Neural machine translation: A review
F Stahlberg - Journal of Artificial Intelligence Research, 2020 - jair.org
The field of machine translation (MT), the automatic translation of written text from one
natural language into another, has experienced a major paradigm shift in recent years …
natural language into another, has experienced a major paradigm shift in recent years …
Subword regularization: Improving neural network translation models with multiple subword candidates
T Kudo - arXiv preprint arXiv:1804.10959, 2018 - arxiv.org
Subword units are an effective way to alleviate the open vocabulary problems in neural
machine translation (NMT). While sentences are usually converted into unique subword …
machine translation (NMT). While sentences are usually converted into unique subword …
Vuldeepecker: A deep learning-based system for vulnerability detection
The automatic detection of software vulnerabilities is an important research problem.
However, existing solutions to this problem rely on human experts to define features and …
However, existing solutions to this problem rely on human experts to define features and …
Chinese relation extraction with multi-grained information and external linguistic knowledge
Chinese relation extraction is conducted using neural networks with either character-based
or word-based inputs, and most existing methods typically suffer from segmentation errors …
or word-based inputs, and most existing methods typically suffer from segmentation errors …
VDSimilar: Vulnerability detection based on code similarity of vulnerabilities and patches
H Sun, L Cui, L Li, Z Ding, Z Hao, J Cui, P Liu - Computers & Security, 2021 - Elsevier
Vulnerability detection using machine learning is a hot topic in improving software security.
However, existing works formulate detection as a classification problem, which requires a …
However, existing works formulate detection as a classification problem, which requires a …
Patchdb: A large-scale security patch dataset
Security patches, embedding both vulnerable code and the corresponding fixes, are of great
significance to vulnerability detection and software maintenance. However, the existing …
significance to vulnerability detection and software maintenance. However, the existing …
Porous lattice transformer encoder for Chinese NER
Incorporating lexicons into character-level Chinese NER by lattices is proven effective to
exploitrich word boundary information. Previous work has extended RNNs to consume …
exploitrich word boundary information. Previous work has extended RNNs to consume …
ASR n-best fusion nets
Current spoken language understanding systems heavily rely on the best hypothesis (ASR 1-
best) generated by automatic speech recognition, which is used as the input for downstream …
best) generated by automatic speech recognition, which is used as the input for downstream …