Long-form question answering (LFQA) aims at answering complex, open-ende...
Textual adversarial samples play important roles in multiple subfields o...
In linguistics, a sememe is defined as the minimum semantic unit of
lang...
It is very common to use quotations (quotes) to make our writings more
e...
Backdoor attacks are a kind of emergent security threat in deep learning...
Adversarial attacks and backdoor attacks are two common security threats...
Recent studies show that neural natural language processing (NLP) models...
Poetry is one of the most important art forms of human languages. Recent...
Conventional tokenization methods for Chinese pretrained language models...
A sememe is defined as the minimum semantic unit in linguistics. Sememe
...
Backdoor attacks are a kind of insidious security threat against machine...
Due to the success of pre-trained models (PTMs), people usually fine-tun...
Pre-trained Language Models (PLMs) have proven to be beneficial for vari...
Backdoor attacks, which are a kind of emergent training-time threat to d...
Adversarial attacking aims to fool deep neural networks with adversarial...
Textual adversarial attacking has received wide and increasing attention...
Country image has a profound influence on international relations and
ec...
Sememes, defined as the minimum semantic units of human languages in
lin...
A sememe is defined as the minimum semantic unit of human languages. Sem...
Word Sense Disambiguation (WSD), which aims to identify the correct sens...
Semantic compositionality (SC) refers to the phenomenon that the meaning...
Word similarity computation is a widely recognized task in the field of
...
In this paper, we present an open sememe-based lexical knowledge base
Op...