Junichiro Mori
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Junichiro Mori has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
Ichiro Sakata
The University of Tokyo
3 shared publicationsMasaru Isonuma
The University of Tokyo
3 shared publications- Ichiro Sakata
The University of Tokyo
2 shared publications - Danushka Bollegala
Department of Computer Science, University of Liverpool, Liverpool, United Kingdom
1 shared publication - Hiromi Arai
École de Technologie Supérieure RIKEN Center for Advanced Intelligence Project Université du Québec à Montréal Osaka University Université du Québec à Montréal
1 shared publication - Hisashi Kashima
Kyoto University, Kyoto, Japan
1 shared publication
Latest Publications
- Open Access
- 12 October 2024
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 57 (12) , 1-45
Trustworthy human computation: a survey
Human computation is an approach to solving problems that prove difficult using AI only, and involves the cooperation of many humans. Because human computation requires close engagement with both “human populations as users” and “human populations as driving forces,” establishing mutual trust between AI and humans is an important issue to further the development of human computation. This survey lays the groundwork for the realization of trustworthy human computation. First, the trustworthiness of human computation as computing systems, that is, trust offered by humans to AI, is examined using the RAS (reliability, availability, and serviceability) analogy, which define measures of trustworthiness in conventional computer systems. Next, the social trustworthiness provided by human computation systems to users or participants is discussed from the perspective of AI ethics, including fairness, privacy, and transparency. Then, we consider human–AI collaboration based on two-way trust, in which humans and AI build mutual trust and accomplish difficult tasks through reciprocal collaboration. Finally, future challenges and research directions for realizing trustworthy human computation are discussed.
- 12 October 2024
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 57 (12) , 1-45
Open AccessTrustworthy human computation: a survey
Human computation is an approach to solving problems that prove difficult using AI only, and involves the cooperation of many humans. Because human computation requires close engagement with both “human populations as users” and “human populations as driving forces,” establishing mutual trust between AI and humans is an important issue to further the development of human computation. This survey lays the groundwork for the realization of trustworthy human computation. First, the trustworthiness of human computation as computing systems, that is, trust offered by humans to AI, is examined using the RAS (reliability, availability, and serviceability) analogy, which define measures of trustworthiness in conventional computer systems. Next, the social trustworthiness provided by human computation systems to users or participants is discussed from the perspective of AI ethics, including fairness, privacy, and transparency. Then, we consider human–AI collaboration based on two-way trust, in which humans and AI build mutual trust and accomplish difficult tasks through reciprocal collaboration. Finally, future challenges and research directions for realizing trustworthy human computation are discussed.
- Open Access
Differentiable Instruction Optimization for Cross-Task Generalization
Instruction tuning has been attracting much attention to achieve generalization ability across a wide variety of tasks. Although various types of instructions have been manually created for instruction tuning, it is still unclear what kind of instruction is optimal to obtain cross-task generalization ability. This work presents instruction optimization, which optimizes training instructions with respect to generalization ability. Rather than manually tuning instructions, we introduce learnable instructions and optimize them with gradient descent by leveraging bilevel optimization. Experimental results show that the learned instruction enhances the diversity of instructions and improves the generalization ability compared to using only manually created instructions.
Open AccessDifferentiable Instruction Optimization for Cross-Task Generalization
Instruction tuning has been attracting much attention to achieve generalization ability across a wide variety of tasks. Although various types of instructions have been manually created for instruction tuning, it is still unclear what kind of instruction is optimal to obtain cross-task generalization ability. This work presents instruction optimization, which optimizes training instructions with respect to generalization ability. Rather than manually tuning instructions, we introduce learnable instructions and optimize them with gradient descent by leveraging bilevel optimization. Experimental results show that the learned instruction enhances the diversity of instructions and improves the generalization ability compared to using only manually created instructions.
- Open Access
SciReviewGen: A Large-scale Dataset for Automatic Literature Review Generation
Automatic literature review generation is one of the most challenging tasks in natural language processing. Although large language models have tackled literature review generation, the absence of large-scale datasets has been a stumbling block to the progress. We release SciReviewGen, consisting of over 10,000 literature reviews and 690,000 papers cited in the reviews. Based on the dataset, we evaluate recent transformer-based summarization models on the literature review generation task, including Fusion-in-Decoder extended for literature review generation. Human evaluation results show that some machine-generated summaries are comparable to human-written reviews, while revealing the challenges of automatic literature review generation such as hallucinations and a lack of detailed information. Our dataset and code are available at https://github.com/tetsu9923/SciReviewGen.
Open AccessSciReviewGen: A Large-scale Dataset for Automatic Literature Review Generation
Automatic literature review generation is one of the most challenging tasks in natural language processing. Although large language models have tackled literature review generation, the absence of large-scale datasets has been a stumbling block to the progress. We release SciReviewGen, consisting of over 10,000 literature reviews and 690,000 papers cited in the reviews. Based on the dataset, we evaluate recent transformer-based summarization models on the literature review generation task, including Fusion-in-Decoder extended for literature review generation. Human evaluation results show that some machine-generated summaries are comparable to human-written reviews, while revealing the challenges of automatic literature review generation such as hallucinations and a lack of detailed information. Our dataset and code are available at https://github.com/tetsu9923/SciReviewGen.
