Uniform Meaning Representation Parsing as a Pipelined Approach

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3ASB6IIP9Y" target="_blank" >RIV/00216208:11320/25:SB6IIP9Y - isvavai.cz</a>

Result on the web

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85204887484&partnerID=40&md5=6ba25a0afeb49f72cb3e2f6b5e4182ae" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85204887484&partnerID=40&md5=6ba25a0afeb49f72cb3e2f6b5e4182ae</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Uniform Meaning Representation Parsing as a Pipelined Approach

Original language description

Uniform Meaning Representation (UMR) is the next phase of semantic formalism following Abstract Meaning Representation (AMR), with added focus on inter-sentential relations allowing the representational scope of UMR to cover a full document. This, in turn, greatly increases the complexity of its parsing task with the additional requirement of capturing document-level linguistic phenomena such as coreference, modal and temporal dependencies. In order to establish a strong baseline despite the small size of recently released UMR v1.0 corpus, we introduce a pipeline model that does not require any training. At the core of our method is a two-track strategy of obtaining UMR's sentence and document graphs separately, with the document-level triples being compiled at the token level and the sentence graph being converted from AMR graphs. By leveraging alignment between AMR and its sentence, we are able to generate the first automatic English UMR parses. © 2024 Association for Computational Linguistics.

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

TextGraphs ACL - Proc. TextGraphs-17: Graph-Based Methods Nat. Lang. Process., Annu. Meet. Assoc. Comput. Linguist.

ISBN

979-889176145-2

ISSN

—

e-ISSN

—

Number of pages

13

Pages from-to

40-52

Publisher name

Association for Computational Linguistics (ACL)

Place of publication

—

Event location

Bangkok

Event date

Jan 1, 2025

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—