Index: app/doc/utt.texinfo =================================================================== --- app/doc/utt.texinfo (revision e28a62525995e07b8d354225ae96189c5c02a06d) +++ app/doc/utt.texinfo (revision 9ace5d204d63628901f9f128d3f99ce5f7c973c0) @@ -1,4 +1,6 @@ + \input texinfo @c -*-texinfo-*- -@documentencoding ISO-8859-2 +@c @documentencoding ISO-8859-2 +@documentencoding UTF-8 @c @documentlanguage pl @@ -11,5 +13,5 @@ This manual is for UAM Text Tools (version 0.90, October, 2008) -Copyright @copyright{} 2005, 2007 Tomasz Obrêbski, Micha³ Stolarski, Justyna Walkowska, Pawe³ Konieczka. +Copyright @copyright{} 2005, 2007 Tomasz Obrębski, Michał Stolarski, Justyna Walkowska, Paweł Konieczka. Permission is granted to copy, distribute and/or modify this document @@ -31,5 +33,5 @@ @subtitle edition 0.01, @today @subtitle status: prescript -@author by Justyna Walkowska, Tomasz Obr@,{}ebski and Micha@l{} Stolarski +@author by Justyna Walkowska, Tomasz Obrębski and Michał Stolarski @page @vskip 0pt plus 1filll @@ -42,7 +44,12 @@ @iftex +@tex +% \usepackage[T1]{fontenc} +% \usepackage[utf8]{inputenc} +% \usepackage{times} +@end tex + @parskip = 0.5@normalbaselineskip plus 3pt minus 1pt @end iftex - @c @headings off @c @everyheading LEM(1) @| @| LEM(1) @@ -84,5 +91,6 @@ @item -tokenization +tokenization Ã³Å‚Ä +ÅŒ @item dictionary-based morphological analysis @@ -90,5 +98,6 @@ heuristic morphological analysis of unknown words @item -spelling correction +spelling correction Ã³Å‚Ä +śćŌ @item pattern search @@ -125,9 +134,9 @@ @itemize @item Pawel Konieczka -@item Tomasz Obrebski -@item Michal Stolarski +@item Tomasz Obrębski +@item Michał Stolarski @item Marcin Walas @item Justyna Walkowska -@item Pawel Werenski +@item Paweł Wereński @end itemize @@ -251,5 +260,5 @@ @example 0000 00 BOS * -0000 07 W Piszemy lem:pisaÊ,V +0000 07 W Piszemy lem:pisać,V 0007 01 S _ 0008 05 W dobre lem:dobry,ADJ @@ -262,5 +271,5 @@ 0024 11 W Warszawiacy lem:Warszawiak,N 0035 01 S _ -0036 03 W te¿ +0036 03 W teÅŒ 0039 01 P . 0040 00 EOS * @@ -270,5 +279,5 @@ @example 0000 BOS * -0000 W Piszemy lem:pisaÊ,V +0000 W Piszemy lem:pisać,V 0007 S _ 0008 W dobre lem:dobry,ADJ @@ -283,5 +292,5 @@ @example 0000 BOS * -W Piszemy lem:pisaÊ,V +W Piszemy lem:pisać‡,V S _ W dobre lem:dobry,ADJ @@ -294,5 +303,5 @@ W Warszawiacy lem:Warszawiak,N S _ -W te¿ +W teÅŒ P . EOS * @@ -429,5 +438,5 @@ -@c [JAK UZYSKAÆ POLSKIE CZCIONKI W DVI???] +@c [JAK UZYSKAÆ POLSKIE CZCIONKI W DVI???] @macro parhelp @@ -651,5 +660,5 @@ @multitable {aaaaaaaaaaaaaaaaaaaaaaaaa} {aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa} -@item @strong{Authors:} @tab Tomasz Obrêbski +@item @strong{Authors:} @tab Tomasz Obrębski @item @strong{Component category:} @tab source @item @strong{Input format:} @tab raw text file @@ -756,5 +765,5 @@ @c @chapter sen - sentencizer -@c Authors: Tomasz Obrêbski +@c Authors: Tomasz Obrębski @c --------------------------------------------------------------------- @@ -767,5 +776,5 @@ @multitable {aaaaaaaaaaaaaaaaaaaaaaaaa} {aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa} -@item @strong{Authors:} @tab Tomasz Obrêbski, Micha³ Stolarski +@item @strong{Authors:} @tab Tomasz Obrębski, Michał Stolarski @item @strong{Component category:} @tab filter @item @strong{Input format:} @tab UTT regular @@ -871,5 +880,5 @@ @example -0000 07 W Piszemy lem:pisaÊ,V/AiVpMdTrfNpP1 +0000 07 W Piszemy lem:pisać,V/AiVpMdTrfNpP1 0007 01 B _ 0008 05 W dobre lem:dobry,ADJ/DpNpCnavGaifn @@ -886,5 +895,5 @@ @example -0000 07 W Piszemy lem:pisaÊ,V/AiVpMdTrfNpP1 +0000 07 W Piszemy lem:pisać,V/AiVpMdTrfNpP1 0007 01 S _ 0008 05 W dobre lem:dobry,ADJ/DpNpCnavGaifn lem:dobry,ADJ/DpNsCnavGn @@ -898,5 +907,5 @@ @example -0000 07 W Piszemy lem:pisaÊ,V/AiVpMdTrfNpP1 +0000 