Language Model Priming for Cross-Lingual Event Extraction

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F22%3ACSBT4H3W" target="_blank" >RIV/00216208:11320/22:CSBT4H3W - isvavai.cz</a>

Výsledek na webu

<a href="https://ojs.aaai.org/index.php/AAAI/article/view/21307" target="_blank" >https://ojs.aaai.org/index.php/AAAI/article/view/21307</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1609/aaai.v36i10.21307" target="_blank" >10.1609/aaai.v36i10.21307</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Language Model Priming for Cross-Lingual Event Extraction

Popis výsledku v původním jazyce

We present a novel, language-agnostic approach to "priming" language models for the task of event extraction, providing particularly effective performance in low-resource and zero-shot cross-lingual settings. With priming, we augment the input to the transformer stack's language model differently depending on the question(s) being asked of the model at runtime. For instance, if the model is being asked to identify arguments for the trigger "protested", we will provide that trigger as part of the input to the language model, allowing it to produce different representations for candidate arguments than when it is asked about arguments for the trigger "arrest" elsewhere in the same sentence. We show that by enabling the language model to better compensate for the deficits of sparse and noisy training data, our approach improves both trigger and argument detection and classification significantly over the state of the art in a zero-shot cross-lingual setting.

Název v anglickém jazyce

Language Model Priming for Cross-Lingual Event Extraction

Popis výsledku anglicky

We present a novel, language-agnostic approach to "priming" language models for the task of event extraction, providing particularly effective performance in low-resource and zero-shot cross-lingual settings. With priming, we augment the input to the transformer stack's language model differently depending on the question(s) being asked of the model at runtime. For instance, if the model is being asked to identify arguments for the trigger "protested", we will provide that trigger as part of the input to the language model, allowing it to produce different representations for candidate arguments than when it is asked about arguments for the trigger "arrest" elsewhere in the same sentence. We show that by enabling the language model to better compensate for the deficits of sparse and noisy training data, our approach improves both trigger and argument detection and classification significantly over the state of the art in a zero-shot cross-lingual setting.

Druh

J_ost - Ostatní články v recenzovaných periodicích

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 periodika

Proceedings of the AAAI Conference on Artificial Intelligence

ISSN

2159-5399

e-ISSN

2571-0966

Svazek periodika

36

Číslo periodika v rámci svazku

10

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

9

Strana od-do

10627-10635

Kód UT WoS článku

—

EID výsledku v databázi Scopus

—