Membership inference (MI) attacks threaten user privacy through determin...
Training language models to learn from human instructions for zero-shot
...
Despite the success of text-to-text pre-trained models in various natura...
Existing reference-free metrics have obvious limitations for evaluating
...
Large-scale pre-training has shown remarkable performance in building
op...
Distinct is a widely used automatic metric for evaluating the diversity ...
Dialogue safety problems severely limit the real-world deployment of neu...
Although pre-trained language models have remarkably enhanced the genera...
Existing pre-trained models for knowledge-graph-to-text (KG-to-text)
gen...
Autoregressive models have been widely used in unsupervised text style
t...
Unsupervised commonsense question answering is appealing since it does n...
Recommending appropriate algorithms to a classification problem is one o...
Pre-trained Language Models (PLMs) have proven to be beneficial for vari...
Despite the success of generative pre-trained language models on a serie...
The advancements of neural dialogue generation models show promising res...
Open-domain question answering (QA) aims to find the answer to a questio...
Most existing approaches for goal-oriented dialogue policy learning used...
The research of knowledge-driven conversational systems is largely limit...
Due to the significance and value in human-computer interaction and natu...
To advance multi-domain (cross-domain) dialogue modeling as well as alle...
In text generation evaluation, many practical issues, such as inconsiste...
Story generation, namely generating a reasonable story from a leading
co...
In spite of great advancements of machine reading comprehension (RC),
ex...
Most of the existing pre-trained language representation models neglect ...
Automatic defect recognition is one of the research hotspots in steel
pr...
Most of the existing generative adversarial networks (GAN) for text
gene...
Existing neural methods for data-to-text generation are still struggling...
There is a resurgent interest in developing intelligent open-domain dial...
Advertising (ad for short) keyword suggestion is important for sponsored...
A verification code is an automated test method used to distinguish betw...
In this paper we address a task of relation mention extraction from nois...
Ranking is a fundamental and widely studied problem in scenarios such as...
Existing relation classification methods that rely on distant supervisio...
Dialogue management (DM) decides the next action of a dialogue system
ac...
Multi-relation Question Answering is a challenging task, due to the
requ...
Endowing a chatbot with personality or an identity is quite challenging ...
Perception and expression of emotion are key factors to the success of
d...
Sentiment understanding has been a long-term goal of AI in the past deca...
Knowledge representation is an important, long-history topic in AI, and ...
Knowledge graph embedding aims at offering a numerical knowledge
represe...
Knowledge representation is a major topic in AI, and many studies attemp...
Recently, knowledge graph embedding, which projects symbolic entities an...