@inproceedings{serutla-kourie-1998-sentence,
title = "Sentence analysis using a concept lattice",
author = "Serutla, Lebelo and
Kourie, Derrick",
editor = "Farwell, David and
Gerber, Laurie and
Hovy, Eduard",
booktitle = "Proceedings of the Third Conference of the Association for Machine Translation in the Americas: Technical Papers",
month = oct # " 28-31",
year = "1998",
address = "Langhorne, PA, USA",
publisher = "Springer",
url = "https://link.springer.com/chapter/10.1007/3-540-49478-2_21",
pages = "225--235",
abstract = "Grammatically incorrect sentences result either from an unknown (possibly misspelled) word, an incorrect word order or even an omitted / redundant word. Sentences with these errors are a bottle-neck to NLP systems because they cannot be parsed correctly. Human beings are able to overcome this problem (either occurring in spoken or written language) since they are capable of doing a semantic similarity search to find out if a similar utterance has been heard before or a syntactic similarity search for a stored utterance that shares structural similarities with the input. If the syntactic and semantic analysis of the rest of the input can be done correctly, then a {`}gap{'} that exists in the utterance, can be uniquely identified. In this paper, a system named SAUCOLA which is based on a concept lattice, that mimics human skills in resolving knowledge gaps that exist in written language is presented. The preliminary results show that correct stored sentences can be retrieved based on the words contained in the incorrect input sentence.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="serutla-kourie-1998-sentence">
<titleInfo>
<title>Sentence analysis using a concept lattice</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lebelo</namePart>
<namePart type="family">Serutla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derrick</namePart>
<namePart type="family">Kourie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>1998-oct 28-31</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Conference of the Association for Machine Translation in the Americas: Technical Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Farwell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurie</namePart>
<namePart type="family">Gerber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eduard</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Springer</publisher>
<place>
<placeTerm type="text">Langhorne, PA, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Grammatically incorrect sentences result either from an unknown (possibly misspelled) word, an incorrect word order or even an omitted / redundant word. Sentences with these errors are a bottle-neck to NLP systems because they cannot be parsed correctly. Human beings are able to overcome this problem (either occurring in spoken or written language) since they are capable of doing a semantic similarity search to find out if a similar utterance has been heard before or a syntactic similarity search for a stored utterance that shares structural similarities with the input. If the syntactic and semantic analysis of the rest of the input can be done correctly, then a ‘gap’ that exists in the utterance, can be uniquely identified. In this paper, a system named SAUCOLA which is based on a concept lattice, that mimics human skills in resolving knowledge gaps that exist in written language is presented. The preliminary results show that correct stored sentences can be retrieved based on the words contained in the incorrect input sentence.</abstract>
<identifier type="citekey">serutla-kourie-1998-sentence</identifier>
<location>
<url>https://link.springer.com/chapter/10.1007/3-540-49478-2_21</url>
</location>
<part>
<date>1998-oct 28-31</date>
<extent unit="page">
<start>225</start>
<end>235</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sentence analysis using a concept lattice
%A Serutla, Lebelo
%A Kourie, Derrick
%Y Farwell, David
%Y Gerber, Laurie
%Y Hovy, Eduard
%S Proceedings of the Third Conference of the Association for Machine Translation in the Americas: Technical Papers
%D 1998
%8 oct 28 31
%I Springer
%C Langhorne, PA, USA
%F serutla-kourie-1998-sentence
%X Grammatically incorrect sentences result either from an unknown (possibly misspelled) word, an incorrect word order or even an omitted / redundant word. Sentences with these errors are a bottle-neck to NLP systems because they cannot be parsed correctly. Human beings are able to overcome this problem (either occurring in spoken or written language) since they are capable of doing a semantic similarity search to find out if a similar utterance has been heard before or a syntactic similarity search for a stored utterance that shares structural similarities with the input. If the syntactic and semantic analysis of the rest of the input can be done correctly, then a ‘gap’ that exists in the utterance, can be uniquely identified. In this paper, a system named SAUCOLA which is based on a concept lattice, that mimics human skills in resolving knowledge gaps that exist in written language is presented. The preliminary results show that correct stored sentences can be retrieved based on the words contained in the incorrect input sentence.
%U https://link.springer.com/chapter/10.1007/3-540-49478-2_21
%P 225-235
Markdown (Informal)
[Sentence analysis using a concept lattice](https://link.springer.com/chapter/10.1007/3-540-49478-2_21) (Serutla & Kourie, AMTA 1998)
ACL
- Lebelo Serutla and Derrick Kourie. 1998. Sentence analysis using a concept lattice. In Proceedings of the Third Conference of the Association for Machine Translation in the Americas: Technical Papers, pages 225–235, Langhorne, PA, USA. Springer.