Making moral judgments is an essential step toward developing ethical AI...
Recently, text watermarking algorithms for large language models (LLMs) ...
Time series are the primary data type used to record dynamic system
meas...
Previous question-answer pair generation methods aimed to produce fluent...
Reaction and retrosynthesis prediction are fundamental tasks in computat...
The non-Euclidean geometry of hyperbolic spaces has recently garnered
co...
Relation extraction (RE) tasks show promising performance in extracting
...
Multimodal relation extraction (MRE) is the task of identifying the sema...
Heterogeneous graph neural networks (HGNNs) can learn from typed and
rel...
Maximizing the user-item engagement based on vectorized embeddings is a
...
Relation extraction (RE) aims to extract potential relations according t...
Searching on bipartite graphs is basal and versatile to many real-world ...
Transferring prior knowledge from a source domain to the same or similar...
Trustworthy artificial intelligence (AI) technology has revolutionized d...
Multiple Instance Learning (MIL) and transformers are increasingly popul...
Drug combination therapy is a well-established strategy for disease trea...
Existing pre-training methods for extractive Question Answering (QA) gen...
Hyperbolic space is emerging as a promising learning space for represent...
Heterogeneous graph neural networks (HGNNs) were proposed for representa...
Information Extraction (IE) aims to extract structured information from
...
Graph-structured data are widespread in real-world applications, such as...
Incorporating knowledge graphs (KGs) as side information in recommendati...
Considering the prevalence of the power-law distribution in user-item
ne...
RNA structure determination and prediction can promote RNA-targeted drug...
The concept relatedness estimation (CRE) task is to determine whether tw...
Graph Neural Networks (GNNs) have attracted much attention due to their
...
Learning vectorized embeddings is at the core of various recommender sys...
Keyphrase generation is the task of automatically predicting keyphrases ...
In large-scale recommender systems, the user-item networks are generally...
Text revision refers to a family of natural language generation tasks, w...
Graph neural networks generalize conventional neural networks to
graph-s...
Due to the promising advantages in space compression and inference
accel...
Network quantization has gained increasing attention with the rapid grow...
Meta-learning has gained wide popularity as a training framework that is...
To alleviate data sparsity and cold-start problems of traditional recomm...
Aiming to alleviate data sparsity and cold-start problems of traditional...
We study controllable text summarization which allows users to gain cont...
Dialogue summarization aims to generate a summary that indicates the key...
Representation learning over temporal networks has drawn considerable
at...
In recent years, reference-based and supervised summarization evaluation...
Select-then-compress is a popular hybrid, framework for text summarizati...
Variational autoencoders (VAEs) have been widely applied for text modeli...
We present DistillFlow, a knowledge distillation approach to learning op...
Self-training has proven effective for improving NMT performance by
augm...
Deep semi-supervised learning is a fast-growing field with a range of
pr...
Dynamic graphs arise in a plethora of practical scenarios such as social...
Semi-supervised learning (SSL) has tremendous value in practice due to i...
In conversational machine reading, systems need to interpret natural lan...
Contributions: The Chinese University of Hong Kong (CUHK)-Jockey Club AI...
With the rapid development of biomedical software and hardware, a large
...