Title: The SPECIALIST Lexicon and Lexical Tools
1The SPECIALIST Lexicon and Lexical Tools
- Allen Browne
- Guy Divita
- Chris Lu
2(No Transcript)
3Text processing
Lexical tools
SPECIALIST LEXICON
4The SPECIALIST Lexicon
- A syntactic lexicon
- Biomedical and general English
- Over 180,000 records
5The SPECIALIST Lexicon
- General English
- 10,000 most frequent words from the American
Heritage word frequency list - 2,000 words used by Longmans Dictionary of
Contemporary English - Verbs and adjectives identified by heuristics
6Lexicon Growth
7George A. Miller The Science of Words 1991
8The SPECIALIST Lexicon
- Morphology
- Inflection
- Derivation
- Orthography
- Spelling variants
- Syntax
- Complementation for verbs, nouns, and adjectives
9Morphology
- Inflectional
- nucleus -- nuclei
- cauterize, cauterizes, cauterized, cauterizing
- red, redder reddest
- Derivational
- laryngeal -- larynx
- transport -- transportation
10Inflectional Morphology
The pitcher wound up and he flang the ball at the
batter. The batter swang and missed. The pitcher
flang the ball again and this time the batter
connected. He hit a high fly right to the center
fielder. The center fielder was all set to catch
the ball, but at the last minute his eyes were
blound by the sun and he dropped it. --J. H.
"Dizzy" Dean
11Derivational Morphology
Dictionary ology ist
12Orthography
Spelling Variation
- align -- aline
- Graves disease -- Gravess disease -- Graves
disease - anesthetize -- anaesthetise
- esophagus -- oesophagus
13British and American Spelling
- Criticise -- criticize
- naturalise --naturalize
- centre -- center
- foetus -- fetus
14Syntax -- Verb Complements
- Intran
- Ill treat.
- trannp
- He treated the patient.
- ditrannp,pphr(with,np)
- She treated the patient with the drug.
15Syntax -- Verb Complements
basetreat entryE0061964 catverb variantsreg
intran trannp tranpphr(with,np) tranpphr(o
f,np) ditrannp,pphr(to,np) ditrannp,pphr(with,
np) ditrannp,pphr(for,np) cplxtrannp,advbl no
minalizationtreatmentnounE0061968
16The 2003 SPECIALIST Lexicon
17(No Transcript)
18Lexicon Unit Records
basechronic entryE0016869 catadj variantsin
v positionattrib(1) positionpred stative
baseKaposi's sarcoma spelling_variantKaposi
sarcoma entryE0003576 catnoun variantsuncount
variantsreg variantsglreg
baseaspirate entryE0010803 catverb
variantsreg trannp
nominalizationaspirationnounE0010804
basein entryE0033870 catprep
19Noun Variants
- Kaposis sarcoma
- Kaposis sarcomas
- Kaposis sarcomata
- Kaposi sarcoma
- Kaposi sarcomas
- Kaposi sarcomata
baseKaposi's sarcoma spelling_variantKaposi
sarcoma entryE0003576 catnoun variantsuncount
variantsreg variantsglreg
20Regular Nouns
The plural suffix is s. y becomes ie following a
consonant before s. e is inserted before s if the
base ends in s, z, x, ch, or s
21Regular Nouns
22Greco-latin Regular nouns
23Uncount Nouns(abstract or mass)
basesmallpox entryE0056359 catnoun variants
uncount basepotassium entryE0049387 catnoun
variantsuncount
- a smallpox
- two smallpoxes
- much smallpox
- a potassium
- two potassiums
- much potassium
24Fixed Plural Nouns
basescissors entryE0054633 catnoun
variantsplur
basepolice entryE0048616 catnoun variantspl
ur
25Irregular Nouns
baselarynx entryE0036919 catnoun
variantsirreglarynges variantsreg
basecorpus entryE0019113 catnoun
variantsirregcorpora variantsreg
26Regular Verbs
- The third person present tense suffix is s.
- y becomes ie following a consonant before s.
- e is inserted between z, x, ch, or sh and s.
- The past tense suffix is ed.
- y becomes ie following a consonant before ed.
- Final e is deleted before ed.
27Regular Verbs
- dismissdismisses, dismissed, dismissing
- agree agrees agreed agreeing
- dry dries, dried, drying
28Regular Doubling Verbs
- End in a CVC pattern
- Double the final consonant before ed and ing.
- Are otherwise regular
- variantsregd
- e.g. control controls, controlled, controlling
29Irregular Verbs
basedive catverb variantsreg
variantsirregdivesdovedovediving
intran intranpart(in) ...
30Dive vs. Dove
31Regular Adjectives and Adverbs
- The comparative suffix is er.
- The superlative suffix is est.
- y become ie after a consonant before er or est.
- Final e is deleted before er or est.
- e.g. green greener, greenest
32Regular Doubling Adjectives and Adverbs
- CVC final pattern
- Final consonant is doubled before ed or est.
