Intelligent systems designed using machine learning algorithms require a large number of labeled data. Background knowledge provides complementary, real world factual information that can augment the limited labeled data to train a machine learning algorithm. The term Knowledge Graph (KG) is in vogue as for many practical applications, it is convenient and useful to organize this background knowledge in the form of a graph. Recent academic research and implemented industrial intelligent systems have shown promising performance for machine learning algorithms that combine training data with a knowledge graph. In this article, we discuss the use of relevant KGs to enhance input data for two applications that use machine learning -- recommendation and community detection. The KG improves both accuracy and explainability.
SEER: Semantic Enhancement and Emotional Reasoning Network for Multimodal Fake News Detection
School of Artificial Intelligence, Optics, and Electronics (iOPEN), Northwestern Polytechnical University(人工智能、光学与电子学院(iOPEN),西北工业大学);School of Computer Science, Northwestern Polytechnical University(计算机学院,西北工业大学);Unit 93212 of People’s Liberation Army of China(中国人民解放军第九三二一二单位);School of Marine Science and Technology, Northwestern Polytechnical University(海洋科学与技术学院,西北工业大学);Cyberspace Institute of Advanced Technology, Guangzhou University(高级技术网络空间研究院,广州大学)
Improving Semantic Parsing for Task Oriented Dialog
Facebook Conversational AI(Facebook对话式AI);Stanford University(斯坦福大学);Facebook AI Research(Facebook人工智能研究)
最近提出了使用分层表示的语义解析,用于面向任务的对话,结果很有希望[Gupta et al 2018]。在本文中,我们提出了三种不同的改进模型:上下文嵌入,集成,和成对重新排名的基础上的语言模型。我们分类的错误可能的分层表示,如错误的顶部意图,缺失的跨度或分裂跨度,并表明这三种方法纠正不同类型的错误。最好的模型结合了这三种技术,精确匹配精度比最先进的模型高出6.4%,错误减少了33%,从而在面向任务的解析(TOP)数据集上产生了新的最先进的结果。
Improving Pre-trained Language Models with Syntactic Dependency Prediction Task for Chinese Semantic Error Recognition
Harbin Institute of Technology(哈尔滨工业大学);iFLYTEK Research(讯飞研究院)
现有的中文文本错误检测主要集中在拼写和简单的语法错误。这些错误已被广泛研究,对人类来说相对简单。相反,汉语的语义错误研究不足,而且更加复杂,人类不容易识别。本文的任务是汉语语义错误识别(CSER),一个二元分类任务,以确定一个句子是否包含语义错误。目前的研究还没有有效的方法来解决这个问题。本文继承了BERT的模型结构,设计了多个与句法相关的预训练任务,使模型能够学习句法知识。我们的预训练任务考虑依赖结构的方向性和依赖关系的多样性。由于目前尚缺乏针对CSER的公开数据集,本文首次建立了一个高质量的CSER数据集--汉语语义可接受性语料库(Corpus of Chinese Linguistic Semantic Acceptability,CoCLSA)。在CoCLSA上的实验结果表明,我们的方法优于通用的预训练模型和语法注入模型。
CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR
Zhejiang University(浙江大学);Westlake University(西湖大学);School of Engineering(工程学院);Institute of Advanced Technology(先进技术研究院);Westlake Institute for Advanced Study(西湖研究学院)
Deep Semantic Graph Learning via LLM based Node Enhancement
University of California San Diego(加利福尼亚大学圣迭戈分校);Johns Hopkins University(约翰斯·霍普金斯大学);Duke University(杜克大学);University of Amsterdam(阿姆斯特丹大学);Simon Fraser University(西蒙菲莎大学)
MARIS: Marine Open-Vocabulary Instance Segmentation with Geometric Enhancement and Semantic Alignment
University of Science and Technology of China(中国科学技术大学);Institute of Artificial Intelligence (TeleAI)(人工智能研究院(TeleAI));China Telecom(中国电信);Fudan University(复旦大学);Northwestern Polytechnical University(西北工业大学)
Cognition-Inspired Dual-Stream Semantic Enhancement for Vision-Based Dynamic Emotion Modeling
College of Intelligent Robotics and Advanced Manufacturing, Fudan University(复旦大学智能机器人与先进制造学院);Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University(上海智能信息处理重点实验室,复旦大学计算机科学与人工智能学院);School of Data Science and Engineering, East China Normal University(华东师范大学数据科学与工程学院)
Improving Code Translation with Syntax-Guided and Semantic-aware Preference Optimization
State Key Laboratory for Novel Software Technology, Nanjing University, China(南京大学新型软件技术国家重点实验室);National Institute of Healthcare Data Science, Nanjing University, China(南京大学健康数据科学国家研究院)