TY - GEN
T1 - Conditional Sentence Rephrasing without Parallel Training Corpus
AU - Lee, Yen Ting
AU - Li, Cheng Te
AU - Lin, Shou De
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - This paper aims to rephrase a sentence with a given condition, and the generated sentence should be similar to the origin sentence and satisfy the given condition without parallel training corpus. We propose a conditional sentence VAE (CS-VAE) model to solve the task. CS-VAE is trained as an autoencoder, along with the condition control on the generated sentence with the same semantics. With the experimental demonstration supported, CS-VAE is proven to effectively solve the task with high-quality sentences.
AB - This paper aims to rephrase a sentence with a given condition, and the generated sentence should be similar to the origin sentence and satisfy the given condition without parallel training corpus. We propose a conditional sentence VAE (CS-VAE) model to solve the task. CS-VAE is trained as an autoencoder, along with the condition control on the generated sentence with the same semantics. With the experimental demonstration supported, CS-VAE is proven to effectively solve the task with high-quality sentences.
UR - http://www.scopus.com/inward/record.url?scp=85138041275&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85138041275&partnerID=8YFLogxK
U2 - 10.1109/ICMEW56448.2022.9859385
DO - 10.1109/ICMEW56448.2022.9859385
M3 - Conference contribution
AN - SCOPUS:85138041275
T3 - ICMEW 2022 - IEEE International Conference on Multimedia and Expo Workshops 2022, Proceedings
BT - ICMEW 2022 - IEEE International Conference on Multimedia and Expo Workshops 2022, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2022
Y2 - 18 July 2022 through 22 July 2022
ER -