A5007922382- Language, Metaphor, and Cognition
- Topic Modeling
- Natural Language Processing Techniques
- Recommender Systems and Techniques
- Cancer-related molecular mechanisms research
- Advanced Graph Neural Networks
- Multimodal Machine Learning Applications
- Sentiment Analysis and Opinion Mining
- Speech Recognition and Synthesis
- Adversarial Robustness in Machine Learning
- Advanced Text Analysis Techniques
- Swearing, Euphemism, Multilingualism
- Music and Audio Processing
- RNA Research and Splicing
- RNA and protein synthesis mechanisms
- Visual Attention and Saliency Detection
- Text and Document Classification Technologies
- Digital Media Forensic Detection
- Humor Studies and Applications
- Emotion and Mood Recognition
- Chemical Synthesis and Analysis
- Handwritten Text Recognition Techniques
- Image Enhancement Techniques
- Plant and Fungal Interactions Research
- Computational Drug Discovery Methods
Xinjiang University
2020-2025
China Pharmaceutical University
2025
Hangzhou Dianzi University
2023-2024
<abstract><p>Long non-coding RNAs (lncRNAs) play a regulatory role in many biological cells, and the recognition of lncRNA-protein interactions is helpful to reveal functional mechanism lncRNAs. Identification interaction by techniques costly time-consuming. Here, an ensemble learning framework, RLF-LPI proposed, predict interactions. The residual LSTM autoencoder module with fusion attention can extract potential representation features capture dependencies between sequences...
Long non-coding RNA(lncRNA) can interact with microRNA(miRNA) and play an important role in inhibiting or activating the expression of target genes occurrence development tumors. Accumulating studies focus on prediction miRNA-lncRNA interaction, mostly are concerned biological experiments machine learning methods. These methods found long cycles, high costs, requiring over much human intervention. In this paper, a data-driven hierarchical deep framework was proposed, which composed capsule...
Anaphora resolution of Uyghur is a challenging task because complex language structure and limited corpus. We propose multi-attention based capsule network model for personal pronouns resolution, which can obtain the multi-layer implicit semantic information effectively. Independently recurrent neural (IndRNN) applied in this to achieve interdependent features with long distance. Moreover, extract richer textual improve expression ability. Compared single attention-based combines Long...
Abstract Few-shot Event Detection (FSED) is a sub-task of that aims to accurately identify event types with limited training instances and enable smooth transfer newly-emerged types. Recently, the dominant works have used prototypical network accomplish this task employ contrastive learning alleviate issue semantically-close categories. Nevertheless, these methods still suffer from two serious problems: (1) inadequate prototype representations resulting data; (2) hard-easy sample imbalance...
Social recommendation systems play a vital role in today's Internet era. The richness of social relationships can compensate for the sparsity interaction data between users and items, thereby reducing impact this on systems. Typically, utilize graph to describe users, items their relationships. So using Graph Neural Networks (GNN) effectively analyze complex nodes. However, traditional GNN models primarily focus node neighbors during information propagation, which may hinder capturing global...
<title>Abstract</title> In the field of multimodal intent detection research, researchers have worked on seamlessly integrating various information types to accurately recognize user intent, which is crucial for creating efficient dialog systems in complex real-world environments. Current approaches still significant potential improvement exploring deep connections between modalities and extracting key semantic features from non-textual data. this paper, we introduce GFIDF, a step-by-step...
The metaphor is a pervasive linguistic device that has become an active research topic in the computer field because of its essential role language's cognitive and communicative processes. Currently, rapid expansion social media encourages development multimodal. As most popular communication method media, memes have attracted attention many linguists, who believe metaphors contain rich metaphorical information. However, multimodal detection suffers from insufficient information due to short...