Ke Zhang

Named Entity Recognition Among Chinese MicroBlog Based on Cascaded CRF

2018

There are several features in the content of microblog, including brief, flexible, too colloquial, too much noise caused by informality terms (abbreviations, cyber words), etc. These features are new challenges for named entity recognition. In …

Controllable Length Control Neural Encoder-Decoder via Reinforcement Learning

2019 · arXiv (Cornell University)

Controlling output length in neural language generation is valuable in many scenarios, especially for the tasks that have length constraints. A model with stronger length control capacity can produce sentences with more specific length, however, …

Research on fast construction of question answering system based on target graph

2021

Aiming at the problems of chaotic structure and lack of visual query methods in small sample domain data, this paper proposes a fast construction framework of question answering (QA) system based on target graph. Firstly, …

Prescribed time convergence and robust zeroing neural network for solving time-varying linear matrix equation

2023 · International Journal of Computer Mathematics

Zeroing neural network offers a new solution method to solve the time-varying linear matrix equation. As an important component, the activation function directly affects the performance of zeroing neural network in solving time-varying linear matrix …

BUMP: A Benchmark of Unfaithful Minimal Pairs for Meta-Evaluation of Faithfulness Metrics

2023

Liang Ma, Shuyang Cao, Robert L Logan IV, Di Lu, Shihao Ran, Ke Zhang, Joel Tetreault, Alejandro Jaimes. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Deep Efficient Private Neighbor Generation for Subgraph Federated Learning

2024 · Society for Industrial and Applied Mathematics eBooks

Behemoth graphs are often fragmented and separately stored by multiple data owners as distributed subgraphs in many realistic applications. Without harming data privacy, it is natural to consider the subgraph federated learning (subgraph FL) scenario, …

Intelligent detection and recovery on satellite telemetry loss

2025 · Journal of Physics Conference Series

Abstract The article takes the high-orbit satellite telemetry system as an example. Firstly, the general system architecture of the satellite telemetry system is summarized. Then, starting from the system design characteristics, the recovery strategy analysis …

Dual Decomposition of Weights and Singular Value Low Rank Adaptation

2025 · arXiv (Cornell University)

Parameter-Efficient Fine-Tuning (PEFT) has emerged as a critical paradigm for adapting Large Language Models (LLMs) to downstream tasks, among which Low-rank Adaptation (LoRA) represents one of the most widely adopted methodologies. However, existing LoRA-based approaches …