TY - GEN
T1 - XLTime
T2 - 2022 Findings of the Association for Computational Linguistics: NAACL 2022
AU - Cao, Yuwei
AU - Groves, William
AU - Saha, Tanay Kumar
AU - Tetreault, Joel R.
AU - Jaimes, Alex
AU - Peng, Hao
AU - Yu, Philip S.
N1 - Publisher Copyright:
© Findings of the Association for Computational Linguistics: NAACL 2022 - Findings.
PY - 2022
Y1 - 2022
N2 - Temporal Expression Extraction (TEE) is essential for understanding time in natural language. It has applications in Natural Language Processing (NLP) tasks such as question answering, information retrieval, and causal inference. To date, work in this area has mostly focused on English as there is a scarcity of labeled data for other languages. We propose XLTime, a novel framework for multilingual TEE. XLTime works on top of pre-trained language models and leverages multi-task learning to prompt cross-language knowledge transfer both from English and within the non-English languages. XLTime alleviates problems caused by a shortage of data in the target language. We apply XLTime with different language models and show that it outperforms the previous automatic SOTA methods on French, Spanish, Portuguese, and Basque, by large margins. XLTime also closes the gap considerably on the handcrafted HeidelTime method.
AB - Temporal Expression Extraction (TEE) is essential for understanding time in natural language. It has applications in Natural Language Processing (NLP) tasks such as question answering, information retrieval, and causal inference. To date, work in this area has mostly focused on English as there is a scarcity of labeled data for other languages. We propose XLTime, a novel framework for multilingual TEE. XLTime works on top of pre-trained language models and leverages multi-task learning to prompt cross-language knowledge transfer both from English and within the non-English languages. XLTime alleviates problems caused by a shortage of data in the target language. We apply XLTime with different language models and show that it outperforms the previous automatic SOTA methods on French, Spanish, Portuguese, and Basque, by large margins. XLTime also closes the gap considerably on the handcrafted HeidelTime method.
UR - https://www.scopus.com/pages/publications/85137340829
U2 - 10.18653/v1/2022.findings-naacl.148
DO - 10.18653/v1/2022.findings-naacl.148
M3 - 会议稿件
AN - SCOPUS:85137340829
T3 - Findings of the Association for Computational Linguistics: NAACL 2022 - Findings
SP - 1931
EP - 1942
BT - Findings of the Association for Computational Linguistics
PB - Association for Computational Linguistics (ACL)
Y2 - 10 July 2022 through 15 July 2022
ER -