grammar_cop 0.1.0

data/data/en/4.0.knowledge

@@ -0,0 +1,306 @@
+; Post-processing knowledge file
+; 6/96
+
+; ----------------------------------------------------------------------------
+; This file contains the knowledge related to post-processing, in the 
+; form of lists and rules. This file is read by post-process.c at run-time. 
+; Syntax of file:
+;           line starting with ";" is a comment
+;           commas are field delimiters 
+;           any token beginning with the character @ is expanded to the set
+;               of symbols it defined. e.g. one could write
+; FOO: blah1 blah2 blah3
+; thus defining a set FOO containing three strings. Then one could later write
+; BAR: blah5 @FOO blah8
+; which defines a set BAR containing 5 strings. 
+; 
+; Capitalized tokens are *required*, though if you feel like providing an
+; empty list afterwards, that's your right.
+; ----------------------------------------------------------------------------
+
+
+; The following links start a domain. Each must be given a name in the
+; table below (STARTING_LINK_TYPE_TABLE)
+  
+DOMAIN_STARTER_LINKS: 
+ W   Ce   Cs   Ca   Cc   Ci   R*   Rn   Re   RSe  Mr   QI#d   Mv*   Jr  Mj   Qd  
+ TOn   TOi   Mg*   MVi  Ss#d   Bsd   ER   Z  Ma#*   SIs#g  BIqx   MX#p   MX#a  
+ MX#r   MX#j   MV#o   MV#p  Eq   COq   CCq  AFd   PFc 
+
+
+
+; ----------------------------------------------------------------------
+; The following links start a urfl domain.  They are also included in the 
+; domain, as opposed to regular starter links (above), which are not. A
+; urfl domain includes links accessible from the root word, tracing to
+; the right (as well as everything accessible from the left end of the 
+; starter link).
+
+URFL_DOMAIN_STARTER_LINKS:  TOo   I#j  Pa##j   CP
+
+
+
+; ----------------------------------------------------------------------
+; The following start a urfl_only domain. These include _only_ links :
+; reachable from the root word, tracing to the right. They aren't
+; included in the domain
+
+URFL_ONLY_DOMAIN_STARTER_LINKS:  SFsx   Ss#g   COp    
+
+
+
+; ----------------------------------------------------------------------
+; Links which start a domain and are also part of the domain. This must be 
+; a sublist of the domain_starter_list 
+
+DOMAIN_CONTAINS_LINKS: 
+ Mg*   Mx   Bsd   MX#a   Ma#*   Mv*   MX#r   Ss#d   Ws   Wq  Qd   Mj   Wj 
+ Wi  MX#j   AFd   PFc   Jr   Wd   Mr
+
+
+
+; ----------------------------------------------------------------------
+; These links are not put in the word/link graph. They also cannot be the 
+; starter links for a domain. (These links may also only be used in cycles.)
+
+IGNORE_THESE_LINKS: Xca
+
+
+
+; ----------------------------------------------------------------------
+; These links may only be used in cycles.
+
+MUST_FORM_A_CYCLE_LINKS:  R#*   TOt   EXx   HA    SFsic   Jr  JQ  Xca
+
+
+; ----------------------------------------------------------------------
+; These links are not traced further if they point back before the root word.
+; The creation of Rw necessitated making B#m a restricted link, to
+; prevent the (e) domain, started by Ce, from extending around through
+; the Rw link.
+; Reverted.
+; This breaks parsing of 
+;    How fast a program does he think it is
+;    I wonder how fast a program he thinks it is
+;    I wonder how much money you earned
+;    I wonder how many people you saw
+;    I wonder how big a department it is
+;    I wonder how much oil they spilled
+;    This is the man whose dog I bought
+;    I wonder which dog he said you chased
+;    How efficient a program is it
+; Meanwhile, I can't find the Ce problem mentioned ... this needs more
+; documentation!
+
+RESTRICTED_LINKS: 
+   B#*  D##w   B#w   B#d   AFh  MVt   Xx   HL   SFsic  AFd   Bc   CX  EAh  
+   H   HA   PFc   B#j   Wd   PF   Z
+
+;   H   HA   PFc   B#j   Wd   PF   Z  B#m
+
+
+; ----------------------------------------------------------------------
+; ---------------------- LINK TYPE TABLE-------------------------------
+; ----------------------------------------------------------------------
+; The following table associates a domain type with each possible
+; starting link. It contains pairs: the first of each pair is a link
+; type, and the second is the domain to which that link type belongs.
