Papers by Peichao Lai

4 papers
Enhancing Unsupervised Sentence Embeddings via Knowledge-Driven Data Augmentation and Gaussian-Decayed Contrastive Learning (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for data augmentation neglect fine-grained knowledge, such as entities and quantities, leading to insufficient diversity and high data noise.
Approach: They propose a pipeline-based data augmentation method via LLMs and introduce the Gaussian-decayed gradient-assisted Contrastive Sentence Embedding (GCSE) model to enhance unsupervised sentence embeddings.
Outcome: The proposed method achieves state-of-the-art performance in semantic textual similarity tasks using fewer data samples and smaller LLMs.
Improving Low-Resource Sequence Labeling with Knowledge Fusion and Contextual Label Explanations (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to sequence labeling are limited due to the scarcity of domain-specific data and semantic distribution biases in domain-based contexts.
Approach: They propose a framework that integrates an LLM-based knowledge enhancement workflow with a span-based Knowledge Fusion for Rich and Efficient Extraction model.
Outcome: The proposed model achieves state-of-the-art performance on multiple domain-specific sequence labeling datasets and is highly efficient.
Quantum-inspired Language Model with Lindblad Master Equation and Interference Measurement for Sentiment Analysis (2024.naacl-long)

Copied to clipboard

Challenge: Quantum-inspired models have demonstrated superior performance in many downstream language tasks, such as question answering and sentiment analysis.
Approach: They propose a quantum-inspired neural network that integrates the Lindblad Master Equation to model the evolution process and the interferometry to the measurement process, providing more physical meaning to strengthen the interpretability.
Outcome: The proposed model outperforms existing models on sentiment analysis datasets and shows that it is more accurate and performs better than existing models.
PCBERT: Parent and Child BERT for Chinese Few-shot NER (2022.coling-1)

Copied to clipboard

Challenge: Existing approaches to improve model performance on few-shot or zero-shot datasets are not effective for Chinese few- shot NER.
Approach: They propose a prompt-based Parent and Child BERT for Chinese few-shot NER to train an annotating model on high-resource datasets and then discover more implicit labels on low-resourced datasets.
Outcome: The proposed model can be used on Weibo and other Chinese NER datasets and it is shown to be effective in few-shot learning.

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