Li Deng
YOU?
Author Swipe
View article: The Impact of Brand Storytelling on Consumer Perception
The Impact of Brand Storytelling on Consumer Perception Open
Brand storytelling has become a powerful strategy in marketing. Instead of just showing product features, it helps brands connect with people through emotions, values, and shared ideas. This review looks at how storytelling shapes consumer…
View article: Biological age prediction and NAFLD risk assessment: a machine learning model based on a multicenter population in Nanchang, Jiangxi, China
Biological age prediction and NAFLD risk assessment: a machine learning model based on a multicenter population in Nanchang, Jiangxi, China Open
View article: AD-DES: An adaptive dual dynamic ensemble selection for imbalanced data streams
AD-DES: An adaptive dual dynamic ensemble selection for imbalanced data streams Open
View article: Analysis of Points of Interests Recommended for Leisure Walk Descriptions
Analysis of Points of Interests Recommended for Leisure Walk Descriptions Open
Leisure walking is a physical activity where locomotion through a natural or even urban environment is the goal in itself, e.g., in pursuit of health and wellbeing. In contrast to destination-oriented walks that are focused on navigation e…
View article: Optimization of compressed sensing-based radio interferometric imaging: hyperparameter selection
Optimization of compressed sensing-based radio interferometric imaging: hyperparameter selection Open
View article: Imbalanced Data Classification Based on Improved Random-SMOTE and Feature Standard Deviation
Imbalanced Data Classification Based on Improved Random-SMOTE and Feature Standard Deviation Open
Oversampling techniques are widely used to rebalance imbalanced datasets. However, most of the oversampling methods may introduce noise and fuzzy boundaries for dataset classification, leading to the overfitting phenomenon. To solve this p…
View article: Prompt-Driven Dynamic Object-Centric Learning for Single Domain Generalization
Prompt-Driven Dynamic Object-Centric Learning for Single Domain Generalization Open
Single-domain generalization aims to learn a model from single source domain data to achieve generalized performance on other unseen target domains. Existing works primarily focus on improving the generalization ability of static networks.…
View article: An Accurate and Trustworthy Deep Learning Approach for Bladder Tumor Segmentation with Uncertainty Estimation
An Accurate and Trustworthy Deep Learning Approach for Bladder Tumor Segmentation with Uncertainty Estimation Open
View article: Exploration of new media operation and brand promotion strategy in the era of artificial intelligence
Exploration of new media operation and brand promotion strategy in the era of artificial intelligence Open
This paper proposes a new evaluation model for the current situation and challenges of further media communication of enterprise brands through diversified publicity. A comprehensive evaluation model based on AHP-EWM-TOPSIS is constructed …
View article: Feature selection via a multi-swarm salp swarm algorithm
Feature selection via a multi-swarm salp swarm algorithm Open
Feature selection (FS) is a promising pre-processing step before performing most data engineering tasks. The goal of it is to select the optimal feature subset with promising quality from the original high-dimension feature space. The Salp…
View article: Trusting Language Models in Education
Trusting Language Models in Education Open
Language Models are being widely used in Education. Even though modern deep learning models achieve very good performance on question-answering tasks, sometimes they make errors. To avoid misleading students by showing wrong answers, it is…
View article: Rule Learning over Knowledge Graphs: A Review
Rule Learning over Knowledge Graphs: A Review Open
Compared to black-box neural networks, logic rules express explicit knowledge, can provide human-understandable explanations for reasoning processes, and have found their wide application in knowledge graphs and other downstream tasks. As …
View article: An improved SMOTE based on center offset factor and synthesis strategy for imbalanced data classification
An improved SMOTE based on center offset factor and synthesis strategy for imbalanced data classification Open
It is an enormous challenge for imbalanced data learning in the field of machine learning. To construct balanced datasets, oversampling techniques have been studied extensively. However, many oversampling methods suffer from introducing no…
View article: Kai-Xin-San regulates synaptic plasticity through calcium signaling to alleviate symptoms of depression-like behavioral disorders in mice
Kai-Xin-San regulates synaptic plasticity through calcium signaling to alleviate symptoms of depression-like behavioral disorders in mice Open
View article: OSLAT: Open Set Label Attention Transformer for Medical Entity Retrieval and Span Extraction
OSLAT: Open Set Label Attention Transformer for Medical Entity Retrieval and Span Extraction Open
Medical entity span extraction and linking are critical steps for many healthcare NLP tasks. Most existing entity extraction methods either have a fixed vocabulary of medical entities or require span annotations. In this paper, we propose …
View article: MEDCOD: A Medically-Accurate, Emotive, Diverse, and Controllable Dialog\n System
