Joint span and token framework for few-shot named entity recognition
2023
Few-shot Named Entity Recognition (NER) is a challenging task that involves identifying new entity types using a limited number of labeled instances for training. Currently, the majority of Few-shot...
Share article
MOTT: A new model for multi-object tracking based on green learning paradigm
2023
Multi-object tracking (MOT) is one of the most essential and challenging tasks in computer vision (CV). Unlike object detectors, MOT systems nowadays are more complicated and consist of several neural...
Share article
Multi-grained hypergraph interest modeling for conversational recommendation
2023
Conversational recommender system (CRS) interacts with users through multi-turn dialogues in natural language, which aims to provide high-quality recommendations for user’s instant information need....
Share article
A unified network embedding algorithm for multi-type similarity measures
2023
Traditional network embedding aims to learn representations by capturing a predefined vertex-to-vertex similarity measure. However, in practice, there are different types of similarity measures (e.g.,...
Share article
Batch virtual adversarial training for graph convolutional networks
2023
We present batch virtual adversarial training (BVAT), a novel regularization method for graph convolutional networks (GCNs). BVAT addresses the issue that GCNs do not ensure the smoothness of the model’s...
Share article
AdaDS: Adaptive data selection for accelerating pre-trained language model knowledge distillation
2023
Knowledge distillation (KD) is a widely used method for transferring knowledge from large teacher models to computationally efficient student models. Unfortunately, the computational cost of KD becomes...
Share article
A survey on complex factual question answering
2023
Answering complex factual questions has drawn a lot of attention. Researchers leverage various data sources to support complex QA, such as unstructured texts, structured knowledge graphs and relational...
Share article
Language as a latent sequence: Deep latent variable models for semi-supervised paraphrase generation
2023
This paper explores deep latent variable models for semi-supervised paraphrase generation, where the missing target pair for unlabelled data is modelled as a latent paraphrase sequence. We present a...
Share article
Learning fair representations via an adversarial framework
2023
Fairness has become a central issue for our research community as classification algorithms are adopted in societally critical domains such as recidivism prediction and loan approval. In this work,...
Share article
Is Chinese Spelling Check ready? Understanding the correction behavior in real-world scenarios
2023
The task of Chinese Spelling Check (CSC) is crucial for identifying and rectifying spelling errors in Chinese texts. While prior work in this domain has predominantly relied on benchmarks such as SIGHAN...
Share article
Semantic graph based topic modelling framework for multilingual fake news detection
2023
Fake news detection is one of the most alluring problems that has grabbed the interest of Machine Learning (ML) and Natural Language Processing (NLP) experts in recent years. The majority of existing...
Share article
Word sense induction with agglomerative clustering and mutual information maximization
2023
Word sense induction (WSI) is a challenging problem in natural language processing that involves the unsupervised automatic detection of a word’s senses (i.e., meanings). Recent work achieves significant...
Share article
Sarcasm detection using news headlines dataset
2023
Sarcasm has been an elusive concept for humans. Due to interesting linguistic properties, sarcasm detection has gained traction of the Natural Language Processing (NLP) research community in the past...
Share article
Graph-based methods for cervical cancer segmentation: Advancements, limitations, and future directions
2023
Cervical cancer remains a significant health concern worldwide, where precise segmentation of cervical lesions is integral for effective diagnosis and treatment planning. This systematic review critically...
Share article
MONEY: Ensemble learning for stock price movement prediction via a convolutional network with adversarial hypergraph model
2023
Stock price prediction is challenging in financial investment, with the AI boom leading to increased interest from researchers. Despite these recent advances, many studies are limited to capturing the...
Share article
Interactive active learning for fairness with partial group label
2023
The rapid development of AI technologies has found numerous applications across various domains in human society. Ensuring fairness and preventing discrimination are critical considerations in the development...
Share article
Restricted orthogonal gradient projection for continual learning
2023
Continual learning aims to avoid catastrophic forgetting and effectively leverage learned experiences to master new knowledge. Existing gradient projection approaches impose hard constraints on the...
Share article
UPRec: User-aware Pre-training for sequential Recommendation
2023
Recent years witness the success of pre-trained models to alleviate the data sparsity problem in recommender systems. However, existing pre-trained models for recommendation mainly focus on leveraging...
Share article
CAILIE 1.0: A dataset for Challenge of AI in Law - Information Extraction V1.0
2022
Legal information extraction requires identifying and classifying legal elements from specific legal documents. Considering that information extraction is mainly regarded as the first step in natural...
Share article
HSSDA: Hierarchical relation aided Semi-Supervised Domain Adaptation
2022
The mainstream domain adaptation (DA) methods transfer the supervised source domain knowledge to the unsupervised or semi-supervised target domain, so as to assist the classification task in the target...
Share article
Optimized separable convolution: Yet another efficient convolution operator
2022
The convolution operation is the most critical component in recent surge of deep learning research. Conventional 2D convolution needs O(C2K2) parameters to represent, where C is the channel size and...
Share article