+
+STARTING_LINK_TYPE_TABLE: 
+ Ce    e  
+ R*    r  
+ Rn    r
+ Re    r  
+ W     m  
+ RSe   e  
+ Cs    s  
+ Ca    s  
+ Jr    e  
+ Mr    r  
+ Cc    s  
+ Mv*   e  
+ QI#d  s  
+ BIqx  s  
+ TOn   e  
+ TOi   e  
+ MVi   e  
+ MV#o  s  
+ MV#p  s  
+ AFd   s  
+ PFc   s  
+ Mg*   e  
+ Mj    j  
+ Qd    m  
+ MX#j  j  
+ TOo   x  
+ I#j   x  
+ Pa##j x  
+ CP    x
+ COp   d  
+ SFsx  d  
+ Ss#g  d  
+ SIs#g s  
+ Ss#d  s  
+ Bsd   s  
+ ER    s  
+ Z     s  
+ Ma#*  e  
+ MX#p  e  
+ Ci    e  
+ MX#a  e  
+ Eq    e  
+ COq   e  
+ CCq   s  
+ MX#r  r 
+
+
+; ----------------------------------------------------------------------
+; ----------------------- LINK SETS ------------------------------------
+; ----------------------------------------------------------------------
+; (Not in use at present; see comment at beginning of file)
+
+; ----------------------------------------------------------------------
+; ----------------- RULES ----------------------------------------------
+; ----------------------------------------------------------------------
+; Explanation of syntax: as usual, each stanza begins with a label 
+; terminated by a colon. The interpretation of the rule depends on 
+; the label, as specified in each stanza.
+
+; The following rule asserts that the linkage must *still* be connected 
+; when the specified set(s) of links are removed from the linkage.
+
+FORM_A_CYCLE_RULES:
+        @MUST_FORM_A_CYCLE_LINKS  ,  "'must form a cycle' violation0"
+
+
+; For the following rules, if a domain contains a link matching the 1st 
+; column, it must also contain a linkage matching one of the members of the 
+; set in the 2nd column. The individual rules are demarcated by semicolons and
+; the fields within a rule are demarcated by commas. 
+
+CONTAINS_ONE_RULES:
+ SI#*  ,  Wq    Qd    CQ    PFc             , "Bad use of s-v inversion1" ,
+ SI#x  ,  Wq    Qd    CQ    PFc             , "Bad use of s-v inversion2" ,
+ SFI##* , Wq    Qd    CQ    PFc             , "Bad use of s-v inversion3",
+ SXI   ,  Wq    Qd    CQ    PFc             , "Bad use of s-v inversion4" ,
+ Ws    ,  D##w    S##w    H                 , "S-V inversion required5",
+ I#a   ,  B#m    B#w                        , "incorrect use of 'to'6"       ,
+ Wq    ,  SI    SFI   SXI                   , "S-V inversion required7" ,
+ Qd    ,  SI    SFI   SXI                   , "S-V inversion required8" ,
+ PFc   ,  SI    SFI   SXI                   , "S-V inversion required9" ,
+ Mj    ,  Jw    JQ                          , "Incorrect relative10" ,
+ MX#j  ,  Jw    JQ                          , "Incorrect relative11" ,
+ Wj    ,  Jw    JQ                          , "Misuse of preposition12"     ,
+ JQ    ,  Mj    Wj    MX#j                  , "Misuse of preposition13"     ,
+ Jw    ,  Mj    Wj    MX#j                  , "Misuse of preposition14"     ,
+ B#j   ,  Jr                                , "Incorrect relative15"       ,
+ Jr    ,  B#j                               , "Incorrect relative16"       ,
+ EAh   ,  AF    Bsm    B*m    Qe    Ca    AFm              
+					    , "Incorrect use of 'how'17"    ,
+ EEh   ,  AF    Bsm    B*m    Qe    Ca    AFm               
+					    , "Incorrect use of 'how'18"    ,
+ Qe    ,  EEh           		    , "Incorrect use of adverb19"   ,
+ THi   ,  SFsi   SFIsi   OXi                , "Complement requires 'it'20"  ,
+ TSi   ,  SFsi   SFIsi   OXi                , "Complement requires 'it'21"   ,
+ QIi   ,  SFsi   SFIsi   OXi                , "Complement requires 'it'22"    ,
