Kai Wang

Correlation analysis between social network content and query intention

2015

Social network contains large amounts of user interests and preferences which may therefore help improve techniques for information retrieval, such as user profile construction and query expansion. By the manual annotation, we find that query …

Analysis on the Promotion of qDouble-tutor Systemq to Academic Atmosphere Construction in Universities

2016

Talent cultivation in universities are developing into a direction of high quality, high competency, diversification mode and compound type.Setting a tutorial system will exert a profound influence on cultivation of students' good ideological and moral …

On the Generation of Medical Question-Answer Pairs

2018 · arXiv (Cornell University)

Question answering (QA) has achieved promising progress recently. However, answering a question in real-world scenarios like the medical domain is still challenging, due to the requirement of external knowledge and the insufficient quantity of high-quality …

Novel robust generalized high-degree cubature kalman filter for transfer alignment

2018

A novel robust generalized high-degree Cubature Kalman filter (RGHCKF) for transfer alignment is proposed to solve the problem that the Cubature Kalman filter (CKF) declines in accuracy and even diverges when the non-Gaussian noise and …

CBOWRA: A Representation Learning Approach for Medication Anomaly Detection

2019

Electronic health record is an important source for clinical researches and applications, and errors inevitably occur in the data, which lead to severe damages to both patients and hospital services. One of such errors is …

Using Deep Time Delay Neural Network for Slot Filling in Spoken Language Understanding

2020 · Symmetry

Modeling the context of a target word is of fundamental importance in predicting the semantic label for slot filling task in Spoken Language Understanding (SLU). Although Recurrent Neural Network (RNN) has shown to successfully achieve …

On-Demand Generation of Entangled Photon Pairs in the Telecom C-Band with InAs Quantum Dots

2021 · ACS Photonics

High Resolution Image Download MS PowerPoint Slide Entangled photons are an integral part in quantum optics experiments and a key resource in quantum imaging, quantum communication, and photonic quantum information processing. Making this resource available …

Improving Non-native Word-level Pronunciation Scoring with Phone-level Mixup Data Augmentation and Multi-source Information

2022 · arXiv (Cornell University)

Deep learning-based pronunciation scoring models highly rely on the availability of the annotated non-native data, which is costly and has scalability issues. To deal with the data scarcity problem, data augmentation is commonly used for …

Reliable Label Correction is a Good Booster When Learning with Extremely Noisy Labels

2022 · arXiv (Cornell University)

Learning with noisy labels has aroused much research interest since data annotations, especially for large-scale datasets, may be inevitably imperfect. Recent approaches resort to a semi-supervised learning problem by dividing training samples into clean and …

RL4RS: A Real-World Dataset for Reinforcement Learning based Recommender System

2021 · arXiv (Cornell University)

Reinforcement learning based recommender systems (RL-based RS) aim at learning a good policy from a batch of collected data, by casting recommendations to multi-step decision-making tasks. However, current RL-based RS research commonly has a large …

Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models

2023 · arXiv (Cornell University)

Continual learning (CL) can help pre-trained vision-language models efficiently adapt to new or under-trained data distributions without re-training. Nevertheless, during the continual training of the Contrastive Language-Image Pre-training (CLIP) model, we observe that the model's …

SADA: Self-Adaptive Domain Adaptation From Black-Box Predictors

2024

Domain adaptation from black-box predictors aims to perform domain adaptation using predictions from a model trained on the source domain, thereby avoiding privacy issues associated with source domain data and enabling the training of a …

On LLM-Enhanced Mixed-Type Data Imputation with High-Order Message Passing

2025 · Proceedings of the VLDB Endowment

Missing data imputation, which aims to impute the missing values in the raw datasets, is crucial for modern data-driven models like large language models (LLMs). Despite its importance, existing solutions either 1) only support numerical …

External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation

2025 · arXiv (Cornell University)

Ads recommendation is a prominent service of online advertising systems and has been actively studied. Recent studies indicate that scaling-up and advanced design of the recommendation model can bring significant performance improvement. However, with a …