Yi Chen

Character-based parsing with convolutional neural network

2015 · International Conference on Artificial Intelligence

We describe a novel convolutional neural network architecture with k-max pooling layer that is able to successfully recover the structure of Chinese sentences. This network can capture active features for unseen segments of a sentence …

Learning Context-Specific Word/Character Embeddings

2017 · Proceedings of the AAAI Conference on Artificial Intelligence

Unsupervised word representations have demonstrated improvements in predictive generalization on various NLP tasks. Most of the existing models are in fact good at capturing the relatedness among words rather than their ''genuine'' similarity because the …

Design and implementation of innovation and entrepreneurship management system based on WEB

2022

During the reform of talent mode in colleges and universities, to improve the level of innovation and entrepreneurship of college students, relevant training plans have begun to be promoted and implemented nationwide. Entrepreneurship for college …

Few-shot Question Answering with Entity-Aware Prompt

2023

Providing simple task descriptions or prompts in natural language for large pre-trained language models yields impressive few-shot learning results in different tasks, such as text classification, knowledge probing, machine translation, and named entity recognition. In …

Boosting Service Workflow Reliability Through Enhanced Detection of Artifact Anomalies

2025

Enterprises widely use workflow management systems (WfMS) to generate service-based workflows by orchestrating existing services. Modern WMS enables nontechnical users to create and modify workflows via graphical tools and natural language commands. Incorrect artifact operations, …

An Improved Spatial Clustering Method for Automatic Detection of Active Geohazards in Lanzhou

2025 · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

Spaceborne interferometric synthetic aperture radar (InSAR) has been extensively employed to detect surface displacements. However, the automatic extraction of locations and boundaries of active geohazards from surface displacement data remains a significant research challenge. In …