Papers by Haiyan Ning

2 papers
VAEGPT-Sim: Improving Sentence Representation with Limited Corpus Using Gradually-Denoising VAE (2024.findings-acl)

Copied to clipboard

Challenge: Text embedding requires a highly efficient method for training domain-specific models on limited corpora.
Approach: They propose a model that combines a denoising variational autoencoder with a target-specific discriminator to generate synonymous sentences that closely resemble human language.
Outcome: The proposed model surpasses ConSERT by 2.8 points in small-dataset training on STS benchmarks.
HMCL: Task-Optimal Text Representation Adaptation through Hierarchical Contrastive Learning (2025.findings-emnlp)

Copied to clipboard

Challenge: Hierarchical Multilevel Contrastive Learning (HMCL) improves text representation for general large language models.
Approach: a new contrastive learning framework is developed to improve general large language models . HMCL integrates 3-level semantic differentiation and unifies contrastive and pair classification into a strategy .
Outcome: HMCL outperforms unsupervised methods and supervised fine-tuning approaches in multi-domain and multilingual benchmarks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations