Xiaolong Wang

VRCA: a clustering algorithm for massive amount of texts

2015 · International Conference on Artificial Intelligence

There are lots of texts appearing in the web every day. This fact enables the amount of texts in the web to explode. Therefore, how to deal with large-scale text collection becomes more and more …

Gated Semantic Difference Based Sentence Semantic Equivalence Identification

2020 · IEEE/ACM Transactions on Audio Speech and Language Processing

This article proposes a novel sentence semantic equivalence identification (SSEI) method by using the semantic difference features between sentences. The lexical differences of a sentence pair are first extracted, and the bidirectional long short term …

Generalization in Reinforcement Learning by Soft Data Augmentation

2020 · arXiv (Cornell University)

Extensive efforts have been made to improve the generalization ability of Reinforcement Learning (RL) methods via domain randomization and data augmentation. However, as more factors of variation are introduced during training, optimization becomes increasingly challenging, …

KEoG: A knowledge-aware edge-oriented graph neural network for document-level relation extraction

2020

Document-level relation extraction (RE) has attracted more and more attentions recently. Edge-oriented graph neural network (EoG) is a new neural network exhibiting greater potential than previous node-oriented graph neural networks for document-level RE. In this …

Understanding the deterrence effect of punishment for marine information security policies non-compliance

2022 · Journal of Ocean Engineering and Science

In the organizational setting of marine engineering, a significant number of information security incidents have been arised from the employees’ failure to comply with the information security policies (ISPs). This may be treated as a …

Learning Natural Language Inference using Bidirectional LSTM model and Inner-Attention

2016 · arXiv (Cornell University)

In this paper, we proposed a sentence encoding-based model for recognizing text entailment. In our approach, the encoding of sentence is a two-stage process. Firstly, average pooling was used over word-level bidirectional LSTM (biLSTM) to …