+ TOi   ,  SFsi   SFIsi   OXi                , "Complement requires 'it'23"     ,
+ Ci    ,  SFsi   SFIsi   OXi                , "Complement requires 'it'24"     ,
+ COqi  ,  SFsi   SFIsi   OXi                , "Complement requires 'it'25"     ,
+ CPi   ,  SFsi   SFIsi   OXi                , "Complement requires 'it'26"     ,
+ Eqi   ,  SFsi   SFIsi   OXi                , "Complement requires 'it'27"     ,
+ LEi   ,  SFsi   SFIsi   OXi                , "Complement requires 'it'28"     ,
+ MVti  ,  SFsi   SFIsi   OXi                , "Complement requires 'it'29"     ,
+ AFdi  ,  SFsi   SFIsi   OXi                , "Complement requires 'it'30"     ,
+ O#i   ,  SFsi   SFIsi   OXi                , "Complement requires 'it'31"     ,
+ SFst  ,  O*t    Ost    Omt    Bs#t    B*#t    Bc#t    , "Bad use of 'there'32"           ,
+ SFIst ,  O*t    Ost    Omt    Bs#t    B*#t    Bc#t    , "Bad use of 'there'33"           ,
+ SFp   ,  Opt    Omt    O*t    Bp#t    B*#t    Bc#t    , "Bad use of 'there'34"           ,
+;
+; This SFu rule forces subject-object agreement for uncountable noun objects
+ SFu   ,  Out    Omt    O*t    Bp#t    B*#t    Bc#t    , "Bad use of 'there'34a"           ,
+ SFIp  ,  Opt    Omt    O*t    Bp#t    B*#t    Bc#t    , "Bad use of 'there'35"           ,
+ OXt   ,  O#t    B##t                     ,   "Bad use of 'there'36"           ,
+ SFsi* ,  TOi    THi   QIi    TSi    O#i    Ci    THb   CPi   
+          COqi    CPi    Eqi    AFdi    BIh , "Bad use of 'it'37"           ,
+ SFIsi ,  TOi    THi   QIi    TSi    O#i    Ci    THb   CPi   
+          COqi    CPi    Eqi    AFdi    BIh , "Bad use of 'it'38"           ,
+ OXi   ,  TOi    THi   QIi    TSi    O#i    Ci    THb   CPi   
+          COqi    CPi    Eqi    AFdi    BIh , "Bad use of 'it'39"           ,
+ THb   ,  S##t    SI##t  SFsi  SFIsi        , "Bad use of predicate40"      ,
+ BIh   ,  Ss#b    SIs#b  SFsi  SFIsi        , "Bad use of predicate41"      ,
+ BIq   ,  S##q    SI##q  SFsi  Ss#b    SFIsi SIs#b 
+                                            , "Bad use of predicate42"      ,
+ MVt   ,  Dm#m   EAm   EEm   MVm  Pam   Pafm   AFm   EB#m   MVb AJrc
+          Om   Mam  Am  Jm  Ds*m   MX#m     , "Bad comparative43"    ,
+ MVz   ,  D##y    EAy    EEy    MVy    EB#y , "Bad comparative44"    ,
+ MV#a  ,  Pam    Pafm    EAm   Ds*m   EAy   AFm   Mam   Am  
+					    , "Bad comparative45"    ,
+ MV#i  ,  Pam    Pafm    EAm   Ds*m   EAy   AFm   Mam   Am  
+					    , "Bad comparative46"    ,
+ MV#o  ,  D##m    D##y    Om    Oy    Jm    Jy   Am   MX#m  
+					    , "Bad comparative47"    ,
+ MV#p  ,  EEm   MVb   Dm#m   EEy   D##y  MVm   Om   Oy 
+                            Jm   Jy   Am   MX#m         
+					    , "Bad comparative48"    ,
+ Pafc  ,  EB#m    EB#y                      , "Bad comparative49"    ,
+ Pafc  ,  Pa*    Paf*                       , "Bad comparative50"    ,
+ MVat  ,  MVm                               , "Bad comparative51"    ,
+ MVpt  ,  MVm                               , "Bad comparative52"    ,
+ MVat  ,  MVa   MVp                         , "Bad comparative53"    ,
+ MVpt  ,  MVa   MVp                         , "Bad comparative54"    ,
+ U#t   ,  D##m    D##y    Om    Oy    Jm    Jy   Am   MX#m           
+				            , "Bad comparative55"    ,
+ Cc    ,  EEm    EEy    MVm    MVb    MVy              
+	                                    , "Bad comparative56"    ,
+ Sp#c  ,  Dmcm    Dmcy    Om    Oy    Jm    Jy  MX#m         
