Papers by Guosheng Liang

2 papers
Learning distributed sentence vectors with bi-directional 3D convolutions (2020.coling-main)

Copied to clipboard

Challenge: Existing methods that render words or characters into images separately, but instead use text's visual features as input, we use 3-dimensional convolutions to learn distributed sentence representation.
Approach: They propose to use text's visual features as input to learn distributed sentence representation using 3-dimensional sentence tensors and multiple 3-dimensional convolutions with different lengths are applied to the sentence .
Outcome: The proposed model performs well on several downstream natural language processing tasks.
ThinkSwitcher: When to Think Hard, When to Think Fast (2025.findings-emnlp)

Copied to clipboard

Challenge: Large reasoning models excel at solving complex tasks by leveraging long chain-of-thought (CoT) reasoning.
Approach: They propose a framework that enables a single LRM to dynamically switch between short and long CoT modes based on task complexity.
Outcome: The proposed framework reduces computational cost by 20-30% while maintaining high accuracy on complex tasks.

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