Program
PACLIC 2025 Program
All times are in the Hanoi time zone (GMT+7).
Oral presentations are assigned slots of 20 mins in total (including Q/A)
Day 1: December 5, 2025
9:15 Opening Remarks
9:30 Keynote Talk: Marco Marelli (University of Milan-Bicocca)
The Meaning of Jabberwock: Semantic Activation in the Processing of Unfamiliar Words.
10:30 Coffee Break
11:00 Oral Presentations
Session 1a: Language Learning
Atsushi Nakanishi. Scaffolded AI Feedback for L2 Writing: Fostering Self-Correction in Japanese University Students
Van-Khanh Tran, Duc-Huy Nguyen and Van-Khai Dang. PRISM: A Pedagogical Multi‑Agent for Structured Group Learning
Yo Ehara. Keeping LLMs from Being Distracted: Grade-Aware Kanji Reading Estimation Fully Executable in Web Browsers for Japanese Education
I-Ping Wan, Xiang Li and Yu Ching Tsai. Syllabic Distribution and Developmental Patterns of Mandarin Glides in Preschool Children
Session 1b: NLP Applications
Yuha Nishigata, Waka Ito and Kimio Kuramitsu. Non-English Code Generation with Cross-Lingual Chain of Thought
Dat Nguyen Thanh, Nguyen Lam Hung, Anh Thi-Hoang Nguyen and Hop Do Trong. MTikGuard System: A Transformer-Based Multimodal System for Child-Safe Content Moderation on TikTok
Khanh-Hung Huynh, Phuc Hoang Gia Bui, Huyen Doan My Dinh, Phi-Long Nguyen, Thien-Vu Nguyen-Ho and Trong-Hop Do. Online Information Extraction System (EAOS) for Social Media Comments
Mayank Bumb, Anshul Vemulapalli, Sri Harsha Vardhan Prasad Jella, Anish Gupta, An La, Ryan Rossi, Hongjie Chen, Franck Dernoncourt, Nesreen K. Ahmed and Yu Wang. Forecasting Time Series with LLMs via Patch-Based Prompting and Decomposition
12:30 Lunch break
13:30 Keynote Talk: Chu-Ren Huang (The Hong Kong Polytechnic University)
From Sensory Modalities to Embodied Cognition: How to Reconcile Linguistic Studies with Large Language Models.
14:30 Poster Session 1
- Thien Khuu, Thuan Huynh, Nam Van Chi and Tung Le. Generation via Optimized Sentence Ordering
- Tomokazu Takehisa. Verb Phrase Idioms in Valency Alternation: A Selection-based Approach
- Yujia Tian, Yanyuan Ye, Mingxi Lu, Fanlu Jia and Ran Tao. Speech-Like Cues and the Limits of Musicality: Lexical Tone Normalization in Mandarin across Speech, Rap, and Song Contexts
- Nakyung Yoon. A/E pelita as an aspectual marker in Korean Auxiliary Verb Constructions: An Experimental Comparison with Spanish Optional se
- Yimei Shao, Yu-Yin Hsu and Chu-Ren Huang. Sensory and Affective Dimensions in Mandarin Monosyllabic Adjectives
- Yuzuki Tsukagoshi and Ikki Ohmukai. Improving Classical Language Machine Translation using Supervised Fine-Tuning with Philological Commentary
- Huy Trieu, Thanh Thai Nguyen, Thanh Nghia Vo, Thinh Vuong Vo, Thanh Tu Dang and Tung Le. KWordinaryVQA: A Keyword-Driven Generative Visual Question Answering System for Culinary Exploration
- Menghan Dong, Youzhi Wu, Siqi Wang and Zhen Wu. Diagnosing the Cultural Gap in Machine Translation of Classical Chinese: A Computational Analysis of the Analects
