On different approaches to syntactic analysis into bi-lexical dependencies: An empirical comparison of direct, PCFG-based, and HPSG-based parsers

We compare three different approaches to parsing into syntactic, bi- lexical dependencies for English: a ‘direct’ data-driven dependency parser, a statistical phrase structure parser, and a hybrid, ‘deep’ grammar-driven parser. The analyses from the latter two are post- converted to bi-lexical depen...

Full description

Bibliographic Details
Main Authors: Angelina Ivanova, Stephan Oepen, Rebecca Dridan, Dan Flickinger, Lilja Øvrelid, Emanuele Lapponi
Format: Article
Language:English
Published: Institute of Computer Science, Polish Academy of Sciences 2016-04-01
Series:Journal of Language Modelling
Subjects:
Online Access:https://jlm.ipipan.waw.pl/index.php/JLM/article/view/101
_version_ 1818948482996633600
author Angelina Ivanova
Stephan Oepen
Rebecca Dridan
Dan Flickinger
Lilja Øvrelid
Emanuele Lapponi
author_facet Angelina Ivanova
Stephan Oepen
Rebecca Dridan
Dan Flickinger
Lilja Øvrelid
Emanuele Lapponi
author_sort Angelina Ivanova
collection DOAJ
description We compare three different approaches to parsing into syntactic, bi- lexical dependencies for English: a ‘direct’ data-driven dependency parser, a statistical phrase structure parser, and a hybrid, ‘deep’ grammar-driven parser. The analyses from the latter two are post- converted to bi-lexical dependencies. Through this ‘reduction’ of all three approaches to syntactic dependency parsers, we determine empirically what performance can be obtained for a common set of de- pendency types for English, across a broad variety of domains. In doing so, we observe what trade-offs apply along three dimensions, accuracy, efficiency, and resilience to domain variation. Our results suggest that the hand-built grammar in one of our parsers helps in both accuracy and cross-domain parsing performance, but these accuracy gains do not necessarily translate to improvements in the downstream task of negation resolution.
first_indexed 2024-12-20T08:47:31Z
format Article
id doaj.art-0df2c5afa1a04faba8f5434681121b52
institution Directory Open Access Journal
issn 2299-856X
2299-8470
language English
last_indexed 2024-12-20T08:47:31Z
publishDate 2016-04-01
publisher Institute of Computer Science, Polish Academy of Sciences
record_format Article
series Journal of Language Modelling
spelling doaj.art-0df2c5afa1a04faba8f5434681121b522022-12-21T19:46:13ZengInstitute of Computer Science, Polish Academy of SciencesJournal of Language Modelling2299-856X2299-84702016-04-014110.15398/jlm.v4i1.10152On different approaches to syntactic analysis into bi-lexical dependencies: An empirical comparison of direct, PCFG-based, and HPSG-based parsersAngelina Ivanova0Stephan Oepen1Rebecca Dridan2Dan Flickinger3Lilja Øvrelid4Emanuele Lapponi5University of OsloUniversity of Oslo Potsdam UniversityUniversity of OsloStanford UniversityUniversity of OsloUniversity of OsloWe compare three different approaches to parsing into syntactic, bi- lexical dependencies for English: a ‘direct’ data-driven dependency parser, a statistical phrase structure parser, and a hybrid, ‘deep’ grammar-driven parser. The analyses from the latter two are post- converted to bi-lexical dependencies. Through this ‘reduction’ of all three approaches to syntactic dependency parsers, we determine empirically what performance can be obtained for a common set of de- pendency types for English, across a broad variety of domains. In doing so, we observe what trade-offs apply along three dimensions, accuracy, efficiency, and resilience to domain variation. Our results suggest that the hand-built grammar in one of our parsers helps in both accuracy and cross-domain parsing performance, but these accuracy gains do not necessarily translate to improvements in the downstream task of negation resolution.https://jlm.ipipan.waw.pl/index.php/JLM/article/view/101Syntactic Dependency ParsingDomain Variation
spellingShingle Angelina Ivanova
Stephan Oepen
Rebecca Dridan
Dan Flickinger
Lilja Øvrelid
Emanuele Lapponi
On different approaches to syntactic analysis into bi-lexical dependencies: An empirical comparison of direct, PCFG-based, and HPSG-based parsers
Journal of Language Modelling
Syntactic Dependency Parsing
Domain Variation
title On different approaches to syntactic analysis into bi-lexical dependencies: An empirical comparison of direct, PCFG-based, and HPSG-based parsers
title_full On different approaches to syntactic analysis into bi-lexical dependencies: An empirical comparison of direct, PCFG-based, and HPSG-based parsers
title_fullStr On different approaches to syntactic analysis into bi-lexical dependencies: An empirical comparison of direct, PCFG-based, and HPSG-based parsers
title_full_unstemmed On different approaches to syntactic analysis into bi-lexical dependencies: An empirical comparison of direct, PCFG-based, and HPSG-based parsers
title_short On different approaches to syntactic analysis into bi-lexical dependencies: An empirical comparison of direct, PCFG-based, and HPSG-based parsers
title_sort on different approaches to syntactic analysis into bi lexical dependencies an empirical comparison of direct pcfg based and hpsg based parsers
topic Syntactic Dependency Parsing
Domain Variation
url https://jlm.ipipan.waw.pl/index.php/JLM/article/view/101
work_keys_str_mv AT angelinaivanova ondifferentapproachestosyntacticanalysisintobilexicaldependenciesanempiricalcomparisonofdirectpcfgbasedandhpsgbasedparsers
AT stephanoepen ondifferentapproachestosyntacticanalysisintobilexicaldependenciesanempiricalcomparisonofdirectpcfgbasedandhpsgbasedparsers
AT rebeccadridan ondifferentapproachestosyntacticanalysisintobilexicaldependenciesanempiricalcomparisonofdirectpcfgbasedandhpsgbasedparsers
AT danflickinger ondifferentapproachestosyntacticanalysisintobilexicaldependenciesanempiricalcomparisonofdirectpcfgbasedandhpsgbasedparsers
AT liljaøvrelid ondifferentapproachestosyntacticanalysisintobilexicaldependenciesanempiricalcomparisonofdirectpcfgbasedandhpsgbasedparsers
AT emanuelelapponi ondifferentapproachestosyntacticanalysisintobilexicaldependenciesanempiricalcomparisonofdirectpcfgbasedandhpsgbasedparsers