Topic models have evolved from conventional Bayesian probabilistic model...
Dialogue acts (DAs) can represent conversational actions of tutors or
st...
Dialogue Acts (DAs) can be used to explain what expert tutors do and wha...
Neural processes (NPs) have brought the representation power of parametr...
Enabled by multi-head self-attention, Transformer has exhibited remarkab...
Paralinguistic speech processing is important in addressing many issues,...
Knowledge tracing (KT) aims to leverage students' learning histories to
...
Current work in named entity recognition (NER) uses either cross entropy...
Domain adaptation is an effective solution to data scarcity in low-resou...
Recently, discrete latent variable models have received a surge of inter...
Uncertainty estimation is essential to make neural networks trustworthy ...
Transformer has obtained promising results on cognitive speech signal
pr...
We study acquisition functions for active learning (AL) for text
classif...
Multilingual Neural Machine Translation (MNMT) trains a single NMT model...
Neural topic models (NTMs) apply deep neural networks to topic modelling...
This paper proposes a transformer over transformer framework, called
Tra...
This paper presents an unsupervised extractive approach to summarize
sci...
Continual learning (CL) refers to a machine learning paradigm that using...
Graph neural networks (GNNs) are important tools for transductive learni...
Extreme multi-label classification (XML) is becoming increasingly releva...
Topic modelling has been a successful technique for text analysis for al...
Knowledge distillation (KD), as an efficient and effective model compres...
Few/Zero-shot learning is a big challenge of many classifications tasks,...
Obtaining training data for multi-document summarization (MDS) is time
c...
Matrix factorization (MF) has been widely applied to collaborative filte...
Non-negative tensor factorization models enable predictive analysis on c...
Many applications, such as text modelling, high-throughput sequencing, a...
Recently, considerable research effort has been devoted to developing de...
Probabilistic topic models are widely used to discover latent topics in
...
Besides the text content, documents and their associated words usually c...
Relational data are usually highly incomplete in practice, which inspire...
The Dirichlet process and its extension, the Pitman-Yor process, are
sto...