Papers by Chenghao Jia

6 papers
SynET: Synonym Expansion using Transitivity (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to find synonyms from text corpora are distributed and pattern based, but they suffer from low precision and low recall.
Approach: They propose a task of synonym expansion using transitivity and propose auxiliary task to reduce the impact of noisy sentences.
Outcome: The proposed approach reduces the impact of noisy sentences and reduces noise in a real-world dataset.
Heterogeneous Graph Neural Networks for Concept Prerequisite Relation Learning in Educational Data (2021.naacl-main)

Copied to clipboard

Challenge: Existing methods to learn prerequisite relations among concepts are lacking . concepts are crucial for learning, organizing, applying and generating knowledge .
Approach: They propose a concept prerequisite relation learning approach which combines concept representation and concept pairwise features to make it more practical.
Outcome: The proposed method achieves state-of-the-art results on four datasets.
LSDC: An Efficient and Effective Large-Scale Data Compression Method for Supervised Fine-tuning of Large Language Models (2025.findings-naacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are expanding in scale and size, increasing computational costs . large-scale data compression techniques can reduce the size of training datasets while maintaining data integrity.
Approach: They propose a large-scale data compression method to reduce the size of training data . they use a bifurcated quantization strategy to maximize the diversity of samples .
Outcome: The proposed method significantly reduces the size of training data while maximizing the submodular gain.
Can Intelligent Agents Revolutionize Scale Generation? (2026.findings-acl)

Copied to clipboard

Challenge: Existing measurement scales require extensive manual labor and require extensive validation and validation.
Approach: They propose a multi-agent framework that automates scale development by leveraging collaborative AI agents.
Outcome: The proposed framework automates scale development while maintaining rigorous quality standards.
FinDABench: Benchmarking Financial Data Analysis Ability of Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of tasks, but their proficiency and reliability in the specialized domain of financial data analysis remain uncertain.
Approach: FinDABench is a benchmark designed to evaluate the financial data analysis capabilities of Large Language Models (LLMs) it comprises 15,200 training instances and 8,900 test instances, all meticulously crafted by human experts.
Outcome: FinDABench measures the financial data analysis capabilities of large language models (LLMs) across three dimensions: 1) Core Ability; 2) Analytical Ability; 3) Technical Ability.
Adversarial Self-Supervised Data-Free Distillation for Text Classification (2020.emnlp-main)

Copied to clipboard

Challenge: Existing knowledge distillation algorithms rely on the accessibility of the training dataset, which may be unavailable due to privacy issues.
Approach: They propose a data-free distillation method for a pre-trained transformer-based model that uses plug & play Embedding Guessing to craft pseudo embeddings from the teacher's hidden knowledge.
Outcome: The proposed method is the first data-free distillation framework designed for NLP 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