Wenhui Wang

Unified Language Model Pre-training for Natural Language Understanding and Generation

2019 · arXiv (Cornell University)

This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks. The model is pre-trained using three types of language modeling tasks: unidirectional, bidirectional, …

Buffer Overflow Vulnerability Detection Based on Static Analysis-assisted Symbolic Execution

2023

Buffer overflow is a common exploitable high-risk vulnerability that can lead to arbitrary code execution, thus effective detection of buffer overflow vulnerability is of utmost importance for developers, enabling timely remendiation. Symbolic execution is a …

Gated Self-Matching Networks for Reading Comprehension and Question Answering

2017

In this paper, we present the gated selfmatching networks for reading comprehension style question answering, which aims to answer questions from a given passage. We first match the question and passage with gated attention-based recurrent …