In this paper, we focus on the detection of semantic changes in Slovene, a less resourced Slavic language with two million speakers. Detecting and tracking semantic changes provides insight into the evolution of language caused by changes in society and culture. We present the first Slovene dataset for evaluating semantic change detection systems, which contains aggregated semantic change scores for 104 target words obtained from more than 3,000 manually annotated sentence pairs. We analyze an important class of measures of semantic change metrics based on the Average pairwise distance and identify several limitations. To address these limitations, we propose a novel metric based on regularized optimal transport, which offers a more robust framework for quantifying semantic change. We provide a comprehensive evaluation of various existing semantic change detection methods and associated semantic change measures on our dataset. Through empirical testing, we demonstrate that our proposed approach, leveraging regularized optimal transport, achieves either matching or improved performance compared to baseline approaches.
Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Tracking
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);JD Explore Academy, JD.com Inc(京东集团京东探索研究院);The University of Sydney(悉尼大学)
TRACE for Tracking the Emergence of Semantic Representations in Transformers
Department of Computer Science, University of Manchester(曼彻斯特大学计算机科学系);Idiap Research Institute(Idiap研究所);National Biomarker Centre, CRUK-MI, University of Manchester(曼彻斯特大学国家生物标志物中心)
Center for BioMed-X Research, Academy for Advanced Interdisciplinary Studies,Peking University(北京大学生物医学前沿创新中心、前沿交叉学科研究院);Speech and Hearing Research Center, School of Intelligence Science and Technology,Peking University(北京大学智能科学与技术学院言语听觉研究中心);State Key Laboratory of General Artificial Intelligence(通用人工智能国家重点实验室);National Biomedical Imaging Center, State Key Laboratory of Membrane Biology, Institute of Molecular Medicine, Peking-Tsinghua Center for Life Sciences, College of Future Technology, Peking University(国家生物医学成像中心、膜生物学国家重点实验室、分子医学研究所、北京大学生命科学联合中心、未来技术学院)
Copy-Enhanced Heterogeneous Information Learning for Dialogue State Tracking
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);Beijing Unisound Information Technology Co., Ltd(北京云知声信息技术有限公司)
对话状态跟踪(DST)是面向任务的对话系统中的一个重要组成部分,它估计用户在每个对话回合的目标。然而,大多数先前的方法通常遭受以下问题。许多判别模型,特别是端到端(E2 E)模型,很难提取出候选本体中不存在的未知值;而以往的生成模型,虽然可以从话语中提取未知值,但由于忽略了预定义本体的语义信息,导致性能下降。此外,以前的生成模型通常需要手工制作的列表来规范化生成的值。如何整合预定义本体和对话文本(异构文本)的语义信息以生成未知值并提高性能成为一个严峻的挑战。本文提出了一种基于多编码器-解码器的复制增强异构信息学习模型CEDST(Copy Enhanced Heterogeneous Information Learning Model with Multiple Encoder-Decoder for DST),该模型通过从异构文本中复制值,有效地生成包括未知值在内的所有可能值。同时,CEDST通过多个编码器有效地将大的状态空间分解为若干个小的状态空间,并采用多个解码器充分利用这些小的状态空间来产生值。多编解码器架构可以显著提高性能。实验表明,CEDST可以达到最先进的结果在两个数据集和我们构造的数据集与许多未知值。
Trajectories of Change: Approaches for Tracking Knowledge Evolution
Institute of History and Philosophy of Science, Technology, and Literature, Technische Universität Berlin(柏林工业大学科学、技术与文学史哲学研究所);Max Planck Institute of Geoanthropology(马克斯·普朗克地理人类学研究所)
Integrating LLM, EEG, and Eye-Tracking Biomarker Analysis for Word-Level Neural State Classification in Semantic Inference Reading Comprehension
Brown University(布朗大学);University of California San Diego(加利福尼亚大学圣迭戈分校);Yale University(耶鲁大学);University of California Los Angeles(加利福尼亚大学洛杉矶分校);National Central University(国立中央大学)
The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis
State Key Laboratory of AI Safety,Institute of Computing Technology, Chinese Academy of Sciences(人工智能安全国家重点实验室,计算技术研究所,中国科学院);University of Chinese Academy of Sciences(中国科学院大学)