NaCTeM

NEDO-AIRC

Project Description

NaCTeM is collaborating with the New Energy and Industrial Technology Development Organization (NEDO), Japan and the Artificial Intelligence Research Center (AIRC), Japan, to increase the accessibility of AI technology. Specific projects have included:

  • Realization of a Smart Society by Applying Artificial Intelligence Technologies, which concerns the conduct of research and development to promote the social implementation of artificial intelligence technologies in the three high-focus areas of the strategy of artificial intelligence technologies of productivity; health, medical care, and welfare; and mobility.This project specifically concentrates on research, development, and demonstration for the realization of a smart society combining cyber- and physical space with the use of artificial intelligence modules and data-acquisition sensor technologies that have been researched, developed, and deployed so far, and also applying research and development infrastructures.
  • Technology Development Project on Next-Generation Artificial Intelligence Evolving Together With Humans, which aims to transform AI technlogies from strangers into "friends", who understand and trust each other inside and out. To achieve this goal, AI will be made more accessible technology by, firstly, improving the explanatory nature of AI output, secondly, clarifying the concept of quality assurance for AI systems, and thirdly, making AI systems easily constructable without the need to collect large amounts of data. The overall aim is to build an AI system in which humans and AI interact to grow and evolve together.

Publications

Liu, Z., Liu, B, Thompson, P., Yang, K and Ananiadou, S. (In Press).ConspEmoLLM: Conspiracy Theory Detection Using an Emotion-Based Large Language Model. Proceedings of the 13th International Conference on Prestigious Applications of Intelligent Systems (PAIS-2024)

Liu, Z., Yang, K, Zhang, T., Xie, Q., Yu, Z. and Ananiadou, S. (In Press). EmoLLMs: A Series of Emotional Large Language Models and Annotation Tools for Comprehensive Affective Analysis. Proceedings of KDD 2024.

Bishop, J., Xie, Q. and Ananiadou, S. (2024). LongDocFACTScore: Evaluating the Factuality of Long Document Abstractive Summarisation. Proceedings of LREC-COLING 2024, pages 10777-10789.

Liu, Z., Zhang, T., Yang, K, Thompson, P., Yu, Z. and Ananiadou, S. (2024) Emotion detection for misinformation: A review. Information Fusion, 107(102300)

Yang, K, Zhang, T., Kuang, Z., Xie, Q., Huang, J. and Ananiadou, S. (2024) MentaLLaMA: Interpretable Mental Health Analysis on Social Media with Large Language Models Proceedings of WWW 2024, pages 4489-4500.

Yuan, C., Xie, Q. and Ananiadou, S. (2024). Temporal relation extraction with contrastive prototypical sampling. Knowledge-based Systems, 286(111410).

Yuan, C., Xie, Q., Huang, J. and Ananiadou, S. (2024). Back to the Future: Towards Explainable Temporal Reasoning with Large Language Models, Proceedings WWW 2024, pages 1963 - 1974.

Zhang, T., Yang, K, Ji, S., Liu, B, Xie, Q. and Ananiadou, S. (2024). SuicidEmoji: Derived Emoji Dataset and Tasks for Suicide-Related Social Content. Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 24), pages 1136 - 1141.

Liu, B, Schlegel, V., Batista-Navarro, R. and Ananiadou, S. (2023). Argument mining as a multi-hop generative machine reading comprehension task. Findings of the Association for Computational Linguistics: EMNLP 2023, pages 10846-10858.

Yang, K, Ji, S., Zhang, T., Xie, Q., Kuang, Z. and Ananiadou, S. (2023) Towards Interpretable Mental Health Analysis with Large Language Models. Proceedings of EMNLP 2023, pages 6056-6077.

Yang, K, Zhang, T. and Ananiadou, S. (2023). A Bipartite Graph is All We Need for Enhancing Emotional Reasoning with Commonsense Knowledge. Proceedings of CIKM 2023, pages 2917-2927.

Yang, K, Zhang, T. and Ananiadou, S. (2023). Disentangled Variational Autoencoder for Emotion Recognition in Conversations. IEEE Transactions on Affective Computing, 1-12.

Yuan, C., Xie, Q. and Ananiadou, S. (2023). Zero-shot Temporal Relation Extraction with ChatGPT. Proceedings of BioNLP 2023, pages 92-102

Zhang, T., Yang, K, Alhuzali, H., Liu, B and Ananiadou, S. (2023) PHQ-aware depressive symptoms identification with similarity contrastive learning on social media. Information Processing & Management, 60:5(103417).

Zhang, T., Yang, K and Ananiadou, S (2023). Sentiment-guided Transformer with Severity-aware Contrastive Learning for Depression Detection on Social Media. Proceedings of BioNLP 2023, pages 114-126.