Cross-level feature aggregation network for polyp segmentation
Accurate segmentation of polyps from colonoscopy images plays a critical role in the
diagnosis and cure of colorectal cancer. Although effectiveness has been achieved in the …
diagnosis and cure of colorectal cancer. Although effectiveness has been achieved in the …
Malcom: Generating malicious comments to attack neural fake news detection models
In recent years, the proliferation of so-called “fake news” has caused much disruptions in
society and weakened the news ecosystem. Therefore, to mitigate such problems …
society and weakened the news ecosystem. Therefore, to mitigate such problems …
Adversarial machine learning on social network: A survey
S Guo, X Li, Z Mu - Frontiers in Physics, 2021 - frontiersin.org
In recent years, machine learning technology has made great improvements in social
networks applications such as social network recommendation systems, sentiment analysis …
networks applications such as social network recommendation systems, sentiment analysis …
Robust backed-off estimation of out-of-vocabulary embeddings
N Fukuda, N Yoshinaga… - Findings of the …, 2020 - aclanthology.org
Abstract Out-of-vocabulary (oov) words cause serious troubles in solving natural language
tasks with a neural network. Existing approaches to this problem resort to using subwords …
tasks with a neural network. Existing approaches to this problem resort to using subwords …
Context-aware stand-alone neural spelling correction
Existing natural language processing systems are vulnerable to noisy inputs resulting from
misspellings. On the contrary, humans can easily infer the corresponding correct words from …
misspellings. On the contrary, humans can easily infer the corresponding correct words from …
Automatic task requirements writing evaluation via machine reading comprehension
Task requirements (TRs) writing is an important question type in Key English Test and
Preliminary English Test. A TR writing question may include multiple requirements and a …
Preliminary English Test. A TR writing question may include multiple requirements and a …
Finite-context Indexing of Restricted Output Space for NLP Models Facing Noisy Input
NLP models excel on tasks with clean inputs, but are less accurate with noisy inputs. In
particular, character-level noise such as human-written typos and adversarially-engineered …
particular, character-level noise such as human-written typos and adversarially-engineered …
[图书][B] Trustworthy machine learning: Learning under security, explainability and uncertainty constraints
TQ Le - 2022 - search.proquest.com
Trustworthy machine learning models are ones that not only have high accuracy but also
well perform under various realistic constraints, security threats, and are transparent to …
well perform under various realistic constraints, security threats, and are transparent to …
[PDF][PDF] FiRo: Finite-context Indexing of Restricted Output Space for NLP Models Facing Noisy Input
NLP models excel on tasks with clean inputs, but are less accurate with noisy inputs. In
particular, character-level noise such as humanwritten typos and adversarially-engineered …
particular, character-level noise such as humanwritten typos and adversarially-engineered …
[PDF][PDF] Sinhala spell correction: A novel benchmark with neural spell correction
Sinhala is a lowresource IndoAryan language primarily used by approximately 16 million
people living in the island nation of Sri Lanka. Sinhala is a morphologically rich language …
people living in the island nation of Sri Lanka. Sinhala is a morphologically rich language …