DE eng

Search in the Catalogues and Directories

Hits 1 – 11 of 11

1
Text preprocessing
In: Handbook of natural language processing (Boca Raton, Fla., 2010), p. 9-30
MPI für Psycholinguistik
Show details
2
Improving out-of-vocabulary name resolution
In: Computer speech and language. - Amsterdam [u.a.] : Elsevier 19 (2005) 1, 107-128
BLLDB
Show details
3
Improving out-of-vocabulary name resolution
In: Computer speech and language. - Amsterdam [u.a.] : Elsevier 19 (2005) 1, 107
OLC Linguistik
Show details
4
Multilingual Video and Audio News Alerting
In: DTIC (2004)
BASE
Show details
5
Robust information extraction from automatically generated speech transcriptions
In: Speech communication. - Amsterdam [u.a.] : Elsevier 32 (2000) 1, 95-110
OLC Linguistik
Show details
6
Accessing information in spoken audio
Renals, Steve (Hrsg.); Robinson, Tony (Hrsg.); Abberley, Dave (Mitarb.)...
In: Speech communication. - Amsterdam [u.a.] : Elsevier 32 (2000) 1-2, 1-154
BLLDB
Show details
7
Tokenisation and sentence segmentation
In: Handbook of natural language processing. - New York [u.a.] : Dekker (2000), 11-35
BLLDB
Show details
8
Adaptive Multilingual Sentence Boundary Disambiguation
In: Computational linguistics. - Cambridge, Mass. : MIT Press 23 (1997) 2, 241-268
OLC Linguistik
Show details
9
Adaptive multilingual sentence boundary disambiguation
In: Computational linguistics. - Cambridge, Mass. : MIT Press 23 (1997) 2, 241-267
BLLDB
Show details
10
SATZ - An Adaptive Sentence Segmentation System ...
Palmer, David D.. - : arXiv, 1995
BASE
Show details
11
Adaptive Sentence Boundary Disambiguation ...
Abstract: Labeling of sentence boundaries is a necessary prerequisite for many natural language processing tasks, including part-of-speech tagging and sentence alignment. End-of-sentence punctuation marks are ambiguous; to disambiguate them most systems use brittle, special-purpose regular expression grammars and exception rules. As an alternative, we have developed an efficient, trainable algorithm that uses a lexicon with part-of-speech probabilities and a feed-forward neural network. After training for less than one minute, the method correctly labels over 98.5\% of sentence boundaries in a corpus of over 27,000 sentence-boundary marks. We show the method to be efficient and easily adaptable to different text genres, including single-case texts. ... : This is a Latex version of the previously submitted ps file (formatted as a uuencoded gz-compressed .tar file created by csh script). The software from the work described in this paper is available by contacting dpalmer@cs.berkeley.edu ...
Keyword: Computation and Language cs.CL; FOS Computer and information sciences
URL: https://arxiv.org/abs/cmp-lg/9411022
https://dx.doi.org/10.48550/arxiv.cmp-lg/9411022
BASE
Hide details

Catalogues
0
0
3
0
0
0
0
Bibliographies
4
0
0
0
0
0
0
0
1
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
3
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern