Generating Formality-Tuned Summaries Using Input-Dependent Rewards (bibtex)
by Chawla, Kushal, Srinivasan, Balaji Vasan and Chhaya, Niyati
Abstract:
Abstractive text summarization aims at generating human-like summaries by understanding and paraphrasing the given input content. Recent efforts based on sequence-to-sequence networks only allow the generation of a single summary. However, it is often desirable to accommodate the psycho-linguistic preferences of the intended audience while generating the summaries. In this work, we present a reinforcement learning based approach to generate formality-tailored summaries for an input article. Our novel input-dependent reward function aids in training the model with stylistic feedback on sampled and ground-truth summaries together. Once trained, the same model can generate formal and informal summary variants. Our automated and qualitative evaluations show the viability of the proposed framework.
Reference:
Generating Formality-Tuned Summaries Using Input-Dependent Rewards (Chawla, Kushal, Srinivasan, Balaji Vasan and Chhaya, Niyati), In Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), Association for Computational Linguistics, 2019.
Bibtex Entry:
@inproceedings{chawla_generating_2019,
	address = {Hong Kong, China},
	title = {Generating {Formality}-{Tuned} {Summaries} {Using} {Input}-{Dependent} {Rewards}},
	url = {https://www.aclweb.org/anthology/K19-1078},
	doi = {10.18653/v1/K19-1078},
	abstract = {Abstractive text summarization aims at generating human-like summaries by understanding and paraphrasing the given input content. Recent efforts based on sequence-to-sequence networks only allow the generation of a single summary. However, it is often desirable to accommodate the psycho-linguistic preferences of the intended audience while generating the summaries. In this work, we present a reinforcement learning based approach to generate formality-tailored summaries for an input article. Our novel input-dependent reward function aids in training the model with stylistic feedback on sampled and ground-truth summaries together. Once trained, the same model can generate formal and informal summary variants. Our automated and qualitative evaluations show the viability of the proposed framework.},
	booktitle = {Proceedings of the 23rd {Conference} on {Computational} {Natural} {Language} {Learning} ({CoNLL})},
	publisher = {Association for Computational Linguistics},
	author = {Chawla, Kushal and Srinivasan, Balaji Vasan and Chhaya, Niyati},
	month = nov,
	year = {2019},
	keywords = {ARO-Coop, Virtual Humans},
	pages = {833--842}
}
Powered by bibtexbrowser