RUC. Repositorio da Universidade da Coruña
Publication
Contribución de congreso (ConferenceOutput)
Not All Linearizations Are Equally Data-Hungry in Sequence Labeling Parsing
It was held online, 1-3 September 2021., [Absctract]: Different linearizations have been proposed to cast dependency parsing as sequence labeling and solve the task as: (i) a head selection problem, (ii) finding a representation of the token arcs as bracket strings, or (iii) associating partial transition sequences of a transition-based parser to words. Yet, there is little understanding about how these linearizations behave in low-resource setups. Here, we first study their data efficiency, simulating data-restricted setups from a diverse set of rich-resource treebanks. Second, we test whether such differences manifest in truly low-resource setups. The results show that head selection encodings are more data-efficient and perform better in an ideal (gold) framework, but that such advantage greatly vanishes in favour of bracketing formats when the running setup resembles a real-world low-resource configuration., This work is supported by a 2020 Leonardo Grant
for Researchers and Cultural Creators from the FBBVA. The work also receives funding from the
European Research Council (FASTPARSE, grant
agreement No 714150), from ERDF/MICINNAEI (ANSWER-ASAP, TIN2017-85160-C2-1-
R, SCANNER, PID2020-113230RB-C21), from
Xunta de Galicia (ED431C 2020/11), and from
Centro de Investigacion de Galicia ‘CITIC’, funded ´
by Xunta de Galicia and the European Union (European Regional Development Fund- Galicia 2014-
2020 Program) by grant ED431G 2019/01., Xunta de Galicia; ED431C 2020/11, Xunta de Galicia; ED431G 2019/01
Project:
EC / H2020 714150
,
AEI / Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 PID2020-113230RB-C21
,
AEI / Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016 TIN2017-85160-C2-1-R
HANDLE: http://hdl.handle.net/2183/36664
View at: http://hdl.handle.net/2183/36664