Bio

• Iris(Renfen) received her PhD degree in Applied Linguistics in 2017, and has been working at BNU’s ICIP and CIT labs ever since.
• Her research interests include computational linguistics, NLP for educational applications and digital humanities. Her recent work focuses on diachronic language evolution, LLM evaluation and interpretability, Classical Chinese NLP, and second language writing assessment.
• She has published more than 50 peer-reviewed papers in top-tier NLP conferences and journals. She also cooperated with industrial companies to develop real-life applications.
• Her research group has developed a series of language resources and text analysis tools widely used by the community, e.g. Chinese Word Vectors (over 12k stars on Github); CCA, CLRA, and L2C-Cohesion for text complexity analysis; L2C-rater for automated essay scoring; and AI太炎(Taiyan), an LLM for the translation and annotation of Classical Chinese.

Teaching

• Python Programming and Data Analysis
• Object-Oriented Programming with Python
• Natural Language Processing
• Computational Methods in Language and Cultural Studies
• Modern Educational Technologies

Selected Publications

📄 English Publications

1. Xi Cheng, Haroon Popal, Huanqing Wang, Renfen Hu, Yinyin Zang, Mingzhe Zhang, Mark A. Thornton, Yina Ma, Huajian Cai, Yanchao Bi, Jamie Reilly, Ingrid R. Olson and Yin Wang*. The conceptual structure of human relationships across modern and historical cultures. Nature Human Behaviour, 2025. [Website]
2. Nan Hu, Xiaofei Lu and Renfen Hu*. Developing fine-grained sense-aware lexical sophistication indices based on the CEFR levels of word senses. Behavior Research Methods (SSCI Q1), 2025, 57.
3. Mahmoud Abdi Tabari, Xiaofei Lu and Renfen Hu*. The effects of task complexity and task repetition on sense-aware frequency-based lexical sophistication indices in L2 writing. Language Teaching Research (SSCI Q1), 2025.
4. Ziliang Qiu and Renfen Hu*. Deep Associations, High Creativity: A Simple yet Effective Metric for Evaluating Large Language Models. To appear on EMNLP, 2025.
5. Zhihui Yang, Yupei Wang, Kaijie Mo, Zhe Zhao and Renfen Hu*. Does Visual Grounding Enhance the Understanding of Embodied Knowledge in Large Language Models? To appear on Findings of EMNLP, 2025 .
6. Siyu Tian, Kaijie Mo, Yupei Wang and Renfen Hu*. CMT-Eval: A Novel Chinese Multi-turn Dialogue Evaluation Dataset Addressing Real-world Conversational Challenges. To appear on Findings of EMNLP, 2025.
7. Xiaofei Lu and Renfen Hu*. Sense-aware connective-based indices of cohesion and their relationship to cohesion ratings of English language learners' written production. Studies in Second Language Acquisition (SSCI Q1), 2024, 46(3).
8. Yupei Wang, Renfen Hu* and Zhe Zhao. Beyond agreement: diagnosing the rationale alignment of automated essay scoring methods based on linguistically-informed counterfactuals. Findings of EMNLP, 2024.
9. Kaijie Mo and Renfen Hu*. ExpertEase: a multi-agent framework for grade-specific document simplification with large language models. Findings of EMNLP, 2024.
10. Renfen Hu, Jifeng Wu and Xiaofei Lu*. Word-combination-based measures of phraseological diversity, sophistication and complexity and their relationship to L2 Chinese proficiency and writing quality. Language Learning (SSCI Q1), 2022, 72(4).
11. Xiaofei Lu and Renfen Hu*. Sense-aware lexical sophistication indices and their relationship to second language writing quality. Behavior Research Methods (SSCI Q1), 2022, 54(3).
12. Yupei Wang and Renfen Hu*. A prompt-independent and interpretable automated essay scoring method for Chinese second language writing. CCL 2021.
13. Renfen Hu, Shen Li and Shichen Liang. Diachronic sense modeling with deep contextualized word embeddings: an ecological view. ACL 2019.
14. Shen Li, Zhe Zhao, Renfen Hu*, Wensi Li, Tao Liu and Xiaoyong Du. Analogical reasoning on Chinese morphological and semantic relations. ACL 2018.
15. Yuanyuan Qiu, Hongzheng Li, Shen Li, Yingdi Jiang, Renfen Hu* and Lijiao Yang. Revisiting correlations between intrinsic and extrinsic evaluations of word embeddings. CCL NLP-NABD 2018 (Best Paper Award).
16. Shen Li, Zhe Zhao, Tao Liu, Renfen Hu* and Xiaoyong Du. Initializing convolutional filters with semantic features for text classification. EMNLP 2017.
17. Renfen Hu, Jiayong Chen and Kuang-hua Chen*. The construction of a Chinese collocational Knowledge resource and its application for second language acquisition. COLING 2016.

