Research Area: Text Mining, Natural Language Processing　(Mainly in the financial domain, some in agriculture and medicine)

A Member of: IEEE, the Association for Natural Language Processing, the Japanese Society for Artificial Intelligence

2022/10 - :   Studying at Izumi Lab., Department of Systems Innovation, School of Engineering, The University of Tokyo (Ph.D Program)

2022/04 - :   Working at Nikko Asset Management Co., Ltd.

2020/04 - 2022/03 :   Studied at Izumi Lab., Department of Systems Innovation, School of Engineering, The University of Tokyo (Master Program)

2019/05 - 2020/03 :   Researched at Izumi Lab., Faculty of Engineering

2018/04 - 2020/03 :   Studied at Systems Design & Management Course, Department of Systems Innovation, Faculty of Engineering

2016/04 - 2018/03 :   Studied at Natural Sciences I, College of Arts and Sciences (Junior Division)

2015/04 - 2016/03 :   Department of Industrial and Systems Engineering, Faculty of Science and Engineering, Keio University

2009/04 - 2015/03 :   Senior & Junior High School at Komaba, University of Tsukuba

1996/09 :   Born in Tokyo, Japan

• Economy Watchers Survey Dataset (Hugging Face Datasets)
• Japanese DeBERTaV2 Model (base / small)
• Japanese Large Language Model Project
  Japanese datasets and tuning models are available.
  detail (in Japanese)
• ACL anthology Japanese abstract
  Automatic translation of abstracts of articles on ACL anthology into Japanese using ChatGPT.
• Pre-training Language Models for Japanese (github.com/retarfi/language-pretraining)
  Pre-training models for BERT and ELECTRA, using the Japanese Wikipedia and financial domains as corpora. Wikipedia and financial models are available in the Transformers natural language processing library, respectively (huggingface.co/izumi-lab).
• jptranstokenizer: Japanese Tokenzier for transformers (github.com/retarfi/jptranstokenizer)
  Japanese tokenizer compatible with HuggingFace library. Juman++, sudachi and spaCy LUW are available as main-word tokenizers (MeCab is also available). Wordpiece and sentencepiece are available as subword tokenizers. You can load easily a trained tokenizer with Juman++ and sentencepiece.
  PyPI

1. FinDeBERTaV2: Word-Segmentation-Free Pre-trained Language Model for Finance (in Japanese)
   Masahiro Suzuki, Hiroki Sakaji, Masanori Hirano, and Kiyoshi Izumi.
   Transactions of the Japanese Society for Artificial Intelligence, 2024.
   J-STAGE   bib
2. Development and analysis of medical instruction-tuning for Japanese large language models
   Issey Sukeda, Masahiro Suzuki, Hiroki Sakaji, and Satoshi Kodera.
   AIH, 2024.
   AccScience   bib
3. Constructing and analyzing domain-specific language model for financial text mining
   Masahiro Suzuki, Hiroki Sakaji, Masanori Hirano, and Kiyoshi Izumi.
   Information Processing & Management, 2023.
   Impact Factor: 8.6, Q1 Journal as of 2022
   ScienceDirect   paper   detail
4. Forecasting Stock Price Trends by Analyzing Economic Reports With Analyst Profiles
   Masahiro Suzuki, Hiroki Sakaji, Kiyoshi Izumi, and Yasushi Ishikawa.
   Frontiers in Artificial Intelligence, 2022.
   Impact Factor (2022): 4.0
   Frontiers   bib
5. Forecasting Net Income Estimate and Stock Price Using Text Mining from Economic Reports
   Masahiro Suzuki, Hiroki Sakaji, Kiyoshi Izumi, and Yasushi Ishikawa.
   Information, 2020.
   Selected as Cover Story
   MDPI   bib

