Dokumentation och publikationer från Språkteknologigruppen
Här har vi samlat publikationer som
handlar om verktyg utvecklade av
Språkteknologigruppen på KTH CSC.
Själva verktygen kan laddas ned
från Språkteknologigruppens verktygssida. Många
verktyg kan också användas online
via Granska
API.
Snabblänkar till referensmaterial
Granskafamiljen
Dokumentation
- Hemsidan för projektet där Granska skapades
- Populärvetenskaplig beskrivning av Granska
- Användarhandledning för Granska,
Ola Knutsson, kursmaterial i kursen "Språkteknologi", 1997.
- Granskas regelspråk, Ola Knutsson
- "Specifikation
av grammatiska feltyper i Granska",
Domeij & Knutsson, internt arbetspapper, Nada, september 1999.
- SUCs
(Stockholm-Umeå Corpus) taggset (vilket är nästan
samma som Granskas taggset).
- Granskas taggset, en lista på alla taggar som finns.
- "Granskaprojektet:
Rapport från arbetet med granskningsregler och
kommentarer"
Domeij & Knutsson, intern rapport, augusti 1998
- Hur man anropar Granska i Granska API
- Hur man anropar Granska via sockets
- Hur man anropar Granska taggare i Granska API
- Hur man anropar Granskas taggare via sockets
- Hur man anropar GTA i Granska API
- Hur man anropar GTA via sockets
- Hur man anropar Probgranska i Granska API
Forskningsartiklar
Granska
Domeij, Knutsson, Carberger, &
Kann, 2000, "Granska - an efficient hybrid
system for Swedish grammar
checking"
@inproceedings{granska,
author = {Richard Domeij and Ola Knutsson and
Johan Carlberger and Viggo Kann}, title = {Granska
-- an efficient hybrid system for {Swedish}
grammar checking}, booktitle = "Proceedings
of Nodalida '99", pages = {49--56}, address =
"Trondheim, Norway", year =
"2000"}
Carlberger, Domeij., Kann, & Knutsson,
2004, "The development and performance of a
grammar checker for Swedish : A language engineering
perspective"
Carlberger, J., Domeij, R., Kann, V., & Knutsson,
O. (2004). The development and performance of a
grammar checker for Swedish : A language engineering
perspective. Natural Language Engineering, 1(1)
The
development and performance of a grammar checker for
Swedish : A language engineering perspective
(PDF)
Domeij, Knutsson, Carlberger & Kann,
1999, "Granska - ett effektivt hybridsystem för
kontroll av svensk grammatik"
Granska - ett effektivt hybridsystem för kontroll av
svensk grammatik R. Domeij, O. Knutsson,
J. Carlberger, V. Kann NoDaLiDa, 49-56, december
1999.
Granska
- ett effektivt hybridsystem för kontroll av svensk
grammatik (Word-fil på svenska)
Granska
- ett effektivt hybridsystem för kontroll av svensk
grammatik (Word-fil på engelska)
Forskningsartikel som utvärderar och jämför Granska med andra grammatikgranskare:
Bigert, Kann, Knutsson, & Sjöbergh, "Grammar checking for Swedish second language learners", 2004
@incollection{call2004,
author = {Johnny Bigert and Viggo Kann and Ola Knutsson and Jonas Sj\"{o}bergh},
title = {Grammar Checking for {Swedish} Second Language Learners},
booktitle = {{CALL} for the {Nordic} Languages},
pages = "33--47",
publisher = "Samfundslitteratur",
editor = "Peter Juel Henrichsen",
year = "2004"
}
Granskas taggare
Carlberger & Kann, 1999,
"Implementing an efficient part-of-speech
tagger"
@article{carlberger99implementing,
author = "Johan Carlberger and Viggo
Kann", title = "Implementing an
efficient part-of-speech tagger",
journal = "Software -- Practice and
Experience", volume = "29", number =
"9", pages = "815--832", year =
"1999"}
Implementing an efficient
part-of-speech tagger (PDF)
Carlberger & Kann, 2000, "Some applications of a statistical tagger for Swedish"
Some applications of a statistical tagger for Swedish
J. Carlberger, V. Kann
Proc. 4:th conference of the International Quantitative Linguistics Association (Qualico-2000), 51-52, augusti 2000.