+	 				    , "Bad comparative57"    ,
+ Ss#c  ,  Dmum    Dmuy    Om    Oy    Jm    Jy    Ds*y  MX#m        
+					    , "Bad comparative58"    ,
+ S##c  ,  Dm#m    D##y    Om    Oy    Jm    Jy   MX#m         
+					    , "Bad comparative59"    ,
+ THc   ,  TH                                , "Bad comparative60"    ,
+ TOc   ,  TO**   TOf*   TOi*                , "Bad comparative61"    ,
+ TOtc  ,  TOt  ,                              "Bad comparative62"    ,
+ Ma**  ,   TO   TOf   TH   MVp   TOt   QI   OF  MVt   MVz   MVh   Ytm   Ya             
+					    , "Bad use of adjective63"    ,
+ Mam   ,  TO   TOf   TH   MVp   TOt   QI   OF  MVt   MVz   MVh   Ytm   Ya              
+					    , "Bad use of adjective64"    ,
+ MX#a  ,  TO   TOf   TH   MVp   TOt   QI   OF  MVt   MVz   MVh   Ytm   Ya  MJ 
+			                    , "Bad use of adjective65"    ,
+
+; There's no ZZZ connector, which means that Ixd and Oxn
+; are prohibited from ever occuring. 4.0.batch covers this.
+ Ixd   ,  ZZZ                               , "Can't use 'do' with that verb" ,
+ Oxn   ,  ZZZ                               , "Bad use of pronoun66" ,
+ MVh   ,  EExk   EAxk   D##k                , "Incorrect use of that67" ,
+
+; The Rw link necessitated commenting out 68, because we had to make B#m 
+; a restricted link(see above) xxx reverted .. this is needed ...
+;
+B#m  ,   D##w   H   HA                     , "Bad use of gerund68"   
+
+CONTAINS_NONE_RULES:
+ S     ,  Spxi                  	    , "Bad n-v agreement69" ,
+ SI     , SIpxi                		    , "Bad n-v agreement70" ,
+ Ws    ,  B#m   Ca   BT      		    , "Question inversion violated71" ,
+ SF    ,  I*   PP*   TO*   Pa*   Pam  Pg*   Pv*   LE*   AFd*  MVta         
+					    , "Bad use of 'filler' subject72" ,
+ SFI   ,  I*   PP*   TO*   Pa*   Pam  Pg*   Pv*   LE*   AFd*  MVta        
+					    , "Bad use of 'filler' subject73" ,
+ OX    ,  I*   PP*   TO*   Pa*   Pam  Pg*   Pv*   LE*   AFd*  MVta        
+					    , "Bad use of 'filler' subject74" ,
+ MXsr  ,  Sp#w 				    , "Bad n-v agreement75" ,
+ MXpr  ,  Ss#w   S#iw			    , "Bad n-v agreement76" ,
+ Mr    ,  B#*				    , "Bad use of 'whose'77"
+
+
+; ----------------------------------------------------------------------
+; The following rule asserts that all specified domains must have the
+; property that all of the words that touch a link in the domain are
+; not to the left of the root word of the domain. These rules are
+; different from the above in that the first field is a *domain name*,
+; rather than a set of links.
+
+BOUNDED_RULES:
+ s                               , "Unbounded s domain78" ,
+ r                               , "Unbounded r domain79" 

data/data/en/4.0.regex

@@ -0,0 +1,225 @@
+ %***************************************************************************%
+ %                                                                           %
+ %  Copyright (C) 2005, 2006 Sampo Pyysalo, Sophie Aubin                     %
+ %  See file "LICENSE" for information about commercial use of this system   %
+ %                                                                           %
+ %***************************************************************************%
+
+% This file contains regular expressions that are used to match
+% tokens not found in the dictionary. Each regex is given a name which
+% determines the disjuncts assigned when the regex matches; this name
+% must be defined in the dictionary along with the appropriate disjuncts.
