ダウンロード数: 48

このアイテムのファイル:
ファイル 記述 サイズフォーマット 
ACCESS.2023.3308916.pdf1.72 MBAdobe PDF見る/開く
タイトル: Japanese Event Factuality Analysis in the Era of BERT
著者: Kameko, Hirotaka  kyouindb  KAKEN_id  orcid https://orcid.org/0000-0001-9844-6198 (unconfirmed)
Murawaki, Yugo  kyouindb  KAKEN_id  orcid https://orcid.org/0000-0002-0863-1507 (unconfirmed)
Matsuyoshi, Suguru
Mori, Shinsuke  kyouindb  KAKEN_id
著者名の別形: 亀甲, 博貴
村脇, 有吾
森, 信介
キーワード: Task analysis
Multitasking
Tagging
Annotations
Training data
Online services
Neural networks
Event detection
Labeling
Sequential analysis
Event factuality
modality
sequence labeling
neural networks
multi-task learning
発行日: 2023
出版者: Institute of Electrical and Electronics Engineers (IEEE)
誌名: IEEE Access
巻: 11
開始ページ: 93286
終了ページ: 93292
抄録: Recognizing event factuality is a crucial factor for understanding and generating texts with abundant references to possible and counterfactual events. Because event factuality is signaled by modality expressions, identifying modality expression is also an important task. The question then is how to solve these interconnected tasks. On the one hand, while neural networks facilitate multi-task learning by means of parameter sharing among related tasks, the recently introduced pre-training/fine-tuning paradigm might be powerful enough for the model to be able to learn one task without indirect signals from another. On the other hand, ever-increasing model sizes make it practically difficult to run multiple task-specific fine-tuned models at inference time so that parameter sharing can be seen as an effective way to reduce the model’s size. Through experiments, we found: (1) BERT-CRF outperformed non-neural models and BiLSTM-CRF; (2) BERT-CRF did neither benefit from nor was negatively impacted by multi-task learning, indicating the practical viability of BERT-CRF combined with multi-task learning.
著作権等: This work is licensed under a Creative Commons Attribution 4.0 License.
URI: http://hdl.handle.net/2433/285524
DOI(出版社版): 10.1109/ACCESS.2023.3308916
出現コレクション:学術雑誌掲載論文等

アイテムの詳細レコードを表示する

Export to RefWorks


出力フォーマット 


このアイテムは次のライセンスが設定されています: クリエイティブ・コモンズ・ライセンス Creative Commons