---

ACL2024読み会@名大

---

概要

• 会場: 名古屋大学工学部IB電子情報館中棟1階 IB015講義室
• 日時: 2024年09月30日(月)
• 形式: 1人18分(発表15分、質疑3分)

---

プログラム

• 09:30-09:35: Opening [塚越、大鹿, slide]
• 9:35-10:30: Session1: Large Lnaguage Model: Reasoning
  • Can LLMs Learn from Previous Mistakes? Investigating LLMs’ Errors to Boost for Reasoning [大鹿, slide]
  • ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs [陽田, slide]
  • VerifiNER: Verification-augmented NER via Knowledge-grounded Reasoning with Large Language Models [与那覇, slide]
• 10:40-11:35: Session2: Large Language Model: Internal Mechanism
  • Can Large Language Models Interpret Noun-Noun Compounds? A Linguistically-Motivated Study on Lexicalized and Novel Compounds [青野, slide]
  • Do Llamas Work in English? On the Latent Language of Multilingual Transformers [笹野, slide]
  • Word Embeddings Are Steers for Language Models [塚越, slide]
• 11:35-12:30: Lunch Break
• 12:30-13:25: Session3: Question Answering & Downstream Tasks
  • REANO: Optimising Retrieval-Augmented Reader Models through Knowledge Graph Generation [松原, slide]
  • Chain-of-Question: A Progressive Question Decomposition Approach for Complex Knowledge Base Question Answering [河口, slide]
  • DiFiNet: Boundary-Aware Semantic Differentiation and Filtration Network for Nested Named Entity Recognition [大井, slide]
• 13:35-14:30: Session4: Scientific Paper & Downstream Tasks
  • S2GSL: Incorporating Segment to Syntactic Enhanced Graph Structure Learning for Aspect-based Sentiment Analysis [山口, slide]
  • SciMON : Scientific Inspiration Machines Optimized for Novelty [井田, slide]
  • ARIES: A Corpus of Scientific Paper Edits Made in Response to Peer Reviews [生駒, slide]
• 14:30-14:50: Short Break
• 14:50-15:30: Session5: Dataset
  • VariErr NLI: Separating Annotation Error from Human Label Variation [吉田, slide]
  • MAVEN-ARG: Completing the Puzzle of All-in-One Event Understanding Dataset with Event Argument Annotation [金児, slide]
• 15:40-16:35: Session6: Multi Modal
  • T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text [井上, slide]
  • Progressively Modality Freezing for Multi-Modal Entity Alignment [西出, slide]
  • Let’s Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation [大橋, slide]
• 16:35-16:40: Closing

---

発表者

• 笹野遼平, 塚越駿, 青野広太郎, 大鹿雅史, 陽田祥平 (笹野研), 生駒流季, 吉田朝飛 (松原研), 大橋厚元 (東中研), 井田龍希, 大井拓, 松原拓磨, 井上純大, 金児一矢, 西出隆盛, 与那覇竜馬 (豊田工大), 河口欣仁, 山口真 (静大)

---

過去の読み会

• ACL2023読み会@名大
• ACL2019読み会@名大
• ACL2018読み会@名大

---