Learning to Disambiguate Syntactic Relations

Learning to Disambiguate Syntactic Relations

Natural Language is highly ambiguous, on every level. This article describes a fast broad-coverage state-of-the-art parser that uses a carefully hand-written grammar and probability-based machine learning approaches on the syntactic level. It is shown in detail which statistical learning models base...

Full description

Bibliographic Details
Main Author: Gerold Schneider
Format: Article
Language:deu
Published: Bern Open Publishing 2003-12-01
Series:Linguistik Online
Online Access:https://bop.unibe.ch/linguistik-online/article/view/789
id doaj-375610e6991a4daabdba6fcdf78473f9
record_format Article
spelling doaj-375610e6991a4daabdba6fcdf78473f92021-09-13T12:57:10ZdeuBern Open PublishingLinguistik Online1615-30142003-12-0117510.13092/lo.17.789Learning to Disambiguate Syntactic RelationsGerold SchneiderNatural Language is highly ambiguous, on every level. This article describes a fast broad-coverage state-of-the-art parser that uses a carefully hand-written grammar and probability-based machine learning approaches on the syntactic level. It is shown in detail which statistical learning models based on Maximum-Likelihood Estimation (MLE) can support a highly developed linguistic grammar in the disambiguation process. https://bop.unibe.ch/linguistik-online/article/view/789
collection DOAJ
language deu
format Article
sources DOAJ
author Gerold Schneider
spellingShingle Gerold Schneider
Learning to Disambiguate Syntactic Relations
Linguistik Online
author_facet Gerold Schneider
author_sort Gerold Schneider
title Learning to Disambiguate Syntactic Relations
title_short Learning to Disambiguate Syntactic Relations
title_full Learning to Disambiguate Syntactic Relations
title_fullStr Learning to Disambiguate Syntactic Relations
title_full_unstemmed Learning to Disambiguate Syntactic Relations
title_sort learning to disambiguate syntactic relations
publisher Bern Open Publishing
series Linguistik Online
issn 1615-3014
publishDate 2003-12-01
description Natural Language is highly ambiguous, on every level. This article describes a fast broad-coverage state-of-the-art parser that uses a carefully hand-written grammar and probability-based machine learning approaches on the syntactic level. It is shown in detail which statistical learning models based on Maximum-Likelihood Estimation (MLE) can support a highly developed linguistic grammar in the disambiguation process.
url https://bop.unibe.ch/linguistik-online/article/view/789
work_keys_str_mv AT geroldschneider learningtodisambiguatesyntacticrelations
_version_ 1717380680471543808

Similar Items