Language Model Priming for Cross-Lingual Event Extraction
The result's identifiers
Result code in 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>
Result on the web
<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>
Alternative languages
Result language
angličtina
Original language name
Language Model Priming for Cross-Lingual Event Extraction
Original language description
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.
Czech name
—
Czech description
—
Classification
Type
J<sub>ost</sub> - Miscellaneous article in a specialist periodical
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Proceedings of the AAAI Conference on Artificial Intelligence
ISSN
2159-5399
e-ISSN
2571-0966
Volume of the periodical
36
Issue of the periodical within the volume
10
Country of publishing house
US - UNITED STATES
Number of pages
9
Pages from-to
10627-10635
UT code for WoS article
—
EID of the result in the Scopus database
—