MEDCOD: A Medically-Accurate, Emotive, Diverse, and Controllable Dialog\n System Open
We present MEDCOD, a Medically-Accurate, Emotive, Diverse, and Controllable\nDialog system with a unique approach to the natural language generator module.\nMEDCOD has been developed and evaluated specifically for the history taking\ntask.…
View article: MEDCOD: A Medically-Accurate, Emotive, Diverse, and Controllable Dialog System
MEDCOD: A Medically-Accurate, Emotive, Diverse, and Controllable Dialog System Open
We present MEDCOD, a Medically-Accurate, Emotive, Diverse, and Controllable Dialog system with a unique approach to the natural language generator module. MEDCOD has been developed and evaluated specifically for the history taking task. It…
View article: Harnessing the power of artificial intelligence to transform hearing healthcare and research
Harnessing the power of artificial intelligence to transform hearing healthcare and research Open
View article: Multimodal Intelligence: Representation Learning, Information Fusion, and Applications
Multimodal Intelligence: Representation Learning, Information Fusion, and Applications Open
Deep learning methods have revolutionized speech recognition, image\nrecognition, and natural language processing since 2010. Each of these tasks\ninvolves a single modality in their input signals. However, many applications\nin the artifi…
View article: Attentive Tensor Product Learning
Attentive Tensor Product Learning Open
This paper proposes a novel neural architecture — Attentive Tensor Product Learning (ATPL) — to represent grammatical structures of natural language in deep learning models. ATPL exploits Tensor Product Representations (TPR), a structured …
View article: From Caesar Cipher to Unsupervised Learning: A New Method for Classifier Parameter Estimation
From Caesar Cipher to Unsupervised Learning: A New Method for Classifier Parameter Estimation Open
Many important classification problems, such as object classification, speech recognition, and machine translation, have been tackled by the supervised learning paradigm in the past, where training corpora of parallel input-output pairs ar…
View article: Question-Answering with Grammatically-Interpretable Representations
Question-Answering with Grammatically-Interpretable Representations Open
We introduce an architecture, the Tensor Product RecurrentNetwork (TPRN). In our application of TPRN, internal representations—learned by end-to-end optimization in a deep neural network performing a textual question-answering(QA) task—can…
View article: BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems
BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems Open
We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawing Monte Carlo samples from a Bayes-by-Backprop neural netw…
View article: Different osteotomy solutions influence future total knee arthroplasty in patients with multiapical lower extremity deformities
Different osteotomy solutions influence future total knee arthroplasty in patients with multiapical lower extremity deformities Open
Background: Although osteotomy achieves success on correction of lower extremity deformities, a future total knee arthroplasty (TKA) is sometimes inevitable. The zigzagged fumer and tibia after previous osteotomy can somehow influence TKA…
View article: Attentive Tensor Product Learning for Language Generation and Grammar Parsing.
Attentive Tensor Product Learning for Language Generation and Grammar Parsing. Open
This paper proposes a new architecture - Attentive Tensor Product Learning (ATPL) - to represent grammatical structures in deep learning models. ATPL is a new architecture to bridge this gap by exploiting Tensor Product Representations (TP…
View article: Attentive Tensor Product Learning
Attentive Tensor Product Learning Open
This paper proposes a new architecture - Attentive Tensor Product Learning (ATPL) - to represent grammatical structures in deep learning models. ATPL is a new architecture to bridge this gap by exploiting Tensor Product Representations (TP…
View article: Tensor Product Generation Networks for Deep NLP Modeling
Tensor Product Generation Networks for Deep NLP Modeling Open
Qiuyuan Huang, Paul Smolensky, Xiaodong He, Li Deng, Dapeng Wu. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 2018.
View article: BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems
BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems Open
We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawing Monte Carlo samples from a Bayes-by-Backprop neural netw…
View article: Challenges and Open Problems in Signal Processing: Panel Discussion Summary from ICASSP 2017 [Panel and Forum]
Challenges and Open Problems in Signal Processing: Panel Discussion Summary from ICASSP 2017 [Panel and Forum] Open
This column summarizes the panel on open problems in signal processing, which took place on 5 March 2017 at the International Conference on Acoustics, Speech, and Signal Processing (ICASSP) in New Orleans, Louisiana. The goal of the panel …
View article: A Neural-Symbolic Approach to Natural Language Tasks.
A Neural-Symbolic Approach to Natural Language Tasks. Open
Deep learning (DL) has in recent years been widely used in natural language processing (NLP) applications due to its superior performance. However, while natural languages are rich in grammatical structure, DL has not been able to explicit…