DAHRS: Divergence-Aware Hallucination-Remediated SRL Projection

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A8SG27LRT" target="_blank" >RIV/00216208:11320/25:8SG27LRT - isvavai.cz</a>

Result on the web

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85205383898&doi=10.1007%2f978-3-031-70239-6_29&partnerID=40&md5=12e4b95a4af0c685857215a38298072d" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85205383898&doi=10.1007%2f978-3-031-70239-6_29&partnerID=40&md5=12e4b95a4af0c685857215a38298072d</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-70239-6_29" target="_blank" >10.1007/978-3-031-70239-6_29</a>

Result language

angličtina

Original language name

DAHRS: Divergence-Aware Hallucination-Remediated SRL Projection

Original language description

Semantic role labeling (SRL) enriches many downstream applications, e.g., machine translation, question answering, summarization, and stance/belief detection. However, building multilingual SRL models is challenging due to the scarcity of semantically annotated corpora for multiple languages. Moreover, state-of-the-art SRL projection (XSRL) based on large language models (LLMs) yields output that is riddled with spurious role labels. Remediation of such hallucinations is not straightforward due to the lack of explainability of LLMs. We show that hallucinated role labels are related to naturally occurring divergence types that interfere with initial alignments. We implement Divergence-Aware Hallucination-Remediated SRL projection (DAHRS), leveraging linguistically-informed alignment remediation followed by greedy First-Come First-Assign (FCFA) SRL projection. DAHRS improves the accuracy of SRL projection without additional transformer-based machinery, beating XSRL in both human and automatic comparisons, and advancing beyond headwords to accommodate phrase-level SRL projection (e.g., EN-FR, EN-ES). Using CoNLL-2009 as our ground truth, we achieve a higher word-level F1 over XSRL: 87.6% vs. 77.3% (EN-FR) and 89.0% vs. 82.7% (EN-ES). Human phrase-level assessments yield 89.1% (EN-FR) and 91.0% (EN-ES). We also define a divergence metric to adapt our approach to other language pairs (e.g., English-Tagalog). © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

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

Lect. Notes Comput. Sci.

ISBN

978-303170238-9

ISSN

0302-9743

e-ISSN

—

Number of pages

16

Pages from-to

423-438

Publisher name

Springer Science and Business Media Deutschland GmbH

Place of publication

—

Event location

Turin

Event date

Jan 1, 2025

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—