Some
applications of a statistical tagger for Swedish
(PDF)
GTA, granskas parser
Knutsson, Bigert & Kann, 2003, "A
Robust Shallow Parser for Swedish"
@inproceedings{gta, author = {Ola Knutsson and
Johnny Bigert and Viggo Kann}, title = {A Robust
Shallow Parser for {Swedish}}, booktitle =
"Proceedings of Nodalida 2003", address =
"Reykjavik, Iceland", year =
"2003"}
A Robust Shallow Parser for
Swedish (PDF)
Probgranska
Bigert & Knutsson, 2002, "Robust error
detection: A hybrid approach combining unsupervised
error detection and linguistic knowledge"
@inproceedings{probgranska,
author = "Johnny Bigert and Ola Knutsson",
title = "Robust Error Detection: A Hybrid Approach Combining Unsupervised Error Detection and Linguistic Knowledge",
booktitle = "Proceedings of Romand 2002, Robust Methods in Analysis of Natural Language Data",
address = "Frascati, Italy",
pages = "10--19",
year = "2002"}
Robust error
detection: A hybrid approach combining unsupervised error
detection and linguistic knowledge (PDF)
Stavafamiljen
Dokumentation
Forskningsartiklar
Stava
Domeij, Hollman &
Kann, 1994, "Detection of spelling
errors in Swedish not using a word
list en
clair"
@article{stava,
title={Detection of spelling errors
in {Swedish} not using a word list
en clair}, author={Rickard Domeij
and Joachim Hollman and Viggo Kann},
journal={Journal of Quantitative
Linguistics}, volume="1",
pages="195--201", year=1994 }
Tillenius, 1996, "Efficient generation and ranking of spelling error corrections"
Efficient generation and ranking of spelling error corrections
M. Tillenius
NADA report TRITA-NA-E9621, 1996.
Efficient generation and ranking of spelling error corrections (PDF)
Kann, Domeij, Hollman & Tillenius,
1998, "Implementation aspects and applications
of a spelling correction algorithm"
Implementation aspects and applications of a spelling correction algorithm.
V. Kann, R. Domeij, J. Hollman, M. Tillenius
L. Uhlirova, G. Wimmer, G. Altmann, R. Koehler: Text as a Linguistic Paradigm: Levels, Constituents, Constructs. Festschrift in honour of Ludek Hrebicek, Quantitative Linguistics, vol. 60, WVT, 2001.
NADA report TRITA-NA-9813, 1998.
Implementation
aspects and applications of a spelling correction
algorithm (PDF)
Taggstava
Kann, 2010,
"KTHs morfologiska och
lexikografiska verktyg och resurser
(Morphological and Lexicographical
Tools and Resources from
KTH)"
@misc{taggstava2,
author = {Viggo Kann}, title =
{{KTHs} morfologiska och
lexikografiska verktyg och resurser
({M}orphological and Lexicographical
Tools and Resources from {KTH})},
booktitle = "LexicoNordica 17",
pages="99--117", address =
{Sch{\"a}fferg{\aa}rden, Denmark},
year = "2010"}
Särstava
Sjöbergh & Kann,
2004, "Finding the Correct
Interpretation of Swedish Compounds a
Statistical
Approach"
@inproceedings{compounds2004,
author = {Jonas Sj\"{o}bergh and
Viggo Kann}, title = {Finding the
Correct Interpretation of {Swedish}
Compounds a Statistical Approach},
booktitle = "Proceedings of
{LREC}-2004", address = "Lisbon,
Portugal", pages = {899--902}, year =
"2004" }
Sjöbergh & Kann, 2006,
"Vad kan statistik avslöja om svenska sammansättningar?"
