Bits and Pieces: Investigating the Effects of Subwords in Multi-task Parsing Across Languages and Domains

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3ABMQP9MQI" target="_blank" >RIV/00216208:11320/25:BMQP9MQI - isvavai.cz</a>

Result on the web

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85195954671&partnerID=40&md5=066c7879ddda43aa6174782b91aa248f" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85195954671&partnerID=40&md5=066c7879ddda43aa6174782b91aa248f</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Bits and Pieces: Investigating the Effects of Subwords in Multi-task Parsing Across Languages and Domains

Original language description

Neural parsing is very dependent on the underlying language model. However, very little is known about how choices in the language model affect parsing performance, especially in multi-task learning. We investigate questions on how the choice of subwords affects parsing, how subword sharing is responsible for gains or negative transfer in a multi-task setting where each task is parsing of a specific domain of the same language. More specifically, we investigate these issues across four languages: English, German, Italian, and Turkish. We find a general preference for averaged or last subwords across languages and domains. However, specific POS tags may require different subwords, and the distributional overlap between subwords across domains is perhaps a more influential factor in determining positive or negative transfer than discrepancies in the data sizes. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

Czech name

—

Czech description

—

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)

Project

—

Continuities

—

Publication year

2024

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Jt. Int. Conf. Comput. Linguist., Lang. Resour. Eval., LREC-COLING - Main Conf. Proc.

ISBN

978-249381410-4

ISSN

—

e-ISSN

—

Number of pages

13

Pages from-to

2397-2409

Publisher name

European Language Resources Association (ELRA)

Place of publication

—

Event location

Torino, Italia

Event date

Jan 1, 2025

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—