1. Sentiment-driven Stock Selection in Japan using Language Models
   Masahiro Suzuki, and Hiroki Sakaji.
   2024 IEEE Symposium on Computational Intelligence for Financial Engineering and Economics (CIFEr), 2024.
   Accepted
2. JaFIn: Japanese Financial Instruction Dataset
   Kota Tanabe, Masahiro Suzuki, Hiroki Sakaji, and Itsuki Noda.
   2024 IEEE Symposium on Computational Intelligence for Financial Engineering and Economics (CIFEr), 2024.
   Accepted
   arXiv   bib
3. JMedLoRA:Medical Domain Adaptation on Japanese Large Language Models using Instruction-tuning
   Issey Sukeda, Masahiro Suzuki, Hiroki Sakaji, and Satoshi Kodera.
   Deep Generative Models for Health Workshop NeurIPS 2023, 2023.
   OpenReview   arXiv   bib
4. From Base to Conversational: Japanese Instruction Dataset and Tuning Large Language Models
   Masahiro Suzuki, Masanori Hirano, and Hiroki Sakaji.
   2023 IEEE International Conference on Big Data (Big Data), 2023.
   IEEE   arXiv   SSRN   bib
5. llm-japanese-dataset v0: Construction of Japanese Chat Dataset for Large Language Models and its Methodology
   Masanori Hirano, Masahiro Suzuki, and Hiroki Sakaji.
   The 12th International Workshop on Web Services and Social Media (WSSM-2023) in The 26th International Conference on Network-Based Information Systems (NBiS-2023), 2023.
   Springer Link   arXiv   SSRN   bib
6. Gradual Further Pre-training Architecture for Economics/Finance Domain Adaptation of Language Model
   Hiroki Sakaji, Masahiro Suzuki, Kiyoshi Izumi, and Hiroyuki Mitsugi.
   2022 IEEE International Conference on Big Data (Big Data), 2022.
   IEEE   paper   detail
7. Constructing and analyzing domain-specific language model for financial text mining
   Masahiro Suzuki, Hiroki Sakaji, Masanori Hirano, and Kiyoshi Izumi.
   Information Processing and Management Conference, 2022.
8. Market Trend Analysis Using Polarity Index Generated from Analyst Reports
   Rei Taguchi, Hikaru Watanabe, Masanori Hirano, Masahiro Suzuki, Hiroki Sakaji, Kiyoshi Izumi, and Kenji Hiramatsu.
   2021 IEEE International Conference on Big Data (Big Data), 2021.
   IEEE   bib
9. Stock Price Analysis Using Combination of Analyst Reports and Several Document
   Masahiro Suzuki, Toshiya Katagi, Hiroki Sakaji, Kiyoshi Izumi, and Yasushi Ishikawa.
   2019 International Conference on Data Mining Workshops (ICDMW), 2019.
   Best Paper Award
   IEEE   paper   detail