+% Note that the order of the regular expressions matters: matches will
+% be attempted in the order in which the regexs appear in this file,
+% and only the first match will be used.
+
+% Numbers.
+% XXX, we need to add utf8 U+00A0 "no-break space"
+% 
+% Allows at most two colons in hour-muinute-second HH:MM:SS expressions
+% Allows at most two digits between colons
+HMS-TIME: /^[0-9][0-9]?(:[0-9][0-9]?(:[0-9][0-9]?)?)?(AM|PM|am|pm)?$/
+
+% e.g. 1950's leading number can be higher, for science fiction.
+% Must be four digits, or possible three. Must end in s, 's ’s
+DECADE-TIME: /^([1-4][0-9][0-9]|[1-9][0-9])0(s|'s|’s)$/
+
+% Day-of-month names; this regex will match before the one below.
+DAY-ORDINALS: /^(1st|2nd|3rd|[4-9]th|1[0-9]th|2(0th|1st|2nd|3rd|[4-9]th)|30th|31st)$/
+
+% Ordinal numbers; everything except 1st through 13th
+% is handled by regex.
+ORDINALS: /^[1-9][0-9]*(0th|1st|2nd|3rd|[4-9]th)$/
+
+% Allows any number of commas or periods
+% Be careful not match the period at the end of a sentence; 
+% for example: "It happened in 1942."
+NUMBERS: /^[0-9,.]*[0-9]$/
+% This parses signed numbers and ranges, e.g. "-5" and "5-10" and "9+/-6.5"
+NUMBERS: /^[0-9.,-]*[0-9](\+\/-[0-9.,-]*[0-9])?$/
+% Parses simple fractions e.g. "1/60" with no decimal points or anything fancy
+FRACTION: /^[0-9]+\/[0-9]+$/
+% "10(3)" exponent (used in PubMed)
+NUMBERS: /^[0-9.,-]*[0-9][0-9.,-]*\([0-9:.,-]*[0-9][0-9.,-]*\)$/
+
+% Roman numerals
+% The first expr has the potential(?) problem that it matches an empty
+% string. Thus, the next three rules specify that at least one section
+% is non-empty.
+ROMAN-NUMERAL-WORDS: /^M*(CM|D?C{0,3}|CD)(XC|L?X{0,3}|XL)(IX|V?I{0,3}|IV)$/
+% ROMAN-NUMERAL-WORDS: /^M*(CM|D?C{0,3}|CD){1}(XC|L?X{0,3}|XL)(IX|V?I{0,3}|IV)$/
+% ROMAN-NUMERAL-WORDS: /^M*(CM|D?C{0,3}|CD)(XC|L?X{0,3}|XL){1}(IX|V?I{0,3}|IV)$/
+% ROMAN-NUMERAL-WORDS: /^M*(CM|D?C{0,3}|CD)(XC|L?X{0,3}|XL)(IX|V?I{0,3}|IV){1}$/
+
+% Strings of initials. e.g "Dr. J.G.D. Smith lives on Main St."
+INITIALS: /^([A-Z]\.)+$/
+
+% Greek letters with numbers
+GREEK-LETTER-AND-NUMBER: /^(alpha|beta|gamma|delta|epsilon|zeta|eta|theta|iota|kappa|lambda|mu|nu|xi|omicron|pi|rho|sigma|tau|upsilon|phi|chi|psi|omega)\-?[0-9]+$/
+PL-GREEK-LETTER-AND-NUMBER: /^(alpha|beta|gamma|delta|epsilon|zeta|eta|theta|iota|kappa|lambda|mu|nu|xi|omicron|pi|rho|sigma|tau|upsilon|phi|chi|psi|omega)s\-?[0-9]+$/
+
+% Some "safe" derived units. Simple units are in dictionary.
+% The idea here is for the regex to match something that is almost
+% certainly part of a derived unit, and allow the rest to be
+% anything; this way we can capture difficult derived units such
+% as "mg/kg/day" and even oddities such as "micrograms/mouse/day"
+% without listing them explicitly.
+% TODO: add more. 
+% Some (real) misses from these: 
+% micrograms.kg-1.h-1 microM-1 J/cm2 %/day mN/m cm/yr
+% m/s days/week ml/s degrees/sec cm/sec cm/s mm/s N/mm (is that a unit?)