- Chengguang Gan, Qinghao Zhang and Tatsunori Mori. USA Model: Japanese Universal Sentiment Analysis Model and Construction of Japanese Sentiment Text Classification and Part of Speech Dataset
15:30 Coffee Break
16:00 Oral Presentations
Session 2a: Natural Language Generation
Ryuichi Uehara and Michimasa Inaba. A Persona Dialogue Dataset of Lesser-Known Characters for Fairer Evaluation of Role-Playing LLMs
Natsumi Ezure and Michimasa Inaba. The Relationship Between Dialogue Acts and Idea Generation in Human–Human Collaborative Story Writing
Aravinth Sivaganeshan, Nisansa de Silva and Akila Peiris. Fine-tuning an LLM to Generate Lore Coherent Encounters for Dungeons and Dragons
Haruhisa Iseno, Atsumoto Ohashi, Tetsuji Ogawa, Shinnosuke Takamichi and Ryuichiro Higashinaka. Analysis of the Correlation Between Theory of Mind and Dialogue Ability to Identify Essential ToM for Dialogue Systems
17:20 Oral Presentations
Session 3a: NLP Applications II
Oshadha Wijerathne, Amandi Nimasha, Dushan Fernando, Nisansa de Silva and Srinath Perera. ScheduleMe: Multi-Agent Calendar Assistant
Thu Phuong Tran Thi, Vinh Van Nguyen, Thai Nguyen Phuong, Quang Vu Ngoc and Khoa Nguyen Dang. RoSRL: Adaptive Rule-of-Sum Reinforcement Learning for Efficient and Reliable Summarization
Monika Zamojska and Jaroslaw A. Chudziak. On the Role of Contextual Information and Ego States in LLM Agent Behavior for Transactional Analysis Dialogues
Arati Mohapatra and S Jaya Nirmala. Toward True Neutrality: Evaluating Inference-Time Debiasing Strategies for Gender Coreference Resolution in LLMs
16:00 – 19:00 Workshop on the Language of Food in Asia
Charmgil Hong, Jong-Bok Kim, Seulkee Park, and Yunseong Choe. Conceptual Metaphors in Food Reviews: LLM-Based Implications for Korean Discourse
Waka Ito, Manaka Odagaki, Haruka Tsuchida, Yuha Nishigata, Yui Obara, and Kimio Kuramitsu. Toward the Development of a Japanese Food Culture QA
Tian Gao. From Tea to Symbol: A Multimodal Discourse Analysis of HeyTea’s Branding Discourses
Clio Luo. Balancing Heat and Clarity: Alcohol, Tea, and the Body in Premodern Chinese Texts
Miwa Morishita and Yasunari Harada. Landscapes of Matcha: Cultural Semiotics in Japan and Taiwan
Invited Talk: Genta Indra Winata (Capital One) and Emmanuele Chersoni (The Hong Kong Polytechnic University)
Foodies also Need Their Own GPTs: Evaluating Language Models in Visual Question Answering on the WorldCuisines Dataset
Day 2: December 6, 2025
9:30 Keynote Talk: Derek F. Wong (University of Macau)
Can a Language Model Be a Good Judge? Towards Reliable Evaluation and Better Reasoning.
10:30 Coffee Break
11:00 Oral Presentations
Session 4a: Semantics
Sara Besharati. Exploring Synonymy Representation in Large Language Models: A Comparative Analysis with Referential and Use-Based Lexical Resources
Yebin Lee, Sanghoun Song and Arum Kang. Assessing GPT models’ Sensitivity to Epistemic Meanings in Korean Periphrastic Construction
Ganesh Katrapati and Manish Shrivastava. Non Idiomatic Conventionalised Expressions: A New Pain in the Neck?
