KNN-contrastive learning for out-of-domain intent classification

Y Zhou, P Liu, X Qiu - Proceedings of the 60th Annual Meeting of …, 2022 - aclanthology.org
Abstract The Out-of-Domain (OOD) intent classification is a basic and challenging task for
dialogue systems. Previous methods commonly restrict the region (in feature space) of In …

Contrastive learning-enhanced nearest neighbor mechanism for multi-label text classification

R Wang, X Dai - Proceedings of the 60th Annual Meeting of the …, 2022 - aclanthology.org
Abstract Multi-Label Text Classification (MLTC) is a fundamental and challenging task in
natural language processing. Previous studies mainly focus on learning text representation …

Mask-guided BERT for few-shot text classification

W Liao, Z Liu, H Dai, Z Wu, Y Zhang, X Huang, Y Chen… - Neurocomputing, 2024 - Elsevier
Transformer-based language models have achieved significant success in various domains.
However, the data-intensive nature of the transformer architecture requires much labeled …

Relation extraction as open-book examination: Retrieval-enhanced prompt tuning

X Chen, L Li, N Zhang, C Tan, F Huang, L Si… - Proceedings of the 45th …, 2022 - dl.acm.org
Pre-trained language models have contributed significantly to relation extraction by
demonstrating remarkable few-shot learning abilities. However, prompt tuning methods for …

Coarse-to-fine few-shot learning for named entity recognition

R Ma, Z Lin, X Chen, X Zhou, J Wang… - Findings of the …, 2023 - aclanthology.org
Abstract Recently, Few-shot Named Entity Recognition has received wide attention with the
growing need for NER models to learn new classes with minimized annotation costs …

Feature-level debiased natural language understanding

Y Lyu, P Li, Y Yang, M de Rijke, P Ren… - Proceedings of the …, 2023 - ojs.aaai.org
Natural language understanding (NLU) models often rely on dataset biases rather than
intended task-relevant features to achieve high performance on specific datasets. As a …

Mere contrastive learning for cross-domain sentiment analysis

Y Luo, F Guo, Z Liu, Y Zhang - arXiv preprint arXiv:2208.08678, 2022 - arxiv.org
Cross-domain sentiment analysis aims to predict the sentiment of texts in the target domain
using the model trained on the source domain to cope with the scarcity of labeled data …

Insights into wheat science: a bibliometric review using unsupervised machine learning techniques

M Pérez-Pérez, M Ribeiro, F Fdez-Riverola… - Journal of Cereal …, 2024 - Elsevier
Wheat (Triticum spp.) has been one of the most important cereal crops, serving as a source
of protein and energy in the human diet. It remains a vital component of global food security …

EmFore: Online Learning of Email Folder Classification Rules

M Singh, J Cambronero, S Gulwani, V Le… - Proceedings of the …, 2023 - dl.acm.org
Modern email clients support predicate-based folder assignment rules that can automatically
organize emails. Unfortunately, users still need to write these rules manually. Prior machine …

Topic-Aware Contrastive Learning and K-Nearest Neighbor Mechanism for Stance Detection

Y Sun, J Lu, L Wang, S Li, N Huang - Proceedings of the 32nd ACM …, 2023 - dl.acm.org
The goal of stance detection is to automatically recognize the author's expressed attitude in
text towards a given target. However, social media users often express themselves briefly …