@Article{sos,
author = {Jonas Sj\"{o}bergh and Viggo Kann},
title = {Vad kan statistik avsl\"{o}ja om svenska sammans{\"a}ttningar?},
journal = {Spr{\aa}k och Stil},
year = {2006},
volume = {16},
number = {},
pages = {199--214}
}
Övriga verktyg
AutoEval
Bigert, Ericson & Solis, 2003,
"Missplel and AutoEval: Two Generic Tools for
Automatic
Evaluation"
@inproceedings{Bigert03toolbox,
author = "Johnny Bigert and Linus Ericson and
Antoine Solis", year = "2003", title
= "{Missplel} and {AutoEval}: Two Generic Tools
for Automatic Evaluation", booktitle =
"Proceedings of Nodalida 2003", address =
"Reykjavik, Iceland"
}
Missplel
Bigert, Ericson & Solis, 2003,
"Missplel and AutoEval: Two Generic Tools for
Automatic
Evaluation"
@inproceedings{Bigert03toolbox,
author = "Johnny Bigert and Linus Ericson and
Antoine Solis", year = "2003", title
= "{Missplel} and {AutoEval}: Two Generic Tools
for Automatic Evaluation", booktitle =
"Proceedings of Nodalida 2003", address =
"Reykjavik, Iceland"
}
Infomat
Rosell, 2007,
"Infomat - A Vector Space Visualization Tool"
@inproceedings{infomat,
author = {Magnus Rosell},
title = "Infomat -- A Vector Space Visualization Tool",
booktitle = {Proceedings of the Workshop Semantic Content Acquisition and Representation (SCAR) 2007},
address = "Tartu, Finland",
year = "2007"
}
Snålgranska
Forskningsartikel om Snålgranska:
Sjöbergh & Knutsson, 2005,
"Faking Errors to Avoid Making Errors: Very
Weakly Supervised Learning for Error Detection in
Writing"
@inproceedings{snaalgranska,
author = {Jonas Sj\"{o}bergh and Ola Knutsson},
title = "Faking Errors to Avoid Making Errors:
Very Weakly Supervised Learning for Error Detection
in Writing", booktitle = "Proceedings of
{RANLP} 2005", address = "Borovets,
Bulgaria", pages = "506--512", year =
"2005" }
Forskningsartikel som utvärderar och jämför Snålgranska med Granska och andra grammatikgranskare:
Bigert, Kann, Knutsson, & Sjöbergh, "Grammar checking for Swedish second language learners", 2004
@incollection{call2004,
author = {Johnny Bigert and Viggo Kann and Ola Knutsson and Jonas Sj\"{o}bergh},
title = {Grammar Checking for {Swedish} Second Language Learners},
booktitle = {{CALL} for the {Nordic} Languages},
pages = "33--47",
publisher = "Samfundslitteratur",
editor = "Peter Juel Henrichsen",
year = "2004"
}
Forskningsartikel om en liknande grammatikgranskningsmetod:
Sjöbergh, "Chunking: an
Unsupervised Method to Find Errors in Text"
2005
@inproceedings{chunks2005,
author = {Jonas Sj\"{o}bergh},
title = {Chunking: an Unsupervised Method to Find Errors in Text},
booktitle = {Proceedings of NODALIDA 2005},
address = "Joensuu, Finland",
year = "2005"}
Stomp
Sjöbergh, 2003,
"Stomp, a POS-tagger with a different
view"
@inproceedings{stomp2003,
author = {Jonas Sj\"{o}bergh}, title
= {Stomp, a {POS}-tagger with a
different view}, booktitle =
"Proceedings of {RANLP}-2003", pages
="440--444", address = "Borovets,
Bulgaria", year = "2003" }
JavaSDM
Tillbaka till Skrutten