Chan Young Jung. Same Spelling, Different Functions Mah: Evaluating Language Models' Understanding of Singlish Particles
Session 4b: Corpus Linguistics
Ka-Fai Yip, Yaxuan Ji, Dicky Ko, Thomas Ho and Benjamin K. Tsou. Converging and diverging variations in metaphorization of light verbs: A corpus study on four Chinese speech communities
Kazuho Kambara, Yuki Sugawara and Norihisa Takahashi. How “empirical” is corpus linguistics? A meta-analysis using formal concept analysis
Romeo Jr. Tejada, Jose Marie Ocdenaria and Kenneth Lisbo. Speaking to the Inner Child: A Discourse Analysis of Healing Narratives in Digital Therapeutic Culture
12:30 Lunch break
13:30 Poster Session 2
- Junichiro Niimi. Reference Points in LLM Sentiment Analysis: The Role of Structured Context
- Xueyi Wen, Hongzhi Xu and Lili Yang. An Investigation of Sentiment Polarity in Chinese VO Idioms Based on NLP Models
- Daiki Shirafuji, Tatsuhiko Saito and Yasutomo Kimura. An Empirical Survey of Model Merging Algorithms for Social Bias Mitigation
- Manh-Cuong Phan, Thi-Ngoc-Phuong Nguyen, Huu-Loi Le, Huy-The Vu, Hajime Hotta and Minh-Tien Nguyen. From Span Extraction to Classification: A Multi-step Framework for Cognitive Distortion Analysis
- Jesse W. C. Yip and Michelle Man-Long Pang. Researching and Rethinking the Culture and Practice of Eldercare in Hong Kong: A Corpus-assisted Discourse Analysis
- Hoang Thanh Nguyen, Tung Le and Huy Tien Nguyen. HisGraphRAG: GraphRAG for Vietnamese Historical question answering
- James Ald Teves, Ray Daniel Cal, Josh Magdiel Villaluz, Jean Malolos, Mico Magtira, Ramon Rodriguez, Mideth Abisado and Joseph Marvin Imperial. HiligayNER: A Baseline Named Entity Recognition Model for Hiligaynon
- Kentaro Kojima, Yoshihide Kato and Shigeki Matsubara. Is CCGbank Semantically Valid? Insights from Negation Scope Analysis
- Dongnyeong Heo, Daniela Noemi Rim and Heeyoul Choi. Diverse Target Representations for Language Models with Word Difference Representations
14:30 Oral Presentations
Session 5a: NLP Applications III
Keisuke Iwamoto and Kazutaka Shimada. Exaggeration Scoring of News Summaries through LLM-based Relative Judgments
Prathamesh Kokate, Mitali Sarnaik, Manavi Khopade and Raviraj Joshi. Improving the Efficiency of Long Document Classification using Sentence Ranking Approach
Steven Au, Cameron Dimacali, Ojasmitha Pedirappagari, Namyong Park, Franck Dernoncourt, Yu Wang, Nikos Kanakaris, Hanieh Deilamsalehy, Ryan A. Rossi and Nesreen K. Ahmed. Personalized Graph-Based Retrieval for Large Language Models
K. M Hewapathirana, Nisansa de Silva, Chathurike Dayal Athuraliya and Piumi Kandanaarachchi. Domain Adaptation for Multi-document Summarisation: A Case Study in the Medical Research Domain
Session 5b: Sentiment and Emotion Analysis
Xinyi Wang, Mingyu Wan and Chu-Ren Huang. Computational Linguistic Approach to Empathy and its Language Communication Pattern
Jieyu Chen, Yujia Tian, Jing Qi and Ran Tao. Effect of Emotional Congruency and Cognitive Load on Word Processing
Ryota Amano, Kazuya Mera, Yoshiaki Kurosawa and Toshiyuki Takezawa. Controlling Emotion Intensity and Blending in Text via Task Vector Composition for Dialog System Personalization
Katarzyna Szczepaniak and Piotr Andruszkiewicz. MoE4EDiReF: Mixture of Experts for Emotion Discovery and Reasoning its Flip in Conversation
15:50 Coffee Break
16:20 Keynote Talk: Shalom Lappin (University of Gothenburg) Exploring Architectures for Neuro-Symbolic Models in AI.
17:20 Oral Presentations
Session 6a: NLP for Low-resource Languages
Aswinkumar I, Sangeetha Sivanesan and S Jaya Nirmala. Ancient Tamil Palm Leaf Character Recognition using Transformers
Nidhi Kowtal and Raviraj Joshi. L3Cube-MahaEmotions: A Marathi Emotion Recognition Dataset with Synthetic Annotations using CoTR prompting and Large Language Models
R S Mughil Srinivasan, Kesavan T, Abhijith Balan, Abhinav P M, Parameswari Krishnamurthy and Oswald C. VIDAI: VIDukathAI Interpretation Through Analysis of In-context Reasoning in Tamil using LLMs
Session 6b: NLP Applications IV
John Blake, Kazuma Tamura and Krzysztof Kredens. Dual-mode N-gram Similarity Detection for Forensic Authorship Analysis
Thanh-Nhi Nguyen and Trong-Hop Do. A Social Listening System for Beauty Products Using Aspect-Based Sentiment Analysis
Dawid Smalcuga and Piotr Andruszkiewicz. How Is Context Important in Named Entity Recognition? A Comparison of Non-contextual and Contextual Word Embeddings
19:00 Social Dinner
Day 3: December 7, 2025
9:30 Keynote Talk: Mark Liberman (University of Pennsylvania)
Spontaneous Speech: Challenges and Opportunities for Speech Technology and for Models of Perception and Production.
