Geodesic
A partial parser with heuristics reducing the number of false chunks in the russian clause
Učënye zapiski Kazanskogo universiteta. Seriâ Fiziko-matematičeskie nauki, Kazanskii Gosudarstvennyi Universitet. Uchenye Zapiski. Seriya Fiziko-Matematichaskie Nauki, Tome 151 (2009) no. 3, pp. 214-228

Voir la notice du chapitre de livre provenant de la source Math-Net.Ru

The problem of partial parsing is considered in this paper. New heuristics are proposed to reduce the quantity of chunks falsely exposed at the first step of analysis. A very large influence is rendered by the phenomena of homonymy and polysemy on detection of chunks in russian. Falsely exposed chunks are treated as ones which were found out by a partial parser, but are not actually correct. The method of search of chunks with the use of these heuristics got the name “Right-chunk 4”. The formal task statement is carried out. Computer realization of method of search of chunks is executed as software “Chunk-creator 4”. The estimation of quality is conducted.
Keywords: artificial intelligence, computational linguistics, parsing, chunking. 
V. A. Bushtedt; V. N. Polyakov. A partial parser with heuristics reducing the number of false chunks in the russian clause. Učënye zapiski Kazanskogo universiteta. Seriâ Fiziko-matematičeskie nauki, Kazanskii Gosudarstvennyi Universitet. Uchenye Zapiski. Seriya Fiziko-Matematichaskie Nauki, Tome 151 (2009) no. 3, pp. 214-228. http://geodesic.mathdoc.fr/item/UZKU_2009_151_3_a18/
@article{UZKU_2009_151_3_a18,
     author = {V. A. Bushtedt and V. N. Polyakov},
     title = {A partial parser with heuristics reducing the number of false chunks in the russian clause},
     journal = {U\v{c}\"enye zapiski Kazanskogo universiteta. Seri\^a Fiziko-matemati\v{c}eskie nauki},
     pages = {214--228},
     year = {2009},
     volume = {151},
     number = {3},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/UZKU_2009_151_3_a18/}
}
TY  - JOUR
AU  - V. A. Bushtedt
AU  - V. N. Polyakov
TI  - A partial parser with heuristics reducing the number of false chunks in the russian clause
JO  - Učënye zapiski Kazanskogo universiteta. Seriâ Fiziko-matematičeskie nauki
PY  - 2009
SP  - 214
EP  - 228
VL  - 151
IS  - 3
UR  - http://geodesic.mathdoc.fr/item/UZKU_2009_151_3_a18/
LA  - ru
ID  - UZKU_2009_151_3_a18
ER  - 
%0 Journal Article
%A V. A. Bushtedt
%A V. N. Polyakov
%T A partial parser with heuristics reducing the number of false chunks in the russian clause
%J Učënye zapiski Kazanskogo universiteta. Seriâ Fiziko-matematičeskie nauki
%D 2009
%P 214-228
%V 151
%N 3
%U http://geodesic.mathdoc.fr/item/UZKU_2009_151_3_a18/
%G ru
%F UZKU_2009_151_3_a18

[1] Popov E. V., Obschenie s EVM na estestvennom yazyke, Editorial URSS, M., 2004, 360 pp.

[2] Smirnov Yu. M., Andreev A. M., Berezkin D. V., Brik A. V., “Ob odnom sposobe postroeniya sintaksicheskogo analizatora tekstov na estestvennom yazyke”, Izv. vuzov. Priborostroenie, 40:5 (1997), 34–42

[3] Ermakov A. E., “Nepolnyi sintaksicheskii analiz teksta v informatsionno-poiskovykh sistemakh”, Kompyuternaya lingvistika i intellektualnye tekhnologii, Trudy Mezhdunar. seminara Dialog'2002, v 2 t., v. 2, Nauka, M., 2002, 180–185

[4] Ermakov A. E., “Tematicheskii analiz teksta s vyyavleniem sverkhfrazovoi struktury”, Inform. tekhnol., 2000, no. 11, 37–40

[5] Ermakov A. E., Pleshko V. V., “Assotsiativnaya model porozhdeniya teksta v zadache klassifikatsii”, Inform. tekhnol., 2000, no. 12, 34–37

[6] Andreev A. M., Berezkin D. V., Brik A. V., Kantonistov Yu. A., “Veroyatnostnyi sintaksicheskii analizator dlya informatsionno-poiskovoi sistemy”, Kompyuternaya khronika, 1999, no. 1, 3–4

[7] Bushtedt V. A., Polyakov V. N., “Chastichnyi sintaksicheskii analizator dlya korporativnoi poiskovoi sistemy”, Trudy Kazan. shkoly po kompyuternoi i kognitivnoi lingvistike, TEL-2006, Otechestvo, Kazan, 2007, 4–15

[8] Bushtedt V., Polyakov V., “Finding chunks with restricrion of distance to dependent word”, Kognitivnoe modelirovanie v lingvistike, Trudy IX mezhdunar. konf., Sofia, Bulgaria, 2007, 38–47

[9] Kuzmin Yu. G., Polyakov V. N., Shmagina E. V., “Metod leksiko-sintaksicheskikh portretov i zadacha razresheniya leksicheskoi mnogoznachnosti”, Trudy Kazan. shkoly po kompyuternoi i kognitivnoi lingvistike, TEL-2006, Otechestvo, Kazan, 2007, 139–147

[10] Hall K., Novak V., “Corrective modeling for non-projective dependency parsing”, Proceedings of the 9th International Workshop on Parsing Technologies, IWPT, 2005, 42–52 | DOI

[11] D. E. Rozental (red.), Sovremennyi russkii yazyk: Leksika i frazeologiya. Fonetika i orfoepiya. Grafika i orfografiya. Slovoobrazovanie. Morfologiya. Sintaksis, Uchebnik dlya vuzov, Vyssh. shk., M., 1984, 735 pp.