Dependency parsing evaluation for low-resource spontaneous speech
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10440971" target="_blank" >RIV/00216208:11320/21:10440971 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Dependency parsing evaluation for low-resource spontaneous speech
Original language description
How well can a state-of-the-art parsing system, developed for the written domain, perform when applied to spontaneous speech data involving different interlocutors? This study addresses this question in a low-resource setting using child-parent conversations from the CHILDES databse. Specifically, we focus on dependency parsing evaluation for utterances of one specific child (18 - 27 months) and her parents. We first present a semi-automatic adaption of the dependency annotation scheme in CHILDES to that of the Universal Dependencies project, an annotation style that is more commonly applied in dependency parsing. Our evaluation demonstrates that an out-of-domain biaffine parser trained only on written texts performs well with parent speech. There is, however, much room for improvement on child utterances, particularly at 18 and 21 months, due to cases of omission and repetition that are prevalent in child speech. By contrast, parsers trained or fine-tuned with in-domain spoken data on a much smaller scale can achieve comparable results for parent speech and improve the weak parsing performance for child speech at these earlier ages.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Adapt-NLP 2021 - 2nd Workshop on Domain Adaptation for NLP, Proceedings
ISBN
978-1-954085-08-4
ISSN
—
e-ISSN
—
Number of pages
10
Pages from-to
156-165
Publisher name
Association for Computational Linguistics
Place of publication
Stroudsburg
Event location
online
Event date
Apr 20, 2021
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—