Papers by Lifang He

4 papers
Mixup-Transformer: Dynamic Data Augmentation for NLP Tasks (2020.coling-main)

Copied to clipboard

Challenge: Recent work on data augmentation techniques that interpolate inputs and labels shows strong effectiveness in image classification.
Approach: They propose to integrate mixup to transformer-based pre-trained architecture for NLP tasks while keeping the whole end-to-end training system.
Outcome: The proposed framework improves on GLUEbenchmark and transformer-based learning models while keeping the whole end-to-end training system.
Scattered Hypothesis Generation for Open-Ended Event Forecasting (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for event forecasting focus on the most probable outcomes, neglecting the intrinsic uncertainty of real-world events.
Approach: They propose a reinforcement learning framework that optimizes inclusiveness and diversity of the hypothesis by integrating validity-gated score into the overall objective.
Outcome: The proposed framework outperforms baselines on two real-world benchmark datasets.
HETFORMER: Heterogeneous Transformer with Sparse Attention for Long-Text Extractive Summarization (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods for summarizing semantic graph structure from raw text are cumbersome and inefficient for long-text documents.
Approach: They propose a Transformer-based pre-trained model with multi-granularity sparse attentions for long-text extractive summarization.
Outcome: The proposed model performs state-of-the-art on single- and multi-document summarization tasks while using less memory and fewer parameters.
Hierarchical Bi-Directional Self-Attention Networks for Paper Review Rating Recommendation (2020.coling-main)

Copied to clipboard

Challenge: Existing methods for review rating prediction ignore hierarchies among data . paper review rating predictions are important for improving paper review process .
Approach: They propose a Hierarchical bi-directional self-attention Network framework for paper review rating prediction and recommendation . they leverage hierarchical structure of paper reviews with three levels of encoders .
Outcome: The proposed approach can be used to make an effective decision-making tool for the academic paper review process.

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