+% cuts/minute clicks/s beats/minute x/week W/kg/W %/patient-year
+% microIU/ml degrees/s counts/mm2 cells/mm3 tumors/mouse
+% mm/sec ml/hr mJ/cm(2) m2/g amol/mm2 animals/group
+% h-1 min-1 day-1 cm-1 mg-1 kg-1 mg.m-2.min-1 ms.cm-1 g-1
+% sec-1 ms-1 ml.min.-1kg-1 ml.hr-1
+% also, both kilometer and kilometers seem to be absent(!)
+% remember "mm"!
+
+UNITS: /^([npmk]|nano|pico|milli|micro|kilo)?(g|grams?)\//   % grams/anything
+UNITS: /^([fnmp]|femto|nano|micro|pico|mu)?mol(es)?\//       % mol/anything
+UNITS: /^[a-zA-Z\/.]+\/((m|micro)?[lLg]|kg|mol|min|day|h)$/  % common endings
+% common endings, except in the style "mg.kg-1" instead of "mg/kg".
+UNITS: /^[a-zA-Z\/.1-]+\.((m|micro)?[lLg]|kg|mol|min|day|h)(-1|\(-1\))$/
+
+% combinations of numbers and units, e.g. "50-kDa", "1-2h"
+% TODO: Clean up and check that these are up-to-date wrt the 
+% dictionary-recognized units; this is quite a mess currently.
+% TODO: Extend the "number" part of the regex to allow anything
+% that the NUMBER regex matches.
+% One problem here is a failure to split up the expression ... 
+% e.g. "2hr" becomes 2 - ND - hr with the ND link. But 2-hr is treated
+% as a single word ('I is a 2-hr wait')
+% NUMBER-AND-UNIT: /^[0-9.,-]+(msec|s|min|hour|h|hr|day|week|wk|month|year|yr|kDa|kilodalton|base|kilobase|base-pair|kD|kd|kDa|bp|nt|kb|mm|mg|cm|nm|g|Hz|ms|kg|ml|mL|km|microm|\%)$/
+% Comment out above, it screws up handling of unit suffixes, for
+% example: "Zangbert stock fell 30% to $2.50 yesterday."
+
+
+% fold-words. Matches NUMBER-fold, where NUMBER can be either numeric
+% or a spelled-out number, and the hyphen is optional. Note that for
+% spelled-out numbers, anything is allowed between the "initial" number
+% and "fold" to catch e.g. "two-to-three fold" ("fourteen" etc. are absent
+% as the prefix "four" is sufficient to match).
+FOLD-WORDS: /^[0-9.,:-]*[0-9]([0-9.,:-]|\([0-9.,:-]*[0-9][0-9.,:-]*\)|\+\/-)*-?fold$/
+FOLD-WORDS: /^(one|two|three|four|five|six|seven|eight|nine|ten|eleven|twelve|thirteen|fifteen|twenty|thirty|fifty|hundred|thousand|million).*fold$/
+
+% Plural proper nouns.
+% Make sure that apostrophe-s is split out correctly.
+PL-CAPITALIZED-WORDS:  /^[[:upper:]].*[^iuoys'’]s$/
+
+% Other proper nouns.
+% We demand that these end with an alphanumeric, i.e. explicitly
+% reject punctuation. We don't want this regex to "swallow" any trailing
+% commas, colons, or periods/question-marks at the end of sentences.
+% In addition, this must not swallow words ending in 's 'll etc.
+% (... any affix, for that matter ...) and so no embedded apostrophe
+CAPITALIZED-WORDS:     /^[[:upper:]][^'’]*[^[:punct:]]$/
+
+% SUFFIX GUESSING
+% For all suffix-guessing patterns, we insist that the pattern start
+% with an alphanumeric. This is needed to guarentee that the
+% prefix-stripping code works correctly, as otherwise, the regex will
+% gobble the prefix. So for example: "We left (carrying the dog) and
+% Fred followed."  Since "(carrying" is not in the dict, we need to be
+% sure to not match the leading paren so that it will get tripped.
+%
+ING-WORDS:        /^\w.+ing$/
+
+% Plurals or verb-s. Make sure that apostrophe-s is split out correctly.
+% e.g. "The subject's name is John Doe."  should be
+%     +--Ds--+---YS--+--Ds-+
+%     |      |       |     |
+%    the subject.n 's.p name.n 
+S-WORDS:          /^\w.+[^iuoys'’]s$/
+
+% Verbs ending -ed.