1. Development of Dialogue System to Induce Reconcilation of Social Values (in Japanese)
   Ryotaro Kobayashi, Takehiro Takayanagi, Masahiro Suzuki, Yukiko Ogura, and Hiroki Sakaji.
   19th Symposium of Young Researcher Association for NLP Studies (YANS), 2024.
2. EWS: the Economic Watcher Survey Datasets and Tasks for the Financial and Economic Domain (in Japanese)
   Masahiro Suzuki, and Hiroki Sakaji.
   IEICE Tech. Rep., 2024.
   IEICE   Jxiv   bib
3. JaFIn: Japanese Financial Instruction Dataset (in Japanese)
   Kota Tanabe, Masahiro Suzuki, Hiroki Sakaji, and Itsuki Noda.
   IEICE Tech. Rep., 2024.
   IEICE   paper   detail
4. Large Language Models in the Financial Domain (in Japanese)
   Kiyoshi Izumi, Yuri Murayama, Masahiro Suzuki, Takehiro Takayanagi, Shota Nakasuji, Ryotaro Kobayashi, and Makishi Yamamoto.
   The Annual Conference of JSAI, 2024.
   confit   bib
5. Stock Selection Attempt using Sentiment of Japan Company Handbook (in Japanese)
   Masahiro Suzuki.
   Proceedings of the Annual Conference of JSAI, 2024.
   J-STAGE   bib
6. Impact Analysis on Stock Prices by Information Propagation in Social Networks using Artificial Market Simulations (in Japanese)
   Miyuki Matsumoto, Hashimoto Ryuji, Masahiro Suzuki, Yuri Murayama, and Kiyoshi Izumi.
   Proceedings of the Annual Conference of JSAI, 2024.
   J-STAGE   bib
7. Development of a Dataset Representing Agricultural Product Prices for Generative AI of Agricultural Extension Specialist. (in Japanese)
   Akio Kobayashi, Hiroki Sakaji, Tetsuo Katsuragi, Shotaro Mori, Akira Hashimoto, Masahiro Suzuki, and Takahiro Kawamura.
   Proceedings of the Annual Conference of JSAI, 2024.
   J-STAGE   bib
8. JMedLoRA: Medical Domain Adaptation on Japanese Large Language Models using Instruction-tuning (in Japanese)
   Issey Sukeda, Masahiro Suzuki, Hiroki Sakaji, and Satoshi Kodera.
   The Thirtieth Annual Meeting of the Association for Natural Language Processing, 2024.
   paper   detail
9. Language Model Construction and Domain Adaptation using Multiple Nodes (in Japanese)
   Masahiro Suzuki, and Hiroki Sakaji.
   Intelligent Computing Systems (ICS), 2024.
   IPSJ   paper   detail
10. LoRA Tuning Conversational Japanese Large Language Models using Japanese Instruction Dataset (in Japanese)
    Masahiro Suzuki, Masanori Hirano, and Hiroki Sakaji.
    IEICE Tech. Rep., 2023.
    IEICE   Jxiv   bib
11. llm-japanese-dataset v0: Construction of Japanese Chat Dataset for Large Language Models (in Japanese)
    Masanori Hirano, Masahiro Suzuki, and Hiroki Sakaji.
    Special Interest Group on Natural Language Processing, Information Processing Society of Japan, 2023.
    Young Research Award (Co-author)
    SIG-NL   Jxiv   bib
12. Construction of Japanese Instruction Dataset and its Application to Tuning of Large-scale Language Models (in Japanese)
    Masahiro Suzuki, Masanori Hirano, and Hiroki Sakaji.
    18th Symposium of Young Researcher Association for NLP Studies (YANS), 2023.
    Honorable Mention Award and ELYZA Award (Sponsor Award)
13. Causal Text Mining in the Era of Large Language Modeling: A Reality Check (in Japanese)
    Takehiro Takayanagi, Ryotaro Kobayashi, Masahiro Suzuki, Hiroki Sakaji, and Kiyoshi Izumi.
    18th Symposium of Young Researcher Association for NLP Studies (YANS), 2023.
14. Proposing task to extract differences from time series financial documents (in Japanese)
    Masahiro Suzuki, Hiroki Sakaji, and Kiyoshi Izumi.
    Proceedings of the Annual Conference of JSAI, 2023.
    J-STAGE   bib
15. Performance Evaluation of Japanese Pre-trained Language Models with Different Word Segmentation Systems (in Japanese)
    Masahiro Suzuki, Hiroki Sakaji, and Kiyoshi Izumi.
    29th Annual Meeting of the Association for Natural Language Processing (NLP), 2023.
    paper   detail
16. Stock Price Trend Forecast using Multiple Timeseries Analyst Reports (in Japanese)
    Masahiro Suzuki, Hiroki Sakaji, Kiyoshi Izumi, and Yasushi Ishikawa.
    Workshop of Social System and Information Technology (WSSIT2022), 2022.
    paper   detail
17. Construction and Validation of a Pre-Training and Additional Pre-Training Financial Language Model (in Japanese)
    Masahiro Suzuki, Hiroki Sakaji, Masanori Hirano, and Kiyoshi Izumi.
    Proceedings of JSAI Special Interest Group on Financial Infomatics (SIG-FIN) 28, 2022.
    paper   detail
18. Construction and Validation of Additional Pre-Training Language Model using Financial Documents (in Japanese)
    Masahiro Suzuki, Hiroki Sakaji, Kiyoshi Izumi, and Yasushi Ishikawa.
    28th Annual Meeting of the Association for Natural Language Processing (NLP), 2022.
    paper   detail
19. Market Trend Analysis Using Polarity Index Generated from Analyst Reports (in Japanese)
    Rei Taguchi, Hikaru Watanabe, Masanori Hirano, Masahiro Suzuki, Hiroki Sakaji, Kiyosho Izumi, and Kenji Hiramatsu.
    Proceedings of JSAI Special Interest Group on Financial Infomatics (SIG-FIN) 27, 2021.
    J-STAGE   SIG-FIN   paper   detail
20. Construction and Validation of a Pre-Trained Language Model Using Financial Documents (in Japanese)
    Masahiro Suzuki, Hiroki Sakaji, Hirano Masanori, and Kiyoshi Izumi.
    Proceedings of JSAI Special Interest Group on Financial Infomatics (SIG-FIN) 27, 2021.
    J-STAGE   SIG-FIN   paper   detail
21. Performance Validation of Pre-Trained BERT in the Financial Domain (in Japanese)
    Masahiro Suzuki, Hiroki Sakaji, Hirano Masanori, and Kiyoshi Izumi.
    IEICE Tech. Rep., 2021.
    IEICE   paper   detail
22. Construction of Japanese Instruction Dataset and its Application to Tuning of Large-scale Language Models (in Japanese)
    Masahiro Suzuki, Hiroki Sakaji, Hirano Masanori, and Kiyoshi Izumi.
    16th Symposium of Young Researcher Association for NLP Studies (YANS), 2021.
23. Stock Price Movement Forecast from Analyst Reports by Text Mining (in Japanese)
    Masahiro Suzuki, Toshiya Katagi, Hiroki Sakaji, Kiyoshi Izumi, and Yasushi Ishikawa.
    26th Annual Meeting of the Association for Natural Language Processing (NLP), 2020.
    paper   detail
24. Net Income Forecast from Analyst Reports by Text Mining (in Japanese)
    Masahiro Suzuki, Hiroki Sakaji, Kiyoshi Izumi, Hiroyasu Matsushima, and Yasushi Ishikawa.
    Proceedings of the Annual Conference of JSAI, 2020.
    JSTAGE   bib

