@inproceedings{anderson-kotze-2006-finite,
title = "Finite state tokenisation of an orthographical disjunctive agglutinative language: The verbal segment of {N}orthern {S}otho",
author = "Anderson, Winston N and
Kotz{\'e}, Petronella M",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}`06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L06-1442/",
abstract = "Tokenisation is an important first pre-processing step required to adequately test finite-state morphological analysers. In agglutinative languages each morpheme is concatinatively added on to form a complete morphological structure. Disjunctive agglutinative languages like Northern Sotho write these morphemes, for certain morphological categories only, as separate words separated by spaces or line breaks. These breaks are, by their nature, different from breaks that separate words that are written conjunctively. A tokeniser is required to isolate categories, like a verb, from raw text before they can be correctly morphologically analysed. The authors have successfully produced a finite state tokeniser for Northern Sotho, where verb segments are written disjunctively but nominal segments conjunctively. The authors show that since reduplication in the Northern Sotho language does not affect the pre-processing tokeniser, the disjunctive standard verbal segment as a construct in Northern Sotho is deterministic, finite-state and a regular Type 0 language in the Chomsky hierarchy and that the copulative verbal segment, due to its semi-disjunctivism, is ambiguously non-deterministic."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="anderson-kotze-2006-finite">
<titleInfo>
<title>Finite state tokenisation of an orthographical disjunctive agglutinative language: The verbal segment of Northern Sotho</title>
</titleInfo>
<name type="personal">
<namePart type="given">Winston</namePart>
<namePart type="given">N</namePart>
<namePart type="family">Anderson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petronella</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Kotzé</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC‘06)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aldo</namePart>
<namePart type="family">Gangemi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Tokenisation is an important first pre-processing step required to adequately test finite-state morphological analysers. In agglutinative languages each morpheme is concatinatively added on to form a complete morphological structure. Disjunctive agglutinative languages like Northern Sotho write these morphemes, for certain morphological categories only, as separate words separated by spaces or line breaks. These breaks are, by their nature, different from breaks that separate words that are written conjunctively. A tokeniser is required to isolate categories, like a verb, from raw text before they can be correctly morphologically analysed. The authors have successfully produced a finite state tokeniser for Northern Sotho, where verb segments are written disjunctively but nominal segments conjunctively. The authors show that since reduplication in the Northern Sotho language does not affect the pre-processing tokeniser, the disjunctive standard verbal segment as a construct in Northern Sotho is deterministic, finite-state and a regular Type 0 language in the Chomsky hierarchy and that the copulative verbal segment, due to its semi-disjunctivism, is ambiguously non-deterministic.</abstract>
<identifier type="citekey">anderson-kotze-2006-finite</identifier>
<location>
<url>https://aclanthology.org/L06-1442/</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Finite state tokenisation of an orthographical disjunctive agglutinative language: The verbal segment of Northern Sotho
%A Anderson, Winston N.
%A Kotzé, Petronella M.
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC‘06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F anderson-kotze-2006-finite
%X Tokenisation is an important first pre-processing step required to adequately test finite-state morphological analysers. In agglutinative languages each morpheme is concatinatively added on to form a complete morphological structure. Disjunctive agglutinative languages like Northern Sotho write these morphemes, for certain morphological categories only, as separate words separated by spaces or line breaks. These breaks are, by their nature, different from breaks that separate words that are written conjunctively. A tokeniser is required to isolate categories, like a verb, from raw text before they can be correctly morphologically analysed. The authors have successfully produced a finite state tokeniser for Northern Sotho, where verb segments are written disjunctively but nominal segments conjunctively. The authors show that since reduplication in the Northern Sotho language does not affect the pre-processing tokeniser, the disjunctive standard verbal segment as a construct in Northern Sotho is deterministic, finite-state and a regular Type 0 language in the Chomsky hierarchy and that the copulative verbal segment, due to its semi-disjunctivism, is ambiguously non-deterministic.
%U https://aclanthology.org/L06-1442/
Markdown (Informal)
[Finite state tokenisation of an orthographical disjunctive agglutinative language: The verbal segment of Northern Sotho](https://aclanthology.org/L06-1442/) (Anderson & Kotzé, LREC 2006)
ACL