@inproceedings{bies-etal-2006-linguistic,
title = "Linguistic Resources for Speech Parsing",
author = "Bies, Ann and
Strassel, Stephanie and
Lee, Haejoong and
Maeda, Kazuaki and
Kulick, Seth and
Liu, Yang and
Harper, Mary and
Lease, Matthew",
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 = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/755_pdf.pdf",
abstract = "We report on the success of a two-pass approach to annotating metadata, speech effects and syntactic structure in English conversational speech: separately annotating transcribed speech for structural metadata, or structural events, (fillers, speech repairs ( or edit dysfluencies) and SUs, or syntactic/semantic units) and for syntactic structure (treebanking constituent structure and shallow argument structure). The two annotations were then combined into a single representation. Certain alignment issues between the two types of annotation led to the discovery and correction of annotation errors in each, resulting in a more accurate and useful resource. The development of this corpus was motivated by the need to have both metadata and syntactic structure annotated in order to support synergistic work on speech parsing and structural event detection. Automatic detection of these speech phenomena would simultaneously improve parsing accuracy and provide a mechanism for cleaning up transcriptions for downstream text processing. Similarly, constraints imposed by text processing systems such as parsers can be used to help improve identification of disfluencies and sentence boundaries. This paper reports on our efforts to develop a linguistic resource providing both spoken metadata and syntactic structure information, and describes the resulting corpus of English conversational speech.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bies-etal-2006-linguistic">
<titleInfo>
<title>Linguistic Resources for Speech Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ann</namePart>
<namePart type="family">Bies</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephanie</namePart>
<namePart type="family">Strassel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haejoong</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazuaki</namePart>
<namePart type="family">Maeda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seth</namePart>
<namePart type="family">Kulick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mary</namePart>
<namePart type="family">Harper</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Lease</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>We report on the success of a two-pass approach to annotating metadata, speech effects and syntactic structure in English conversational speech: separately annotating transcribed speech for structural metadata, or structural events, (fillers, speech repairs ( or edit dysfluencies) and SUs, or syntactic/semantic units) and for syntactic structure (treebanking constituent structure and shallow argument structure). The two annotations were then combined into a single representation. Certain alignment issues between the two types of annotation led to the discovery and correction of annotation errors in each, resulting in a more accurate and useful resource. The development of this corpus was motivated by the need to have both metadata and syntactic structure annotated in order to support synergistic work on speech parsing and structural event detection. Automatic detection of these speech phenomena would simultaneously improve parsing accuracy and provide a mechanism for cleaning up transcriptions for downstream text processing. Similarly, constraints imposed by text processing systems such as parsers can be used to help improve identification of disfluencies and sentence boundaries. This paper reports on our efforts to develop a linguistic resource providing both spoken metadata and syntactic structure information, and describes the resulting corpus of English conversational speech.</abstract>
<identifier type="citekey">bies-etal-2006-linguistic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/755_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Linguistic Resources for Speech Parsing
%A Bies, Ann
%A Strassel, Stephanie
%A Lee, Haejoong
%A Maeda, Kazuaki
%A Kulick, Seth
%A Liu, Yang
%A Harper, Mary
%A Lease, Matthew
%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 bies-etal-2006-linguistic
%X We report on the success of a two-pass approach to annotating metadata, speech effects and syntactic structure in English conversational speech: separately annotating transcribed speech for structural metadata, or structural events, (fillers, speech repairs ( or edit dysfluencies) and SUs, or syntactic/semantic units) and for syntactic structure (treebanking constituent structure and shallow argument structure). The two annotations were then combined into a single representation. Certain alignment issues between the two types of annotation led to the discovery and correction of annotation errors in each, resulting in a more accurate and useful resource. The development of this corpus was motivated by the need to have both metadata and syntactic structure annotated in order to support synergistic work on speech parsing and structural event detection. Automatic detection of these speech phenomena would simultaneously improve parsing accuracy and provide a mechanism for cleaning up transcriptions for downstream text processing. Similarly, constraints imposed by text processing systems such as parsers can be used to help improve identification of disfluencies and sentence boundaries. This paper reports on our efforts to develop a linguistic resource providing both spoken metadata and syntactic structure information, and describes the resulting corpus of English conversational speech.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/755_pdf.pdf
Markdown (Informal)
[Linguistic Resources for Speech Parsing](http://www.lrec-conf.org/proceedings/lrec2006/pdf/755_pdf.pdf) (Bies et al., LREC 2006)
ACL
- Ann Bies, Stephanie Strassel, Haejoong Lee, Kazuaki Maeda, Seth Kulick, Yang Liu, Mary Harper, and Matthew Lease. 2006. Linguistic Resources for Speech Parsing. In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06), Genoa, Italy. European Language Resources Association (ELRA).