📄 Chinese Publications

1. Shen Li, Renfen Hu and Lijun Wang. Construction and application of an ancient Chinese large language model. Chinese Journal of Language Policy and Planning (in Chinese: 语言战略研究), 2024, 9(5).
2. Zhaoji Wang, Shirui Zhang, Renfen Hu*, and Xuetao Zhang. The Construction and application of an ancient Chinese language resource on Tongjiazi. Journal of Chinese Information Processing (in Chinese: 中文信息学报), 2024, 38(03). (CCL 2023 Best Paper Award)
3. Kaijie Mo and Renfen Hu*. An automatic detection model of register attributes for vocabulary in Mandarin Chinese. Applied Linguistics (in Chinese: 语言文字应用), 2023(04).
4. Shen Li, Renfen Hu and Yuchen Zhu. The joint learning of automatic punctuation and name entity recognition based on intelligent technologies. Digital Humanities (in Chinese: 数字人文), 2023(03).
5. Yiping Peng, Renfen Hu* and Jifeng Wu. Automatic analysis and application of cohesion features of Chinese texts. Applied Linguistics (in Chinese: 语言文字应用), 2023(01).
6. Nan Hu, Wenqiang Zhang and Renfen Hu*. A comparative study of Chinese and Japanese lexical meaning based on the alignment of cross-lingual word embeddings. Applied Linguistics (in Chinese: 语言文字应用), 2022(02).
7. Lei Shu, Yiluan Guo, Huiping Wang, Xuetao Zhang, and Renfen Hu*. The construction and application of ancient Chinese corpus with word sense annotation. Journal of Chinese Information Processing (in Chinese: 中文信息学报), 2022, 36(5). (CCL 2021 Best Resource Paper Award).
8. Renfen Hu. On the relationship between collocation-based syntactic complexity and Chinese second language writing. Applied Linguistics (in Chinese: 语言文字应用), 2021(01).
9. Renfen Hu, Shen Li and Yuchen Zhu. Knowledge representation and sentence segmentation of ancient Chinese based on deep language models. Journal of Chinese Information (in Chinese: 中文信息学报), 2021(4).
10. Renfen Hu. Automatic generation of Chinese vocabulary questions. Journal of Chinese Information (in Chinese: 中文信息学报), 2017(01).
11. Renfen Hu, Qi Zhu and Lijiao Yang. The construction of a topic corpus for teaching Chinese as a second language. Journal of Chinese Information (in Chinese: 中文信息学报), 2015(6).
12. Renfen Hu. Automatic identification of Chinese prepositional phrases for patent machine translation. Applied Linguistics (in Chinese: 语言文字应用), 2015(01).
13. Renfen Hu and Yuchen Zhu. Automatic classification of Tang poetry themes. Acta Scientiarum Naturalium Universitatis Pekinensis (in Chinese: 北京大学学报.自然科学版), 2015(02).
14. Renfen Hu, Bing Cao and Jianyi Du. Research of phonetic symbols of phonograms in Chinese mandarin. Journal of Chinese Information (in Chinese: 中文信息学报), 2013(3).

Resources and Applications

• Chinese Word Vectors over 12,000 stars on Github
  • This project provides 100+ Chinese Word Vectors (embeddings) trained with different representations (dense and sparse), context features (word, ngram, character, and more), and corpora.
  • Moreover, we provide a Chinese analogical reasoning dataset CA8 and an evaluation toolkit for users to evaluate the quality of their word vectors. Detailed discussions on the properties of word embeddings can be found in our papers:
    Analogical Reasoning on Chinese Morphological and Semantic Relations, ACL 2018.
    Revisiting Correlations between Intrinsic and Extrinsic Evaluations of Word Embeddings, CCL 2018 Best Paper.
• Empower AI to understand ancient Chinese
  • Understanding ancient Chinese texts is a very difficult task even for experts in this area, as it involves complex linguistic phenomena and relies heavily on historical and cultural knowledge.
  • We developed a multi-task joint learning approach to build a punctuation and named entity recognition system for ancient Chinese texts, which won first place in the CCL 2020 Ancient Chinese Named Entity Recognition Competition. This system has been applied in various ancient text projects by research institutions and publishing houses.
  • Recently, we constructed "AI Taiyan," an ancient Chinese large language model that demonstrates strong capabilities in interpreting classical literature, supporting various challenging tasks such as word sense explanation, classical-modern Chinese translation, and allusion recognition. This model shows great potential for applications in assisting ancient text collation, dictionary compilation, and digital humanities research.
  • Furthermore, we have open-sourced a series of ancient Chinese language resources to facilitate related research, such as the ancient Chinese word sense annotation corpus and the Tongjiazi dataset.
  
• CCA: Chinese Collocation Assistant
  • CCA is a free online collocation search application to assist Chinese vocabulary learning and teaching. It has served learners and educators from dozens of countries across six continents.
  • We have open-sourced the Chinese Collocation Knowledgebase used in CCA, which was automatically extracted from the Chinese Textbook Corpus (2.4M words) and Chinese Wikipedia (138M words).
  • To better facilitate collocation research, we have developed the Chinese Collocation Analyzer, a tool that supports automatic extraction of syntactic collocations in Modern Chinese and calculation of syntactic complexity measures.
  
  
• Intelligent Language Testing for L2 Learners
  • We proposed an innovative testing approach that integrates automatic item generation (AIG) and computerized adaptive testing (CAT) for assessing Chinese as a second language (CSL) proficiency. Our system enables a rapid, adaptive Chinese proficiency test that takes approximately ten minutes.
  • Additionally, we developed L2C-Rater, an automated essay scoring tool for CSL learners. The source code for L2C-Rater is available on GitHub under an open-source license.
  
  
• Diachronic Sense Modeling of English Words
  • We propose a sense representation and tracking framework that aims to answer not only what and when, but also how word meanings change over time.
  • We have open-sourced diachronic sense evolution data and visualization tool for 3,220 polysemous English words spanning 200 years (1810-2009).
  • Furthermore, we model word change from an ecological viewpoint and identify two interesting sense behaviors in the process of language evolution: sense competition and sense cooperation.