10:30 Coffee Break
11:00 Oral Presentations
Session 7a: Syntax
Masanori Oya, Yuka Kaise and Yuto Tsuchiya. The propositional idea densities of different languages in multi-lingual parallel corpus
Menghan Jiang and Chu-Ren Huang. The Evolutionary Mechanisms of Transitivization in Mandarin VO Compounds: A Corpus-Driven Study of Competing Alternations
Nayoung Kwon and Seongmin Mun. Evaluating Syntactic Generalization in Transformer-Based Models Using Korean Honorific Agreement
Hiroki Unno, Tomohiro Ohno, Koichiro Ito and Shigeki Matsubara. Dependency-Aware Word Prediction Integrated with Incremental Parsing
Session 7b: Semantics II
Minh-Phuong Nguyen, Tien Dang and Naoya Inoue. Non-Interactive Symbolic-Aided Chain-of-Thought for Logical Reasoning
Kohei Oda, Hiroya Takamura, Kiyoaki Shirai and Natthawut Kertkeidkachorn. Improving Interpretability of Lexical Semantic Change with Neurobiological Features
Feifei Sun, Ziyi Tong, Teeradaj Racharak and Minh Le Nguyen. Time Tells: Temporal Event Ordering in Frontier LLMs — Performance, Limitations, and Human Comparison
Hang Zhu, Rowan Hall Maudslay, Kanako Komiya, Sachi Kato and Masayuki Asahara. Large-Scale Japanese Metaphor Corpus Construction: Expanding BCCWJ-Metaphor with Automated Annotation
12:30 Lunch Break
14:00 Oral Presentations
Session 8a: Machine Translation
Wenhui Shi and Ziman Han. RMCP: Enhancing LLM-based Translation via Prompting with Retrieved Monolingual Corpora
Bao Pham-Thai, Vy Do Le Khanh and Huy Quoc To. BV-FRD: A Multimodal Vietnamese-English Food Review Video Description Generation
Jin Yim. Preserving Ambiguity: Prompt Sensitivity in Gender-Neutral Literary Translation by GPT Models
Trong Huy Nguyen, Thanh Huong Le and Que Nhu Tran. Towards Improving Low-Resource Machine Translation with Lightweight Training and Synthetic Data: Case Study of Vietnamese – Khmer
Session 8b: Corpus Linguistics II
Xin Luo, Wing Hei Lok and Yu-Yin Hsu. ‘But this one was so . . . male.’ A Corpus-Based and LLM-Augmented Analysis of Language and Gender Bias in Barbie
Yifan Li, Yanlin Li and Kathleen Ahrens. A corpus-assisted metaphor analysis in portraying businesswomen: Diachronic changes in Hong Kong English news
Nevidu Jayatilleke and Nisansa de Silva. SiDiaC: Sinhala Diachronic Corpus
15:30 Coffee Break
16:00 Oral Presentations
Session 9a: Multimodality
Yi Yao and Qiu Zhuang. Do Multimodal Large Language Models Have “Good Taste”? An Evaluation of MLLMs via the Visual Aesthetic Sensitivity Test
Shuhei Yamashita, Daiki Shirafuji and Tatsuhiko Saito. Bridging the Modality Gap by Similarity Standardization with Pseudo-Positive Samples
Zhenming Li and Kazutaka Shimada. Semantic Meaning or Script Shape? A Comparative Study of Cross-Lingual Transfer in mBERT and PIXEL
Session 9b: NLP for Low-resource Languages II
Abhay Shanbhag, Suramya Jadhav, Amogh Thakurdesai, Ridhima Sinare, Raviraj Joshi and Ananya Joshi. MahaParaphrase: A Marathi Paraphrase Detection Corpus and BERT-based Models
Pankaj Choudhury, Chaitanya Kirti, Dhrubajyoti Pathak and Sukumar Nandi. AsRED: Development and Evaluation of an Assamese Reduplication Dataset
Sharvi Endait, Ruturaj Ghatage, Aditya Kulkarni, Rajlaxmi Patil and Raviraj Joshi. IndicSQuAD: A Comprehensive Multilingual Question Answering Dataset for Indic Languages
17:00 Closing Session