefore, ‘‘word form’’ will be
used here to refer to the physical utterance or inscription and ‘‘word meaning’’ to refer to
the lexicalized concept that a form can be used to express. Then the starting point for
lexical semantics can be said to be the mapping between forms and meanings (Miller,
1986). A conservative initial assumption is that different syntactic categories of words
may have different kinds of mappings.
Table 1 is offered simply to make the notion of a lexical matrix concrete. Word
forms are imagined to be listed as headings for the columns; word meanings as headings
for the rows. An entry in a cell of the matrix implies that the form in that column can be
used (in an appropriate context) to express the meaning in that row. Thus, entry E
1,1
implies that word form F
1
can be used to express word meaning M
1
. If there are two
entries in the same column, the word form is polysemous; if there are two entries in the
same row, the two word forms are synonyms (relative to a context).
Table 1
Illustrating the Concept of a Lexical Matrix:
F
1
and F
2
are synonyms; F
2
is polysemous
Word Word Forms
Meanings F
1
F
2
F
3
. . . F
n
M
1
E
1,1
E
1,2
M
2
E
2,2
M
3
E
3,3
. .
. .
. .
M
m
E
m,n
Mappings between forms and meanings are many:many—some forms have several
different meanings, and some meanings can be expressed by several different forms.
Two difficult problems of lexicography, polysemy and synonymy, can be viewed as
complementary aspects of this mapping. That is to say, polysemy and synonymy are
problems that arise in the course of gaining access to information in the mental lexicon: a
listener or reader who recognizes a form must cope with its polysemy; a speaker or writer
who hopes to express a meaning must decide between synonyms.
As a parenthetical comment, it should be noted that psycholinguists frequently
represent their hypotheses about language processing by box-and-arrow diagrams. In
that notation, a lexical matrix could be represented by two boxes with arrows going
between them in both directions. One box would be labeled ‘Word Meaning’ and the
other ‘Word Form’; arrows would indicate that a language user could start with a
meaning and look for appropriate forms to express it, or could start with a form and
- 5 -
retrieve appropriate meanings. This box-and-arrow representation makes clear the
difference between meaning:meaning relations (in the Word Meaning box) and
word:word relations (in the Word Form box). In its initial conception, WordNet was
concerned solely with the pattern of semantic relations between lexicalized concepts; that
is to say, it was to be a theory of the Word Meaning box. As work proceeded, however,
it became increasingly clear that lexical relations in the Word Form box could not be
ignored. At present, WordNet distinguishes between semantic relations and lexical
relations; the emphasis is still on semantic relations between meanings, but relations
between words are also included.
Although the box-and-arrow representation respects the difference between these
two kinds of relations, it has the disadvantage that the intricate details of the many:many
mapping between meanings and forms are slighted, which not only conceals the
reciprocity of polysemy and synonymy, but also obscures the major device used in
WordNet to represent meanings. For that reason, this description of WordNet has been
introduced in terms of a lexical matrix, rather than as a box-and-arrow diagram.
How are word meanings represented in WordNet? In order to simulate a lexical
matrix it is necessary to have some way to represent both forms and meanings in a
computer. Inscriptions can provide a reasonably satisfactory solution for the forms, but
how meanings should be represented poses a critical question for any theory of lexical
semantics. Lacking an adequate psychological theory, methods developed by
lexicographers can provide an interim solution: definitions can play the same role in a
simulation that meanings play in the mind of a language user.
How lexicalized concepts are to be represented by definitions in a theory of lexical
semantics depends on whether the theory is intended to be constructive or merely
differential. In a constructive theory, the representation should contain sufficient
information to support an accurate construction of the concept (by either a person or a
machine). The requirements of a constructive theory are not easily met, and there is
some reason to believe that the definitions found in most standard dictionaries do not
meet them (Gross, Kegl, Gildea, and Miller, 1989; Miller and Gildea, 1987). In a
differential theory, on the other hand, meanings can be represented by any symbols that
enable a theorist to distinguish among them. The requirements for a differential theory
are more modest, yet suffice for the construction of the desired mappings. If the person
who reads the definition has already acquired the concept and needs merely to identify it,
then a synonym (or near synonym) is often sufficient. In other words, the word meaning
M
1
in Table 1 can be represented by simply listing the word forms that can be used to
express it: {F
1
, F
2
, . . . }. (Here and later, the curly brackets, ‘{’ and ‘},’ surround the
sets of synonyms that serve as identifying definitions of lexicalized concepts.) For
example, someone who knows that board can signify either a piece of lumber or a group
of people assembled for some purpose will be able to pick out the intended sense with no
more help than plank or committee. The synonym sets, {board, plank} and {board,
committee} can serve as unambiguous designators of these two meanings of board.
These synonym sets (synsets) do not explain what the concepts are; they merely signify
that the concepts exist. People who know English are assumed to have already acquired
