A5101535060- Microbial Applications in Construction Materials
- Topic Modeling
- Natural Language Processing Techniques
- Biometric Identification and Security
- Face recognition and analysis
- Sentiment Analysis and Opinion Mining
- Grouting, Rheology, and Soil Mechanics
- User Authentication and Security Systems
- Face and Expression Recognition
- Calcium Carbonate Crystallization and Inhibition
- Methane Hydrates and Related Phenomena
- Bacterial biofilms and quorum sensing
- Speech and dialogue systems
- Microbial bioremediation and biosurfactants
- Advanced Text Analysis Techniques
- Coal Properties and Utilization
- Advanced Graph Neural Networks
- Covalent Organic Framework Applications
- Web Data Mining and Analysis
- Microbial Fuel Cells and Bioremediation
- Concrete and Cement Materials Research
- Forensic and Genetic Research
- Spam and Phishing Detection
- Antimicrobial agents and applications
- Text and Document Classification Technologies
Shandong University of Science and Technology
2021-2024
Jiangsu University of Science and Technology
2024
Institute of Applied Ecology
2022
Chinese Academy of Sciences
2022
Hong Kong Polytechnic University
2011-2021
Baidu (China)
2018-2021
University College London
2020-2021
Harbin Institute of Technology
2012-2021
Jiangxi Normal University
2020-2021
Bellevue Hospital Center
2020
In view of the limited text features short texts, texts should be mined from various angles, and multiple sentiment feature combinations used to learn hidden information. A novel analysis model based on multi-channel convolutional neural network with multi-head attention mechanism (MCNN-MA) is proposed. This combines word part speech features, position dependency syntax separately form three new combined inputs them into network, as well integrates more fully information in text. Finally,...
Yue Feng, Yang Wang, Hang Li. Proceedings of the 59th Annual Meeting Association for Computational Linguistics and 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.
In this paper, we consider the problem of open information extraction (OIE) for extracting entity and relation level intermediate structures from sentences in open-domain. We focus on four types valuable (Relation, Attribute, Description, Concept), propose a unified knowledge expression form, SAOKE, to express them. publicly release data set which contains 48,248 corresponding facts SAOKE format labeled by crowdsourcing. To our knowledge, is largest available human tasks. Using set, train an...
Helpful reviews play a pivotal role in recommending desirable goods and accelerating purchase decisions of customers e-commercial services. Given large proportion product with unknown helpfulness/unhelpfulness, the research on automatic identification helpful has drawn much attention recent years. However, state-of-the-art approaches still rely heavily extracting heuristic text features from domain-specific knowledge. In this paper, we first introduce multi-task neural learning (MTNL)...
Abstract Single-label classification technology has difficulty meeting the needs of text classification, and multi-label become an important research issue in natural language processing (NLP). Extracting semantic features from different levels granularities is a basic key task research. A topic model effective method for automatic organization induction information. It can reveal latent semantics documents analyze topics contained massive Therefore, this paper proposes based on tALBERT-CNN:...
Topic recognition technology has been commonly applied to identify different categories of news topics from the vast amount web information, which a wide application prospect in field online public opinion monitoring, recommendation, and so on. However, it is very challenging effectively utilize key feature information such as syntax semantics text improve topic accuracy. Some researchers proposed combine model with word embedding model, whose results had shown that this approach could...
Abstract Owing to soft clay’s high water content and low strength, the large volumes of it that are excavated during coastal waterway construction must be disposed by being dumped on vacant land or used as fill, results in increasingly serious environmental problems. Another important regional problem is coal fly ash (CFA) produced coal-fired power plants. Soft clay disposal methods can also use CFA have practical significance for infrastructure projects help economies areas with limited...