07 W Piszemy lem:pisać,V/AiVpMdTrfNpP1 0007 01 S _ 0008 05 W dobre lem:dobry,ADJ/DpNpCnavGaifn,ADJ/DpNsCnavGn @@ -932,5 +941,5 @@ string @code{}, replace suffix of length @code{} with string @code{}. For example @code{3t} transforms @samp{kocie} into -@samp{kot}, @code{3-4a³y} transforms @samp{najbielsi} into @samp{bia³y} +@samp{kot}, @code{3-4aÂły} transforms @samp{najbielsi} into @samp{biaÂły} Each dictionary entry must be written in one line and must not contain blank characters. @@ -943,6 +952,6 @@ kotem;2,N/GaNsCi kocie;3t,N/GaNsCl;3t,N/GaNsCv -najbielsi;3-4a³y,ADJ/DsNpCnGp -najbielsze;3-5a³y,ADJ/DsNpCnGaifn +najbielsi;3-4ały,ADJ/DsNpCnGp +najbielsze;3-5ały,ADJ/DsNpCnGaifn najlepsi;dobry,ADJ/DsNpCnGp najlepsze;dobry,ADJ/DsNpCnGaifn @@ -1009,5 +1018,5 @@ @multitable {aaaaaaaaaaaaaaaaaaaaaaaaa} {aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa} -@item @strong{Authors:} @tab Micha³ Stolarski, Tomasz Obrêbski +@item @strong{Authors:} @tab Michał Stolarski, Tomasz Obrębski @item @strong{Component category:} @tab filter @@ -1106,5 +1115,5 @@ -Example: @code{3-4a³y} transforms @i{najbielsi} into @i{bia³y} +Example: @code{3-4ały} transforms @i{najbielsi} into @i{biały} @@ -1114,8 +1123,8 @@ likelihood of the guess. -@example -*³kê;1a,N/GfNsCa -naj*elszy;3-4a³y,ADJ/...:... -@end example +@c @example +@c *łkę;1a,N/GfNsCa +@c naj*elszy;3-4ały,ADJ/...:... +@c @end example @@ -1129,5 +1138,5 @@ @multitable {aaaaaaaaaaaaaaaaaaaaaaaaa} {aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa} -@item @strong{Authors:} @tab Tomasz Obrêbski, Micha³ Stolarski +@item @strong{Authors:} @tab Tomasz Obrębski, Michał Stolarski @item @strong{Component category:} @tab filter @item @strong{Input format:} @tab UTT regular @@ -1216,5 +1225,114 @@ @section kor - configurable spelling corrector -[TODO] +@multitable {aaaaaaaaaaaaaaaaaaaaaaaaa} {aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa} +@item @strong{Authors:} @tab Paweł Werenski, Tomasz Obrębski, Michał Stolarski +@item @strong{Component category:} @tab filter +@item @strong{Input format:} @tab UTT regular +@item @strong{Output format:} @tab UTT regular +@item @strong{Required annotation:} @tab tok +@end multitable + +@menu +* kor description:: +* kor command line options:: +* kor weights definition file:: +* kor dictionaries:: +@end menu + + +@node kor description +@subsection Description + +The spelling corrector applies a Pawel Werenski's dynamic programming +algorithm to the FSA representation of the set of word forms of the +Polex/PMDBF dictionary. The algorithm is an extension of K. Oflazer +algorithm used by @command{cor}. In the extended version it is +possible to assign weights to individual edit operations. + +Given an incorrect word form it returns all word forms +present in the dictionary whose edit distance is smaller than the +threshold given as the parameter. + + +@node kor command line options +@subsection Command line options + +@table @code + +@parhelp +@parversion +@parinteractive +@c @parfile +@c @paroutput +@c @parfail +@c @parcopy +@parinputfield +@paroutputfield +@pardictionary +@parprocess +@parselect +@parunselect +@paroneline +@paronefield + +@item @b{@minus{}@minus{}distance=@var{int}, @minus{}n @var{int}} +Maximum edit distance (default='1'). + +@item @b{@minus{}@minus{}weights=@var{filename}, @minus{}w @var{filename}} +Edit operations' weights file. + +@c @item @b{@minus{}@minus{}replace, @minus{}r} +@c Replace original form with corrected form, place original form in the +@c cor field. This option has no effect in @option{--one-*} modes (default=off) + + +@end table + + +@node kor weights definition file +@subsection Weights definition file + +Example: + +@example + +%stdcor 1 +%xchg 1 +ÅŒ rz 0.5 +ch h 0.5 +u ó 0.5 + +@end