Masaru Isonuma

Masaru Isonuma

Auto-generated profile, based on publicly available information

Masaru Isonuma

The University of Tokyo

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 September 2021 in Transactions of the Association for Computational Linguistics
Verified
Journal Article
Open access
PDF file
MIMasaru Isonuma
Masaru Isonuma
JMJunichiro Mori
Junichiro Mori
DBDanushka Bollegala
Danushka Bollegala
ISIchiro Sakata
Ichiro Sakata
This paper presents a novel unsupervised abstractive summarization method for opinionated texts. While the basic variational autoencoder-based models assume a unimodal Gaussian prior for the latent code of sentences, we alternate it with a recursive Gaussian mixture, where each mixture component corresponds to the latent code of a topic sentence and is mixed by a tree-structured topic distribution. By decoding each Gaussian component, we generate sentences with tree-structured topic guidance, where the root sentence conveys generic content, and the leaf sentences describe specific topics. Experimental results demonstrate that the generated topic sentences are appropriate as a summary of opinionated texts, which are more informative and cover more input contents than those generated by the recent unsupervised summarization model (Bražinskas et al., 2020). Furthermore, we demonstrate that the variance of latent Gaussians represents the granularity of sentences, analogous to Gaussian word embedding (Vilnis and McCallum, 2015).

1 January 2022
Verified
Conference Paper
Open access
PDF file
NSNaomi Sato
Naomi Sato
MIMasaru Isonuma
Masaru Isonuma
KAKimitaka Asatani
Kimitaka Asatani
SIShoya Ishizuka
Shoya Ishizuka
ASAori Shimizu
Aori Shimizu
ISIchiro Sakata
Ichiro Sakata
Naomi Sato, Masaru Isonuma, Kimitaka Asatani, Shoya Ishizuka, Aori Shimizu, Ichiro Sakata. Findings of the Association for Computational Linguistics: EMNLP 2022. 2022.

1 January 2023
Verified
Conference Paper
Open access
PDF file
MIMasaru Isonuma
Masaru Isonuma
JMJunichiro Mori
Junichiro Mori
ISIchiro Sakata
Ichiro Sakata
Masaru Isonuma, Junichiro Mori, Ichiro Sakata. Findings of the Association for Computational Linguistics: ACL 2023. 2023.