Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks113 from public data
- 496
- Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models184
This paper finds that it is possible to hack the model in a data-free way by modifying one single word embedding vector, with almost no accuracy sacrificed on clean samples.
- KQA Pro: A Dataset with Explicit Compositional Programs for Complex Question Answering over Knowledge Base154
Experimental results show that state-of-the-art KBQA methods cannot achieve promising results on KQA Pro as on current datasets, which suggests that K QA Pro is challenging and Complex KBZA requires further research efforts.
- 114
- ChipGAN97
The advantages in visual quality compared with state-of-the-art networks and high stylization perceptual study scores show the effectiveness of the proposed ChipGAN, an end-to-end Generative Adversarial Network based architecture for photo to Chinese ink wash painting style transfer.
- BERT-MK: Integrating Graph Contextualized Knowledge into Pre-trained Language Models94
Experimental results demonstrate that the proposed model achieves the state-of-the-art performance on several medical NLP tasks, and the improvement above MedERNIE indicates that graph contextualized knowledge is beneficial.
- Pretrain-KGE: Learning Knowledge Representation from Pretrained Language Models89
This work presents a universal training framework named Pretrain-KGE consisting of three phases: semantic-based fine-tuning phase, knowledge extracting phase and KGE training phase, which can improve results over KGE models, especially on solving the low-resource problem.
- FHDe2Net: Full High Definition Demoireing Network76
The proposed Full High Definition Demoir´eing Network (FHDe 2 Net) consists of a global to local cascaded removal branch to eradicate multi-scale moir´e patterns and a frequency based high-resolution content separation branch to retain details.
- Classifying medical relations in clinical text via convolutional neural networks73
This study proposes a convolutional neural network architecture with a multi-pooling operation for medical relation classification on clinical records and explores a loss function with a category-level constraint matrix.
- Building a comprehensive syntactic and semantic corpus of Chinese clinical texts66
A comprehensive corpus with its NLP modules constructed, providing a foundation for further study of applying NLP techniques to Chinese texts in the clinical domain, has a number of limitations.
- CRFs based de-identification of medical records53
A novel de-identifier, WI-deId, based on conditional random fields (CRFs) is proposed, which tokenizes the medical records using regular expressions and an off-the-shelf tokenizer, and three groups of features are extracted to train the de-Identifier model.
- Spectral–Spatial Anomaly Detection of Hyperspectral Data Based on Improved Isolation Forest47
The proposed IIF is a modified version of the Isolation Forest (iForest) algorithm, which addresses the poor performance of iForest in detecting local anomalies and anomaly detection in high-dimensional data, and proposes a spectral–spatial anomaly detector based on IIF (SSIIFD) to make full use of global and local information, as well as spectral and spatial information.
- A Framework for Solving Explicit Arithmetic Word Problems and Proving Plane Geometry Theorems44
This paper presents a framework for solving math problems stated in a natural language (NL) and applies the framework to develop algorithms for solving explicit arithmetic word problems and proving plane geometry theorems.
- 39
- Ship Detection in Panchromatic Optical Remote Sensing Images Based on Visual Saliency and Multi-Dimensional Feature Description36
A novel visual saliency detection method based on a hyper-complex Fourier transform of a quaternion to locate regions of interest (ROIs), which can improve the accuracy of the subsequent discrimination process for panchromatic images, compared with the phase spectrum quaternary Fouriertransform (PQFT) method.
- De-identification of medical records using conditional random fields and long short-term memory networks34
Two participating systems based on conditional random fields and long short-term memory networks are described, based on sentence detection and tokenization before de-identification of psychiatric evaluation records.
- 30
- 29
- 29
- 27
- 27
- 23
- 22
- 22
- 21
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.