+ED-WORDS:         /^\w.+ed$/
+
+% Advebs ending -ly.
+LY-WORDS:         /^\w.+ly$/
+
+% Nouns ending in -ism, -asm (chiliasm .. ) Usualy mass nouns
+% Stubbed out for now; I'm not convinced this improves accuracy.
+% ISM-WORDS:        /^\w.+asm$/
+% ISM-WORDS:        /^\w.+ism$/
+
+% Corresponding count noun version of above (chiliast...)
+% AST-WORDS:        /^\w.+ast$/
+% AST-WORDS:        /^\w.+ist$/
+
+% Corresponding adjectival form of above
+ADJ-WORDS: /^\w.+astic$/
+ADJ-WORDS: /^\w.+istic$/
+
+% Nouns ending -ation  stubbed out in BioLG, stub out here ... 
+%ATION-WORDS:      /^\w.+ation$/
+
+% Extension by LIPN 11/10/2005
+% nouns -- typically seen in (bio-)chemistry texts
+% synthetase, kinase
+% 5-(hydroxymethyl)-2’-deoxyuridine
+% hydroxyethyl, hydroxymethyl
+% septation, reguion
+% isomaltotetraose, isomaltotriose
+% glycosylphosphatidylinositol
+% iodide, oligodeoxynucleotide
+% chronicity, hypochromicity
+MC-NOUN-WORDS: /^\w.+ase$/
+MC-NOUN-WORDS: /^\w.+ine?$/
+MC-NOUN-WORDS: /^\w.+yl$/
+MC-NOUN-WORDS: /^\w.+ion$/
+MC-NOUN-WORDS: /^\w.+ose$/
+MC-NOUN-WORDS: /^\w.+ol$/
+MC-NOUN-WORDS: /^\w.+ide$/
+MC-NOUN-WORDS: /^\w.+ity$/
+
+% replicon, intron
+C-NOUN-WORDS: /^\w.+o[rn]$/
+
+% adjectives
+% exogenous, heterologous
+% intermolecular, intramolecular
+% glycolytic, ribonucleic, uronic
+% ribosomal, ribsosomal
+% nonpermissive, thermosensitive
+% inducible, metastable
+ADJ-WORDS: /^\w.+ous$/
+ADJ-WORDS: /^\w.+ar$/
+ADJ-WORDS: /^\w.+ic$/
+ADJ-WORDS: /^\w.+al$/
+ADJ-WORDS: /^\w.+ive$/
+ADJ-WORDS: /^\w.+ble$/
+
+% latin (postposed) adjectives
+% influenzae, tarentolae
+% pentosaceus, luteus, carnosus
+LATIN-ADJ-WORDS: /^\w.+ae$/
+LATIN-ADJ-WORDS: /^\w.+us$/ % must appear after -ous in this file
+
+% latin (postposed) adjectives  or latin plural noun
+% brevis, israelensis
+% japonicum, tabacum, xylinum
+LATIN-ADJ-P-NOUN-WORDS: /^\w.+is?$/
+LATIN-ADJ-S-NOUN-WORDS: /^\w.+um$/
+
+
+% Hyphenated words. In the original LG morpho-guessing system that
+% predated the regex-based system, hyphenated words were detected
+% before ING-WORDS, S-WORDS etc., causing e.g. "cross-linked" to be
+% treated as a HYPHENATED-WORD (a generic adjective/noun), and
+% never a verb. To return to this ordering, move this regex just
+% after the CAPITALIZED-WORDS regex.
+HYPHENATED-WORDS: /^[[:alpha:][:digit:],.][[:alpha:][:digit:],.-]*-[[:alpha:][:digit:],.-]*[[:alpha:][:digit:],.]$/
+
+% proteins often end "ase", so we'll assume those things are names.
+% removed, too many false positives.
+% NAME: /ase$/
+
+% Sequence of punctuation marks. If some mark appears in the affix table
+% such as a period, comma, dash or underscore, and there's a sequence of
+% these, then treat it as a "fill-in-the-blank" placeholder.
+% This matters only for punc. appearing in the affix table, since the
+% tokenizer explicitly mangles based on these punctution marks.
+% 
+% Look for at least four in a row.
+UNKNOWN-WORD: /^[.,-]{4}[.,-]*$/