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 …

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 …

In recent years, machine learning technology has made great improvements in social
networks applications such as social network recommendation systems, sentiment analysis …

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 …

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 …

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 …

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 …

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 …

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 …

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 …