@inproceedings{adolphs-etal-2008-fine,
title = "Some Fine Points of Hybrid Natural Language Parsing",
author = "Adolphs, Peter and
Oepen, Stephan and
Callmeier, Ulrich and
Crysmann, Berthold and
Flickinger, Dan and
Kiefer, Bernd",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/349_paper.pdf",
abstract = "Large-scale grammar-based parsing systems nowadays increasingly rely on independently developed, more specialized components for pre-processing their input. However, different tools make conflicting assumptions about very basic properties such as tokenization. To make linguistic annotation gathered in pre-processing available to deep parsing, a hybrid NLP system needs to establish a coherent mapping between the two universes. Our basic assumption is that tokens are best described by attribute value matrices (AVMs) that may be arbitrarily complex. We propose a powerful resource-sensitive rewrite formalism, chart mapping, that allows us to mediate between the token descriptions delivered by shallow pre-processing components and the input expected by the grammar. We furthermore propose a novel way of unknown word treatment where all generic lexical entries are instantiated that are licensed by a particular token AVM. Again, chart mapping is used to give the grammar writer full control as to which items (e.g. native vs. generic lexical items) enter syntactic parsing. We discuss several further uses of the original idea and report on early experiences with the new machinery.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="adolphs-etal-2008-fine">
<titleInfo>
<title>Some Fine Points of Hybrid Natural Language Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Adolphs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephan</namePart>
<namePart type="family">Oepen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ulrich</namePart>
<namePart type="family">Callmeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Berthold</namePart>
<namePart type="family">Crysmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Flickinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bernd</namePart>
<namePart type="family">Kiefer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Stelios</namePart>
<namePart type="family">Piperidis</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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large-scale grammar-based parsing systems nowadays increasingly rely on independently developed, more specialized components for pre-processing their input. However, different tools make conflicting assumptions about very basic properties such as tokenization. To make linguistic annotation gathered in pre-processing available to deep parsing, a hybrid NLP system needs to establish a coherent mapping between the two universes. Our basic assumption is that tokens are best described by attribute value matrices (AVMs) that may be arbitrarily complex. We propose a powerful resource-sensitive rewrite formalism, chart mapping, that allows us to mediate between the token descriptions delivered by shallow pre-processing components and the input expected by the grammar. We furthermore propose a novel way of unknown word treatment where all generic lexical entries are instantiated that are licensed by a particular token AVM. Again, chart mapping is used to give the grammar writer full control as to which items (e.g. native vs. generic lexical items) enter syntactic parsing. We discuss several further uses of the original idea and report on early experiences with the new machinery.</abstract>
<identifier type="citekey">adolphs-etal-2008-fine</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/349_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Some Fine Points of Hybrid Natural Language Parsing
%A Adolphs, Peter
%A Oepen, Stephan
%A Callmeier, Ulrich
%A Crysmann, Berthold
%A Flickinger, Dan
%A Kiefer, Bernd
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F adolphs-etal-2008-fine
%X Large-scale grammar-based parsing systems nowadays increasingly rely on independently developed, more specialized components for pre-processing their input. However, different tools make conflicting assumptions about very basic properties such as tokenization. To make linguistic annotation gathered in pre-processing available to deep parsing, a hybrid NLP system needs to establish a coherent mapping between the two universes. Our basic assumption is that tokens are best described by attribute value matrices (AVMs) that may be arbitrarily complex. We propose a powerful resource-sensitive rewrite formalism, chart mapping, that allows us to mediate between the token descriptions delivered by shallow pre-processing components and the input expected by the grammar. We furthermore propose a novel way of unknown word treatment where all generic lexical entries are instantiated that are licensed by a particular token AVM. Again, chart mapping is used to give the grammar writer full control as to which items (e.g. native vs. generic lexical items) enter syntactic parsing. We discuss several further uses of the original idea and report on early experiences with the new machinery.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/349_paper.pdf
Markdown (Informal)
[Some Fine Points of Hybrid Natural Language Parsing](http://www.lrec-conf.org/proceedings/lrec2008/pdf/349_paper.pdf) (Adolphs et al., LREC 2008)
ACL
- Peter Adolphs, Stephan Oepen, Ulrich Callmeier, Berthold Crysmann, Dan Flickinger, and Bernd Kiefer. 2008. Some Fine Points of Hybrid Natural Language Parsing. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).