Extractive Summarization Using Multi-Task Learning with Document Classification

no code implementations • EMNLP 2017 • Masaru Isonuma, Toru Fujino, Junichiro Mori, Yutaka Matsuo, Ichiro Sakata

The need for automatic document summarization that can be used for practical applications is increasing rapidly.

Classification Document Classification +5

Unsupervised Neural Single-Document Summarization of Reviews via Learning Latent Discourse Structure and its Ranking

1 code implementation • ACL 2019 • Masaru Isonuma, Junichiro Mori, Ichiro Sakata

This paper focuses on the end-to-end abstractive summarization of a single product review without supervision.

Abstractive Text Summarization Document Summarization +1

Tree-Structured Neural Topic Model

no code implementations • ACL 2020 • Masaru Isonuma, Junichiro Mori, Danushka Bollegala, Ichiro Sakata

This paper presents a tree-structured neural topic model, which has a topic distribution over a tree with an infinite number of branches.

Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance

1 code implementation • 15 Jun 2021 • Masaru Isonuma, Junichiro Mori, Danushka Bollegala, Ichiro Sakata

This paper presents a novel unsupervised abstractive summarization method for opinionated texts.

Abstractive Text Summarization Opinion Summarization +1

SciReviewGen: A Large-scale Dataset for Automatic Literature Review Generation

1 code implementation • 24 May 2023 • Tetsu Kasanishi, Masaru Isonuma, Junichiro Mori, Ichiro Sakata

Automatic literature review generation is one of the most challenging tasks in natural language processing.

Review Generation

Differentiable Instruction Optimization for Cross-Task Generalization

1 code implementation • 16 Jun 2023 • Masaru Isonuma, Junichiro Mori, Ichiro Sakata

Instruction tuning has been attracting much attention to achieve generalization ability across a wide variety of tasks.

Bilevel Optimization