1. Interactive DualChecker for Mitigating Hallucinations in Distilling Large Language Models
   Meiyun Wang, Masahiro Suzuki, Hiroki Sakaji, and Kiyoshi Izumi.
   arXiv   bib
2. Economy Watchers Survey provides Datasets and Tasks for Japanese Financial Domain
   Masahiro Suzuki, and Hiroki Sakaji.
   arXiv   bib
3. Is ChatGPT the Future of Causal Text Mining? A Comprehensive Evaluation and Analysis
   Takehiro Takayanagi, Masahiro Suzuki, Ryotaro Kobayashi, Hiroki Sakaji, and Kiyoshi Izumi.
   arXiv   bib

Scholarship

• 2020/04 :   TOYOTA/Dwango AI Scholarship (1 year: 1,200,000 yen / Approx. 11,000 USD)
• 2020/04 :   JEES / SoftBank AI Human Resources Development Scholarship (1 year: 1,000,000 yen / Approx. 9,000 USD)

Awards

• 2024/02 :   Best Paper Award, Natural Language Understanding and Models of Communication Research Group (NLC)
  NLC Research Award 2023 Recipients (in Japanese)
• 2024/02 :   Most Innovative Application of Artificial Intelligence in Japan, Asia Asset Management 2024 Best of the Best Awards
  Nikko Asset Management Co., Ltd.
  Press Release   Asia Asset Management Best of the Best Awards
• 2023/09 :   Young Research Award (Co-author), Special Interest Group on Natural Language Processing (SIG-NL) Information Processing Society of Japan (IPSJ)
  SIG-NL Young Research Award (in Japanese)
• 2023/08 :   Honorable Mention Award, 18th Symposium of Young Researcher Association for NLP Studies (Yans)
  YANS Award (in Japanese)
• 2023/08 :   ELYZA Award (Sponsor Award), 18th Symposium of Young Researcher Association for NLP Studies (Yans)
  YANS Award (in Japanese)
• 2019/11 :   Best Paper Award in the 2nd International Workshop on Cross-disciplinary Data Exchange and Collaboration (CDEC)
  CDEC HP / Introduction article of Faculty of Engineering, University of Tokyo / Introduction article of Department of Systems Innovation, Graduate School of Engineering, University of Tokyo

• 2024/04-: The Association for Natural Language Processing, Steering committee member of the Young Researcher Association for NLP Studies (YANS)

• The University of Tokyo Golf Team website 2018 production