Retrieving Relevant Context to Align Representations for Cross-lingual Event Detection

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3AF4NB9QQD" target="_blank" >RIV/00216208:11320/23:F4NB9QQD - isvavai.cz</a>

Výsledek na webu

<a href="https://aclanthology.org/2023.findings-acl.135/" target="_blank" >https://aclanthology.org/2023.findings-acl.135/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18653/v1/2023.findings-acl.135" target="_blank" >10.18653/v1/2023.findings-acl.135</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Retrieving Relevant Context to Align Representations for Cross-lingual Event Detection

Popis výsledku v původním jazyce

"We study the problem of cross-lingual transfer learning for event detection (ED) where models trained on a source language are expected to perform well on data for a new target language. Among a few recent works for this problem, the main approaches involve representation matching (e.g., adversarial training) that aims to eliminate language-specific features from the representations to achieve the language-invariant representations. However, due to the mix of language-specific features with event-discriminative context, representation matching methods might also remove important features for event prediction, thus hindering the performance for ED. To address this issue, we introduce a novel approach for cross-lingual ED where representations are augmented with additional context (i.e., not eliminating) to bridge the gap between languages while enriching the contextual information to facilitate ED. At the core of our method involves a retrieval model that retrieves relevant sentences in the target language for an input sentence to compute augmentation representations. Experiments on three languages demonstrate the state-of-the-art performance of our model for cross-lingual ED."

Název v anglickém jazyce

Retrieving Relevant Context to Align Representations for Cross-lingual Event Detection

Popis výsledku anglicky

"We study the problem of cross-lingual transfer learning for event detection (ED) where models trained on a source language are expected to perform well on data for a new target language. Among a few recent works for this problem, the main approaches involve representation matching (e.g., adversarial training) that aims to eliminate language-specific features from the representations to achieve the language-invariant representations. However, due to the mix of language-specific features with event-discriminative context, representation matching methods might also remove important features for event prediction, thus hindering the performance for ED. To address this issue, we introduce a novel approach for cross-lingual ED where representations are augmented with additional context (i.e., not eliminating) to bridge the gap between languages while enriching the contextual information to facilitate ED. At the core of our method involves a retrieval model that retrieves relevant sentences in the target language for an input sentence to compute augmentation representations. Experiments on three languages demonstrate the state-of-the-art performance of our model for cross-lingual ED."

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

2023

Kód důvěrnosti údajů

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

Název statě ve sborníku

"Findings of the Association for Computational Linguistics: ACL 2023"

ISBN

978-1-959429-62-3

ISSN

—

e-ISSN

—

Počet stran výsledku

14

Strana od-do

2157-2170

Název nakladatele

ACL

Místo vydání

Toronto, Canada

Místo konání akce

Toronto, Canada

Datum konání akce

1. 1. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—