- Open Access
- 8 September 2021
- Published by MIT Press in Transactions of the Association for Computational Linguistics
- Vol. 9, 945-961
Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance
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).
- 8 September 2021
- Published by MIT Press in Transactions of the Association for Computational Linguistics
- Vol. 9, 945-961
Open AccessUnsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance
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).
- 4 February 2020
- Published by Springer Nature in Advances in Intelligent Systems and Computing
- p. 3-13
Using Sequence Constraints for Modelling Network Interactions
- 4 February 2020
- Published by Springer Nature in Advances in Intelligent Systems and Computing
- p. 3-13
Using Sequence Constraints for Modelling Network Interactions
- Open Access
Unsupervised Neural Single-Document Summarization of Reviews via Learning Latent Discourse Structure and its Ranking
This paper focuses on the end-to-end abstractive summarization of a single product review without supervision. We assume that a review can be described as a discourse tree, in which the summary is the root, and the child sentences explain their parent in detail. By recursively estimating a parent from its children, our model learns the latent discourse tree without an external parser and generates a concise summary. We also introduce an architecture that ranks the importance of each sentence on the tree to support summary generation focusing on the main review point. The experimental results demonstrate that our model is competitive with or outperforms other unsupervised approaches. In particular, for relatively long reviews, it achieves a competitive or better performance than supervised models. The induced tree shows that the child sentences provide additional information about their parent, and the generated summary abstracts the entire review.
Open AccessUnsupervised Neural Single-Document Summarization of Reviews via Learning Latent Discourse Structure and its Ranking
This paper focuses on the end-to-end abstractive summarization of a single product review without supervision. We assume that a review can be described as a discourse tree, in which the summary is the root, and the child sentences explain their parent in detail. By recursively estimating a parent from its children, our model learns the latent discourse tree without an external parser and generates a concise summary. We also introduce an architecture that ranks the importance of each sentence on the tree to support summary generation focusing on the main review point. The experimental results demonstrate that our model is competitive with or outperforms other unsupervised approaches. In particular, for relatively long reviews, it achieves a competitive or better performance than supervised models. The induced tree shows that the child sentences provide additional information about their parent, and the generated summary abstracts the entire review.
- Open Access
- 29 October 2018
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 7 (11) , 416
Measurement of Opportunity Cost of Travel Time for Predicting Future Residential Mobility Based on the Smart Card Data of Public Transportation
This study attempts to investigate a method for creating an index from mobility data that not only correlates with the number of people who relocate to a place, but also has causal influence on the number of such individuals. By creating an index based on human mobility data, it becomes possible to predict the influence of urban development on future residential movements. In this paper, we propose a method called the travel cost method for multiple places (TCM4MP) by extending the conventional travel cost method (TCM). We assume that the opportunity cost of travel time on non-working days reflects the convenience and amenities of a neighborhood. However, conventional TCM does not assume that the opportunity cost of travel time varies according to the departure place. In this paper, TCM4MP is proposed to estimate the opportunity cost of travel time with respect to the departure place. We consider such estimation to be possible due to the use of massive mobility data. We assume that the opportunity cost of travel time on non-working days reflects the convenience and amenities of the neighborhood. Therefore, we consider that the opportunity cost of travel time has a causal influence on future residential mobility. In this paper, the validity of the proposed method is tested using the smart card data of public transportation in Western Japan. Our proposed method is beneficial for urban planners in estimating the effects of urban development and detecting the shrinkage and growth of a population.
- 29 October 2018
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 7 (11) , 416
Open AccessMeasurement of Opportunity Cost of Travel Time for Predicting Future Residential Mobility Based on the Smart Card Data of Public Transportation
This study attempts to investigate a method for creating an index from mobility data that not only correlates with the number of people who relocate to a place, but also has causal influence on the number of such individuals. By creating an index based on human mobility data, it becomes possible to predict the influence of urban development on future residential movements. In this paper, we propose a method called the travel cost method for multiple places (TCM4MP) by extending the conventional travel cost method (TCM). We assume that the opportunity cost of travel time on non-working days reflects the convenience and amenities of a neighborhood. However, conventional TCM does not assume that the opportunity cost of travel time varies according to the departure place. In this paper, TCM4MP is proposed to estimate the opportunity cost of travel time with respect to the departure place. We consider such estimation to be possible due to the use of massive mobility data. We assume that the opportunity cost of travel time on non-working days reflects the convenience and amenities of the neighborhood. Therefore, we consider that the opportunity cost of travel time has a causal influence on future residential mobility. In this paper, the validity of the proposed method is tested using the smart card data of public transportation in Western Japan. Our proposed method is beneficial for urban planners in estimating the effects of urban development and detecting the shrinkage and growth of a population.