TY - GEN
T1 - Constraint-embedded paraphrase generation for commercial tweets
AU - Cui, Renhao
AU - Agrawal, Gagan
AU - Ramnath, Rajiv
N1 - Publisher Copyright:
© 2021 ACM.
PY - 2021/11/8
Y1 - 2021/11/8
N2 - Automated generation of commercial tweets has become a useful and important tool in the use of social media for marketing and advertising. In this context, paraphrase generation has emerged as an important problem. This type of paraphrase generation has the unique requirement of requiring certain elements to be kept in the result, such as the product name or the promotion details. To address this need, we propose a Constraint-Embedded Language Modeling (CELM) framework, in which hard constraints are embedded in the text content and learned through a language model. This embedding helps the model learn not only paraphrase generation but also constraints in the content of the paraphrase specific to commercial tweets. In addition, we apply knowledge learned from a general domain to the generation task of commercial tweets. Our model is shown to outperform general paraphrase generation models as well as the state-of-the-art CopyNet model, in terms of paraphrase similarity, diversity, and the ability to conform to hard constraints.
AB - Automated generation of commercial tweets has become a useful and important tool in the use of social media for marketing and advertising. In this context, paraphrase generation has emerged as an important problem. This type of paraphrase generation has the unique requirement of requiring certain elements to be kept in the result, such as the product name or the promotion details. To address this need, we propose a Constraint-Embedded Language Modeling (CELM) framework, in which hard constraints are embedded in the text content and learned through a language model. This embedding helps the model learn not only paraphrase generation but also constraints in the content of the paraphrase specific to commercial tweets. In addition, we apply knowledge learned from a general domain to the generation task of commercial tweets. Our model is shown to outperform general paraphrase generation models as well as the state-of-the-art CopyNet model, in terms of paraphrase similarity, diversity, and the ability to conform to hard constraints.
UR - http://www.scopus.com/inward/record.url?scp=85124383367&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85124383367&partnerID=8YFLogxK
U2 - 10.1145/3487351.3490974
DO - 10.1145/3487351.3490974
M3 - Conference contribution
AN - SCOPUS:85124383367
T3 - Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021
SP - 369
EP - 376
BT - Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021
A2 - Coscia, Michele
A2 - Cuzzocrea, Alfredo
A2 - Shu, Kai
PB - Association for Computing Machinery, Inc
T2 - 13th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021
Y2 - 8 November 2021
ER -