As text processing systems expand in scope, they will require ever larger lexicons along with a parsing capability for discriminating among many senses of a word. Existing systems do not incorporate such subtleties in meaning for their lexicons. Ordinary dictionaries contain such information, but are largely untapped. When the contents of dictionaries are scrutinized, they reveal many requirements that must be satisfied in representing meaning and in developing semantic parsers. These requirements were identified in research designed to find primitive verb concepts. The requirements are outlined and general procedures for satisfying them through the use of ordinary dictionaries are described, illustrated by building frames for and examining the definitions of "change" and its uses as a hypernym in other definitions.
Leveraging ChatGPT As Text Annotation Tool For Sentiment Analysis
College of Science and Engineering, Hamad Bin Khalifa University（哈马德·本·哈利法大学科学与工程学院）；Department of Electronic and Computer Engineering, HKUST（香港科技大学电子与计算机工程系）
Far from the Shallow: Brain-Predictive Reasoning Embedding through Residual Disentanglement
Zuckerman Mind Brain Behavior Institute, Columbia University（扎克曼脑行为研究所，哥伦比亚大学）；Department of Electrical Engineering, Columbia University（电气工程系，哥伦比亚大学）；Department of Computer Science, Columbia University（计算机科学系，哥伦比亚大学）
TajikNLP: An Open-Source Toolkit for Comprehensive Text Processing of Tajik (Cyrillic Script)
Institute of Computational Mathematics and Information Technologies（计算数学与信息科技研究所）；Kazan Federal University（喀山联邦大学）；Bokhtar State University named after Nosiri Khusrav（诺西拉夫命名的博克塔尔州大学）
A Natural Language Processing Pipeline of Chinese Free-text Radiology Reports for Liver Cancer Diagnosis
School of Biomedical Engineering, Capital Medical University（首都医科大学生物医学工程学院）；Beijing Friendship Hospital, Capital Medical University（首都医科大学附属北京友谊医院）；Tsinghua University（清华大学）
Tabula nearly rasa: Probing the Linguistic Knowledge of Character-Level Neural Language Models Trained on Unsegmented Text
Stanford University（斯坦福大学）；Facebook AI Research（脸书人工智能研究院）；UPF Linguistics Department（庞培法布拉大学语言学系）
递归神经网络（RNN）在许多自然语言处理任务中取得了惊人的性能。这重新引起了人们对这些通用序列处理设备是否诱导真正的语言知识的兴趣。然而，几乎所有当前的分析研究都用已知单词的词汇表初始化RNN，并在训练过程中为它们提供标记化的输入。我们提出了一个多语言的语言知识编码的RNN训练字符级语言模型，在输入数据与词边界删除的研究。这些网络面临着一个更艰难、更现实的认知任务，必须根据输入统计数据从头开始发现任何有用的语言单元。结果表明，我们的“near tabula rasa”RNN大多能够解决直观地假设单词级别知识的形态，句法和语义任务，并且确实在某种程度上学会了跟踪单词边界。我们的研究为语言学习和使用中明确的、严格的词汇库的必要性的思考打开了大门。
Multilingual LLMs Struggle to Link Orthography and Semantics in Bilingual Word Processing
Department of Electrical Engineering, Indian Institute of Technology Delhi（印度理工学院德里电气工程系）；Yardi School of Artificial Intelligence, Indian Institute of Technology Delhi（印度理工学院德里人工智能学院）
Classification of Natural Language Processing Techniques for Requirements Engineering
University of Manchester（曼彻斯特大学）；Al-Imam Mohammed ibn Saud Islamic University（伊玛目·穆罕默德·本·沙特伊斯兰大学）；Consiglio Nazionale delle Ricerche（意大利国家研究委员会）；Higher Colleges of Technology（高等技术学院）
