Probing for Labeled Dependency Trees

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F22%3APQYQ7XZ5" target="_blank" >RIV/00216208:11320/22:PQYQ7XZ5 - isvavai.cz</a>

Výsledek na webu

<a href="https://aclanthology.org/2022.acl-long.532" target="_blank" >https://aclanthology.org/2022.acl-long.532</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18653/v1/2022.acl-long.532" target="_blank" >10.18653/v1/2022.acl-long.532</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Probing for Labeled Dependency Trees

Popis výsledku v původním jazyce

Probing has become an important tool for analyzing representations in Natural Language Processing (NLP). For graphical NLP tasks such as dependency parsing, linear probes are currently limited to extracting undirected or unlabeled parse trees which do not capture the full task. This work introduces DepProbe, a linear probe which can extract labeled and directed dependency parse trees from embeddings while using fewer parameters and compute than prior methods. Leveraging its full task coverage and lightweight parametrization, we investigate its predictive power for selecting the best transfer language for training a full biaffine attention parser. Across 13 languages, our proposed method identifies the best source treebank 94% of the time, outperforming competitive baselines and prior work. Finally, we analyze the informativeness of task-specific subspaces in contextual embeddings as well as which benefits a full parser's non-linear parametrization provides.

Název v anglickém jazyce

Probing for Labeled Dependency Trees

Popis výsledku anglicky

Probing has become an important tool for analyzing representations in Natural Language Processing (NLP). For graphical NLP tasks such as dependency parsing, linear probes are currently limited to extracting undirected or unlabeled parse trees which do not capture the full task. This work introduces DepProbe, a linear probe which can extract labeled and directed dependency parse trees from embeddings while using fewer parameters and compute than prior methods. Leveraging its full task coverage and lightweight parametrization, we investigate its predictive power for selecting the best transfer language for training a full biaffine attention parser. Across 13 languages, our proposed method identifies the best source treebank 94% of the time, outperforming competitive baselines and prior work. Finally, we analyze the informativeness of task-specific subspaces in contextual embeddings as well as which benefits a full parser's non-linear parametrization provides.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2022

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

ISBN

978-1-955917-21-6

ISSN

—

e-ISSN

—

Počet stran výsledku

16

Strana od-do

7711-7726

Název nakladatele

Association for Computational Linguistics

Místo vydání

—

Místo konání akce

Dublin, Ireland

Datum konání akce

1. 1. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—