example + + +Default weight is set to 1 (@code{%stdcor 1}), the weight of exchange +operation is set to 1 (@code{%xchg 1}), the three principal orthographic +errors are assigned the weight 0.5. + +The edit operation weight declaration, such as + +@example +ÅŒ rz 0.5 +@end example + +works in both ways, i.e. ÅŒ->rz, rz->ÅŒ. + +The default weights definition file for @code{kor} is: + +@example +$HOME/.local/share/utt/weights.kor +@end example + +or, if the above mentioned file is absent: + +@example +/usr/local/share/utt/weights.kor +@end example + + +@node kor dictionaries +@subsection Dictionaries + +see @command{cor} @c --------------------------------------------------------------------- @@ -1228,5 +1346,5 @@ @multitable {aaaaaaaaaaaaaaaaaaaaaaaaa} {aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa} -@item @strong{Authors:} @tab Tomasz Obrêbski +@item @strong{Authors:} @tab Tomasz Obrębski @item @strong{Component category:} @tab filter @item @strong{Input format:} @tab UTT regular @@ -1256,5 +1374,5 @@ input: -0000 05 W Cze¶Ê +0000 05 W Cześć 0005 01 P ! 0006 01 S _ @@ -1267,5 +1385,5 @@ output: 0000 00 BOS * -0000 05 W Cze¶Ê +0000 05 W Cześć 0005 01 P ! 0006 00 EOS * @@ -1288,5 +1406,5 @@ @c @chapter gph - graphizer -@c Authors: Tomasz Obrêbski +@c Authors: Tomasz Obrębski @@ -1301,5 +1419,5 @@ @multitable {aaaaaaaaaaaaaaaaaaaaaaaaa} {aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa} -@item @strong{Authors:} @tab Tomasz Obrêbski +@item @strong{Authors:} @tab Tomasz Obrębski @item @strong{Component category:} @tab filter @item @strong{Input format:} @tab UTT regular @@ -1537,5 +1655,5 @@ @multitable {aaaaaaaaaaaaaaaaaaaaaaaaa} {aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa} -@item @strong{Authors:} @tab Tomasz Obrêbski +@item @strong{Authors:} @tab Tomasz Obrębski @item @strong{Component category:} @tab filter @item @strong{Input format:} @tab UTT flattened @@ -1626,5 +1744,5 @@ @multitable {aaaaaaaaaaaaaaaaaaaaaaaaa} {aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa} -@item @strong{Authors:} @tab Marcin Walas, Tomasz Obrêbski +@item @strong{Authors:} @tab Marcin Walas, Tomasz Obrębski @item @strong{Input format:} @tab UTT flattened @item @strong{Output format:} @tab UTT flattened @@ -1646,5 +1764,5 @@ @multitable {aaaaaaaaaaaaaaaaaaaaaaaaa} {aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa} -@item @strong{Authors:} @tab Tomasz Obrêbski +@item @strong{Authors:} @tab Tomasz Obrębski @item @strong{Component category:} @tab filter @item @strong{Input format:} @tab UTT regular @@ -1839,5 +1957,5 @@ @multitable {aaaaaaaaaaaaaaaaaaaaaaaaa} {aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa} -@item @strong{Authors:} @tab Michal Stolarski, Tomasz Obrebski +@item @strong{Authors:} @tab Michał Stolarski, Tomasz Obrębski @item @strong{Component category:} @tab additional tool @end multitable @@ -1884,5 +2002,5 @@ @multitable {aaaaaaaaaaaaaaaaaaaaaaaaa} {aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa} -@item @strong{Authors:} @tab Tomasz Obrêbski +@item @strong{Authors:} @tab Tomasz Obrębski @item @strong{Input format:} @tab UTT regular @item @strong{Output format:} @tab UTT flattened @@ -1932,5 +2050,5 @@ @multitable {aaaaaaaaaaaaaaaaaaaaaaaaa} {aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa} -@item @strong{Authors:} @tab Tomasz Obrêbski +@item @strong{Authors:} @tab Tomasz Obrębski @item @strong{Input format:} @tab UTT flattened @item @strong{Output format:} @tab UTT regular @@ -2236,5 +2354,4 @@ @tab @code{v} @tab vocative. @item -@item @code{G} @tab @tab Gender @item @@ -2729,5 +2846,5 @@ @c @chapter Copyright @c -@c Copyright 2004 by Tomasz Obrebski +@c Copyright 2004 by Tomasz Obrębski @c This software is free for research and educational use.