Papers by Eric Chang

6 papers
VISREAS: Complex Visual Reasoning with Unanswerable Questions (2024.findings-acl)

Copied to clipboard

Challenge: Logic2Vision is a visual question-answering dataset that validates question authenticity with the corresponding image and then reasoning over it.
Approach: They propose a compositional visual question-answering dataset, VisReas, that consists of answerable and unanswerable visual queries . they use visual genome scene graphs to generate the query and the reasoning steps to generate it.
Outcome: The proposed model outperforms generative models and the existing classification models and outperformed existing models.
MedEval: A Multi-Level, Multi-Task, and Multi-Domain Medical Benchmark for Language Model Evaluation (2023.emnlp-main)

Copied to clipboard

Challenge: Existing medical datasets require high quality domain-specific datasets.
Approach: They propose a multi-level, multi-task, and multi-domain medical benchmark to facilitate the development of language models for healthcare.
Outcome: The proposed model provides granular potential usage and supports a wide range of tasks.
Selective Demonstrations for Cross-domain Text-to-SQL (2023.findings-emnlp)

Copied to clipboard

Challenge: Large language models with in-context learning have demonstrated impressive generalization capabilities in the cross-domain text-to-SQL task without the use of in-domain annotations.
Approach: They propose a demonstration selection framework that utilizes both out-of-domain examples and synthetically generated in-domain demonstration examples to construct demonstrations.
Outcome: The proposed framework outperforms baseline methods on two cross-domain text-to-SQL datasets with improvements of 1.1 and 11.8 points in execution accuracy.
MARS: Unleashing the Power of Speculative Decoding via Margin-Aware Verification (2026.findings-acl)

Copied to clipboard

Challenge: Autoregressive large language models suffer from high inference latency due to memorybandwidth constraints.
Approach: They propose a method that decouples generation and verification by decoupling tokens and a lightweight draft model.
Outcome: The proposed method delivers consistent and significant speedups over state-of-the-art baselines while preserving generation quality across diverse benchmarks.
Weakly Supervised Contrastive Learning for Chest X-Ray Report Generation (2021.findings-emnlp)

Copied to clipboard

Challenge: Radiology report generation aims at generating descriptive text from radiology images automatically.
Approach: They propose a weakly supervised contrastive loss method that generates descriptive text from radiology images automatically.
Outcome: The proposed method outperforms previous work on correctness and text generation metrics for two public benchmarks.
Event Detection from Social Media for Epidemic Prediction (2024.naacl-long)

Copied to clipboard

Challenge: Social media is an easy-to-access platform providing timely updates about societal trends and events.
Approach: They propose a framework to extract epidemic-related events from social media posts to provide early warnings.
Outcome: The proposed framework can detect epidemic events for three unseen epidemics of Monkeypox, Zika, and Dengue while existing models fail miserably.

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