A5103012396- Advanced Graph Neural Networks
- Text and Document Classification Technologies
- Sentiment Analysis and Opinion Mining
- Recommender Systems and Techniques
- Advanced Image and Video Retrieval Techniques
- Enzyme Catalysis and Immobilization
- Topic Modeling
- Graph Theory and Algorithms
- Advanced Bandit Algorithms Research
- Stock Market Forecasting Methods
- Web Data Mining and Analysis
- Information Retrieval and Search Behavior
- Complex Network Analysis Techniques
- Data Management and Algorithms
- Crystallization and Solubility Studies
- Advanced Text Analysis Techniques
- Analytical Chemistry and Chromatography
- Consumer Market Behavior and Pricing
- Natural Language Processing Techniques
- Spam and Phishing Detection
Qingdao University of Science and Technology
2024
Kuaishou (China)
2024
Alibaba Group (China)
2021-2022
Alibaba Group (United States)
2022
Peking University
2014-2015
This paper studies the problem of emotion classification in microblog texts. Given a text which consists several sentences, we classify its as anger, disgust, fear, happiness, like, sadness or surprise if available. Existing methods can be categorized lexicon based machine learning methods. However, due to some intrinsic characteristics texts, previous using these always get unsatisfactory results. introduces novel approach on class sequential rules for The first obtains two potential labels...
The combination of enzymatic synthesis and computer simulation can provide a more powerful solution for obtaining chiral products that are used as pharmaceuticals.
Graph embedding based retrieval has become one of the most popular techniques in information community and search engine industry. The classical paradigm mainly relies on flat Euclidean geometry. In recent years, hyperbolic (negative curvature) spherical (positive representation methods have shown their superiority to capture hierarchical cyclic data structures respectively. However, industrial scenarios such as e-commerce sponsored platforms, large-scale heterogeneous...
Cascade ranking is widely used for large-scale top-k selection problems in online advertising and recommendation systems, learning-to-rank an important way to optimize the models cascade ranking. Previous works on usually focus letting model learn complete order or order, adopt corresponding rank metrics (e.g. OPA NDCG@k) as optimization targets. However, these targets can not adapt various scenarios with varying data complexities capabilities; existing metric-driven methods such Lambda...
In large-scale E-commerce retrieval, the Graph Neural Networks (GNNs) has become one of stage-of-the-arts due to its powerful capability on topological feature extraction and relational reasoning. However, conventional GNNs-based retrieval suffers from low training efficiency, as such scenario normally billions entities tens relations. Under limitation only shallow graph algorithms can be employed, which severely hinders GNNs representation consequently weakens quality. order deal with...
Ad retrieval in sponsored search aims to understand user intentions (user queries) and retrieves a set of ads inferred as being relevant the queries. Due huge amount traffic multiple views relevance (such co-clicking, co-bidding or textual similar), it is highly desirable but remain challenging achieve large-scale, multi-view matching between queries ads, particularly industrial settings. In this paper, we propose scalable ad engine SMAD that developed deployed at Taobao, largest e-commerce...