Welcome to NLPFin Group!
The Natural Language Processing in Finance Group (NLPFin) is led by Dr. Chung-Chi Chen. Our main research lies on the intersection of Natural Language Processing and Finance. We aim to improve the unstructured data understanding and generation in the financial field and further adopt the results in FinTech applications.
Recruitment
NLPFin Group is now recruiting interns, research assistants, and postdocs who are interested in applying NLP in financial and legal documents. Below are some of the topics we are recently interested in, and the research is included but is not limited to these directions. Our members can work in the office of either NLP Lab, National Taiwan University, Taiwan, or Artificial Intelligence Research Center (AIRC), AIST, Japan. Remote work from abroad is also acceptable. Please contact Chung-Chi Chen by emailing c.c.chen@acm.org if you are interested in.
FinTechGroup Members
Ongoing Collaboration
Former Members
Yu-Min Tseng (National Taiwan University)DynamicESG: A Dataset for Dynamically Unearthing ESG Ratings from News Articles. In Proceedings of The 32nd ACM International Conference on Information and Knowledge Management (CIKM'23). pdf resource
Are Expert-Level Language Models Expert-Level Annotators? arXiv
Hon Hai Technology Award
Hsiu-Hung Lee (National Yang Ming Chiao Tung University, Taiwan)
RAG-Enhanced Evidence Recommendation in Financial Legal Resolutions. In Companion Proceedings of the Web Conference 2025 (WWW'25).
Chin-Yi Lin (National Taiwan University)
Argument-Based Sentiment Analysis on Forward-Looking Statements. In Findings of the Association for Computational Linguistics: ACL 2024. pdf
Yi-Ning Juan (National Taiwan University)
Co-Trained Retriever-Generator Framework for Question Generation in Earnings Calls. In Companion Proceedings of the Web Conference 2025 (WWW'25). pdf
Generating Multiple Questions from Presentation Transcripts: A Pilot Study on Earnings Conference Calls. In Proceedings of the 16th International Conference on Natural Language Generation (INLG'23). pdf
CustodiAI: A System for Predicting Child Custody Outcomes. In Proceedings of The 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: System Demonstrations (IJCNLP-AACL'23). pdf
Tomas Goldsack (University of Sheffield - AIST Intern)
From Facts to Insights: A Study on the Generation and Evaluation of Analytical Reports for Deciphering Earnings Calls. Proceedings of the 31st International Conference on Computational Linguistics (COLING-2025). pdf
Sin-Han Yang (National Taiwan University)
Entity-Aware Dual Co-Attention Network for Fake News Detection. In Findings of the Association for Computational Linguistics: EACL 2023 (EACL'23). pdf
Wei-Lin Chen (National Taiwan University - AIST Intern)
Fidelity-Enriched Contrastive Search: Reconciling the Faithfulness-Diversity Trade-Off in Text Generation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP'23). pdf
Chr-Jr Chiu (National Taiwan University)
Pre-Finetuning with Impact Duration Awareness for Stock Movement Prediction. In Companion Proceedings of the Web Conference 2025 (WWW'25). pdf
Learning Strategies for Robust Argument Mining: An Analysis of Variations in Language and Domain. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING'24). pdf
Ming-Xuan Shi (National Taiwan University)
Enhancing Volatility Forecasting in Financial Markets: A General Numeral Attachment Dataset for Understanding Earnings Calls. In Proceedings of The 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL'23). pdf
Ai-Ni Li (National Taiwan University)
Financial Statement Adequacy
Yi-Ting Liu (National Taiwan University)
Dynamic Graph Transformer for Implicit Tag Recognition. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL'21). pdf (Acceptance Rate: 24.7%)
FinSense: An Assistant System for Financial Journalists and Investors. In Proceedings of the 14th International Conference on Web Search and Data Mining (WSDM'21). pdf demo
Ting-Wei Hsu (National Taiwan University)
Semantics-Preserved Data Augmentation for Aspect-Based Sentiment Analysis. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP'21). pdf slides (Acceptance Rate: 17.9%, 190/1060)
Risk-aware Regularization for Opinion-based Portfolio Selection. In Proceedings of 15th International Conference on Web and Social Media (ICWSM'21). pdf
Hedging via Opinion-based Pair Trading Strategy. In Companion Proceedings of the Web Conference 2020 (WWW'20), Taipei, Taiwan. pdf
JianTao Huang (National Taiwan University)
NumHG: A Dataset for Number-Focused Headline Generation, In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING'24), 2024. pdf
Tsun-Hsien Tang (National Taiwan University)
Retrieving Implicit Information for Stock Movement Prediction. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'21). pdf slides poster (Acceptance Rate: 27.6%, 145/526)
Pei-Wei Kao (National Taiwan University)
NTUNLPL at FinCausal 2020, Task 2: Improving Causality Detection Using Viterbi Decoder. In Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation. pdf
Jui Chu (National Taiwan University)
Learning to Generate Correct Numeric Values in News Headlines. In Companion Proceedings of the Web Conference 2020 (WWW'20), Taipei, Taiwan. pdf slides poster
Past Collaboration
Hsiu-Hsuan Yeh (National Taiwan University)Automation of Text-Based Economic Indicator Construction: A Pilot Exploration on Economic Policy Uncertainty Index. In Proceedings of The 33rd ACM International Conference on Information and Knowledge Management (CIKM'24) pdf
Ramon Ruiz Dolz (Universitat Politècnica de València)
Learning Strategies for Robust Argument Mining: An Analysis of Variations in Language and Domain. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING'24). pdf
Sohom Ghosh (Jadavpur University)
Generator-Guided Crowd Reaction Assessment. In Companion Proceedings of the Web Conference 2024 (WWW'24). pdf
The Mask One At a Time Framework for Detecting the Relationship between Financial Entities. In Proceedings of the 15th Annual Meeting of the Forum for Information Retrieval Evaluation (FIRE'23). pdf