@inproceedings{boukaram-etal-2018-improving,
title = "Improving Domain Independent Question Parsing with Synthetic Treebanks",
author = "Boukaram, Halim-Antoine and
Habash, Nizar and
Ziadee, Micheline and
Sakr, Majd",
editor = "Savary, Agata and
Ramisch, Carlos and
Hwang, Jena D. and
Schneider, Nathan and
Andresen, Melanie and
Pradhan, Sameer and
Petruck, Miriam R. L.",
booktitle = "Proceedings of the Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions ({LAW}-{MWE}-{C}x{G}-2018)",
month = aug,
year = "2018",
address = "Santa Fe, New Mexico, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-4924",
pages = "214--221",
abstract = "Automatic syntactic parsing for question constructions is a challenging task due to the paucity of training examples in most treebanks. The near absence of question constructions is due to the dominance of the news domain in treebanking efforts. In this paper, we compare two synthetic low-cost question treebank creation methods with a conventional manual high-cost annotation method in the context of three domains (news questions, political talk shows, and chatbots) for Modern Standard Arabic, a language with relatively low resources and rich morphology. Our results show that synthetic methods can be effective at significantly reducing parsing errors for a target domain without having to invest large resources on manual annotation; and the combination of manual and synthetic methods is our best domain-independent performer.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="boukaram-etal-2018-improving">
<titleInfo>
<title>Improving Domain Independent Question Parsing with Synthetic Treebanks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Halim-Antoine</namePart>
<namePart type="family">Boukaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Micheline</namePart>
<namePart type="family">Ziadee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Majd</namePart>
<namePart type="family">Sakr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions (LAW-MWE-CxG-2018)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Agata</namePart>
<namePart type="family">Savary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Ramisch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jena</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Hwang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melanie</namePart>
<namePart type="family">Andresen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sameer</namePart>
<namePart type="family">Pradhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miriam</namePart>
<namePart type="given">R</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Petruck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Santa Fe, New Mexico, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic syntactic parsing for question constructions is a challenging task due to the paucity of training examples in most treebanks. The near absence of question constructions is due to the dominance of the news domain in treebanking efforts. In this paper, we compare two synthetic low-cost question treebank creation methods with a conventional manual high-cost annotation method in the context of three domains (news questions, political talk shows, and chatbots) for Modern Standard Arabic, a language with relatively low resources and rich morphology. Our results show that synthetic methods can be effective at significantly reducing parsing errors for a target domain without having to invest large resources on manual annotation; and the combination of manual and synthetic methods is our best domain-independent performer.</abstract>
<identifier type="citekey">boukaram-etal-2018-improving</identifier>
<location>
<url>https://aclanthology.org/W18-4924</url>
</location>
<part>
<date>2018-08</date>
<extent unit="page">
<start>214</start>
<end>221</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Domain Independent Question Parsing with Synthetic Treebanks
%A Boukaram, Halim-Antoine
%A Habash, Nizar
%A Ziadee, Micheline
%A Sakr, Majd
%Y Savary, Agata
%Y Ramisch, Carlos
%Y Hwang, Jena D.
%Y Schneider, Nathan
%Y Andresen, Melanie
%Y Pradhan, Sameer
%Y Petruck, Miriam R. L.
%S Proceedings of the Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions (LAW-MWE-CxG-2018)
%D 2018
%8 August
%I Association for Computational Linguistics
%C Santa Fe, New Mexico, USA
%F boukaram-etal-2018-improving
%X Automatic syntactic parsing for question constructions is a challenging task due to the paucity of training examples in most treebanks. The near absence of question constructions is due to the dominance of the news domain in treebanking efforts. In this paper, we compare two synthetic low-cost question treebank creation methods with a conventional manual high-cost annotation method in the context of three domains (news questions, political talk shows, and chatbots) for Modern Standard Arabic, a language with relatively low resources and rich morphology. Our results show that synthetic methods can be effective at significantly reducing parsing errors for a target domain without having to invest large resources on manual annotation; and the combination of manual and synthetic methods is our best domain-independent performer.
%U https://aclanthology.org/W18-4924
%P 214-221
Markdown (Informal)
[Improving Domain Independent Question Parsing with Synthetic Treebanks](https://aclanthology.org/W18-4924) (Boukaram et al., LAW-MWE 2018)
ACL
- Halim-Antoine Boukaram, Nizar Habash, Micheline Ziadee, and Majd Sakr. 2018. Improving Domain Independent Question Parsing with Synthetic Treebanks. In Proceedings of the Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions (LAW-MWE-CxG-2018), pages 214–221, Santa Fe, New Mexico, USA. Association for Computational Linguistics.