TY - GEN
T1 - Controllable Abstractive Summarization Using Multilingual Pretrained Language Model
AU - Sugiri,
AU - Prasojo, Radityo Eko
AU - Krisnadhi, Adila Alfa
N1 - Funding Information:
ACKNOWLEDGMENT This research is supported by Tokopedia-UI AI Center, Faculty of Computer Science Universitas Indonesia, and Program Kompetisi Kampus Merdeka from Ministry of Education, Culture, Research, and Technology Republic of Indonesia.
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - By leveraging a multilingual language model, we show that CTRLSum [1], an abstractive summarization approach that can be controlled by keywords, improves baseline summarization system in four languages: English, Indonesian, Spanish, and French by 1.57 in terms of average ROUGE-1, with the Indonesian model achieving state-of-the-art results. We further provide novel analysis about the importance of keywords fed to CTRLSum which (1) shows hypothetical upper-bound results that outperform the state-of-the-art in all four languages by a large margin and (2) provides natural direction for future work to improve CTRLSum by improving the keyword prediction model.
AB - By leveraging a multilingual language model, we show that CTRLSum [1], an abstractive summarization approach that can be controlled by keywords, improves baseline summarization system in four languages: English, Indonesian, Spanish, and French by 1.57 in terms of average ROUGE-1, with the Indonesian model achieving state-of-the-art results. We further provide novel analysis about the importance of keywords fed to CTRLSum which (1) shows hypothetical upper-bound results that outperform the state-of-the-art in all four languages by a large margin and (2) provides natural direction for future work to improve CTRLSum by improving the keyword prediction model.
KW - controllable abstractive summarization
KW - keyword
KW - multilingual
UR - http://www.scopus.com/inward/record.url?scp=85141638996&partnerID=8YFLogxK
U2 - 10.1109/ICoICT55009.2022.9914846
DO - 10.1109/ICoICT55009.2022.9914846
M3 - Conference contribution
AN - SCOPUS:85141638996
T3 - 2022 10th International Conference on Information and Communication Technology, ICoICT 2022
SP - 228
EP - 233
BT - 2022 10th International Conference on Information and Communication Technology, ICoICT 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 10th International Conference on Information and Communication Technology, ICoICT 2022
Y2 - 2 August 2022 through 3 August 2022
ER -