- Otherwise regular
- e.g. red redder, reddest
33Ancillary Data Bases
- Synonymy
- sm.db
- Derivation
- dm.db, dm.rules
- Inflection
- im.rules
- Neoclassical compounds
- nc.db
34Derivational Facts and Rules
dm.facts treatmentnountreatverb prohibitionno
unprohibitiveadj cell lineagenouncell
linenoun photochemotherapeuticadjphotochemother
apynoun pharmacotherapeuticadjpharmacotherapyn
oun
35Derivational Facts and Rules
dm.rules e.g. alienationalienate ationnouna
teverb rationrate stationstate
36Inflectional Facts and Rules
im.rules Noun rules (glreg) usnounsingular
inounplural antusanti manounsingularm
atanounplural anounsingularaenounplural
umnounsingularanounplural onnounsingular
anounplural sisnounsingularsesnounplura
l isnounsingularidesnounplural mennounsi
ngularminanounplural exnounsingularicesn
ounplural xnounsingularcesnounplural
37Neoclassical compounds
nc.db abdomin(o)abdomenroot abaway
fromprefix acanth(o)prickleroot acar(o)mitero
ot acetabul(o)acetabulumroot adtowardsprefix a
gogueinducingterminal albumin(o)albuminroot si
sconditionterminal stomysurgical
openingterminal
38Synonyms
sm.db alaradjwingnoun amygdalineadjtonsilno
un articularadjjointnoun bulbaradjmedulla
oblongatanoun fununcularadjboilnoun genicular
adjkneenoun hepatocellularadjliver
cellsnoun lazaradjleprosynoun lenticularadjc
rystalline lensnoun ypsiliformadjupsiloidadj w
olframnountungstennoun double
visionnoundiplopianoun
39Relational Tables
- One line records
- Pipe separated Fields --
- Keyed to EUI
- LRAGR matches forms to EUIs
- Word index LRWD
40Relational Tables
- LRAGR - Agreement
- LRCMP - Complements
- LRFIL - Files
- LRFLD - Fields
- LRMOD - Modification
- LRNOM - Nominalization
- LRPRN - Pronouns
- LRPRP - Properties
- LRSPL - Spelling
- LRTRM - Trademarks
- LRWD - Word index
41LRAGR
Agreement and Inflection
- EUI - Entry ID
- STR - Inflected form
- SCA - Syntactic category
- AGR - agreement information
- BAS - Base form (morphological)
- CIT - Citation form (base)
42LRAGR
E0003576Kaposi sarcomasnouncount(thr_plur)Kapo
si sarcomaKaposi's sarcoma E0003576Kaposi
sarcomatanouncount(thr_plur)Kaposi
sarcomaKaposi's sarcoma E0003576Kaposi
sarcomanouncount(thr_sing)Kaposi
sarcomaKaposi's sarcoma E0003576Kaposi
sarcomanoununcount(thr_sing)Kaposi
sarcomaKaposi's sarcoma E0003576Kaposi's
sarcomasnouncount(thr_plur)Kaposi's
sarcomaKaposi's sarcoma E0003576Kaposi's
sarcomatanouncount(thr_plur)Kaposi's
sarcomaKaposi's sarcoma E0003576Kaposi's
sarcomanouncount(thr_sing)Kaposi's
sarcomaKaposi's sarcoma E0003576Kaposi's
sarcomanoununcount(thr_sing)Kaposi's
sarcomaKaposi's sarcoma
43Number Words
- one, thirteen fifty, thousand, million
- Not in the lexicon.
- No part of speech
- Used to construct number expressions
- Three thousand eight hundred and five
- To be released in the 2003 lexicon.
- Accompanying number tools.
44basetwo catnumber_word entryN0000003
variantsecondordinal variantseconddenom
inator,singularpart_denominator
variantseconddenominator,pluralpart_denominator
varianthalfdenominator,singularfull_denomi
nator varianthalvesdenominator,pluralfull_d
enominator number_typeunit value2
digit2
45basetwenty catnumber_word
entryN0000021 variantsreg
number_typedecade value20 digit2
basetwelve catnumber_word
entryN0000013 variantsreg
number_typeteen value12
basebillion catnumber_word
entryN0000032 variantsreg
number_typemagnitude power3
basesexdecillion catnumber_word
entryN0000046 variantsreg
number_typemagnitude power17
46sixty four million four hundred thousand
64 1,000,000 400,000 64,400,000
47Text processing
Lexical tools
SPECIALIST LEXICON
48Lexical Tools
- Wordind -- breaks strings into words
- Produces the Metathesaurus word indexes (MRXW)
- LVG -- performs various lexical transformations
- NORM -- a selection of LVG transformations,
- Used for Metathesaurus indexing
- Produces the Metathesaurus Normalized word and
string indexes (MRXNW MRXNS) - Used to access those indexes
49Normalization
- Hodgkin Disease
- HODGKINS DISEASE
- Hodgkin's Disease
- Disease, Hodgkin's
- HODGKIN'S DISEASE
- Hodgkin's disease
- Hodgkins Disease
- Hodgkin's disease NOS
- Hodgkin's disease, NOS
- Disease, Hodgkins
- Diseases, Hodgkins
- Hodgkins Diseases
- Hodgkins disease
- hodgkin's disease
- DiseaseHodgkins
- Disease, Hodgkin