Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Viet Dac Lai"'
Publikováno v:
SIGIR
We address the poor generalization of few-shot learning models for event detection (ED) using transfer learning and representation regularization. In particular, we propose to transfer knowledge from open-domain word sense disambiguation into few-sho
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::df538bad256adf6d3a0ef3b565673dc3
https://doi.org/10.1145/3404835.3463054
https://doi.org/10.1145/3404835.3463054
Publikováno v:
EACL (System Demonstrations)
We introduce Trankit, a light-weight Transformer-based Toolkit for multilingual Natural Language Processing (NLP). It provides a trainable pipeline for fundamental NLP tasks over 100 languages, and 90 pretrained pipelines for 56 languages. Built on a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2f873e1b6e2cd01cf9689ae7d1eb4509
http://arxiv.org/abs/2101.03289
http://arxiv.org/abs/2101.03289
Publikováno v:
ACL/IJCNLP (Findings)
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5970a098a13e8447d5c072d30c60752e
https://doi.org/10.18653/v1/2021.findings-acl.211
https://doi.org/10.18653/v1/2021.findings-acl.211
Publikováno v:
NAACL-HLT
Existing works on information extraction (IE) have mainly solved the four main tasks separately (entity mention recognition, relation extraction, event trigger detection, and argument extraction), thus failing to benefit from inter-dependencies betwe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::49ad5beea6357b96dd11d2670760cc4e
Publikováno v:
ACL/IJCNLP (1)
Event Detection (ED) aims to recognize mentions of events (i.e., event triggers) and their types in text. Recently, several ED datasets in various domains have been proposed. However, the major limitation of these resources is the lack of enough trai
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2cb554fca097d5dbdadc80aafe4bc371
https://doi.org/10.18653/v1/2021.acl-long.490
https://doi.org/10.18653/v1/2021.acl-long.490
Publikováno v:
NUSE@ACL
Current event detection models under super-vised learning settings fail to transfer to newevent types. Few-shot learning has not beenexplored in event detection even though it al-lows a model to perform well with high gener-alization on new event typ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::21c55ee0a14032d7a464250355135e17
Publikováno v:
Advances in Knowledge Discovery and Data Mining ISBN: 9783030474355
PAKDD (2)
PAKDD (2)
The existing event classification (EC) work primarily focuses on the traditional supervised learning setting in which models are unable to extract event mentions of new/unseen event types. Few-shot learning has not been investigated in this area alth
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d74fbc212dcd7343da1051e8e8b9f8d0
https://doi.org/10.1007/978-3-030-47436-2_18
https://doi.org/10.1007/978-3-030-47436-2_18
Autor:
Thien Huu Nguyen, Viet Dac Lai
Publikováno v:
W-NUT@EMNLP
Traditional event detection classifies a word or a phrase in a given sentence for a set of prede- fined event types. The limitation of such pre- defined set is that it prevents the adaptation of the event detection models to new event types. We study
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3447de98b0bb77bac855c9469f52cfde
http://arxiv.org/abs/1910.11368
http://arxiv.org/abs/1910.11368
Publikováno v:
SoICT
Speaker Authentication is the identification of a user from voice biometrics and has a wide range of applications such as banking security, human computer interaction and ambient authentication. In this work, we investigate the effectiveness of acous
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b2922f017481063ce6e7598b1ebdc840
https://doi.org/10.1145/3287921.3287954
https://doi.org/10.1145/3287921.3287954