Papers by Shaohuan Cheng

5 papers
Beyond Single-Event Extraction: Towards Efficient Document-Level Multi-Event Argument Extraction (2024.findings-acl)

Copied to clipboard

Challenge: mainstream event argument extraction methods process each event in isolation, resulting in inefficient inference and ignoring correlations among multiple events.
Approach: They propose a multi-event argument argument extraction model which extracts arguments from all events simultaneously.
Outcome: The proposed model performs better on four public datasets while saving time.
Enhancing Document-level Event Argument Extraction with Contextual Clues and Role Relevance (2023.findings-acl)

Copied to clipboard

Challenge: Document-level event argument extraction is a challenging task for cross-sentence inference . previous work focused on document-level EAE, but recent work focused more on documentlevel .
Approach: They propose a document-level event argument extraction model that captures contextual clues and latent role information.
Outcome: The proposed model outperforms existing methods on two public datasets with 1.13 F1 and 2.64 F1 improvements on RAMS and WikiEvents respectively.
A Compressive Memory-based Retrieval Approach for Event Argument Extraction (2025.coling-main)

Copied to clipboard

Challenge: Existing retrieval-based EAE methods have input length constraints and the gap between the retriever and the inference model.
Approach: They propose a retrieval-based retrieval mechanism that overcomes input length constraints . they use compressive memory to cache retrieved information and support continuous updates .
Outcome: The proposed method outperforms retrieval-based methods on three public datasets.
Adaptive Textual Label Noise Learning based on Pre-trained Models (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to learning with noisy labels are limited due to the time and labor costs involved.
Approach: They propose an adaptive warm-up and hybrid training frameworks to learn with noisy labels based on pre-trained models.
Outcome: The proposed approach performs comparable or even surpasses state-of-the-art methods in various noise scenarios, including scenarios with the mixture of multiple types of noise.
Hanfu-Bench: A Multimodal Benchmark on Cross-Temporal Cultural Understanding and Transcreation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing studies on cultural understanding with vision-language models primarily emphasize geographic diversity, often overlooking the critical temporal dimensions.
Approach: They propose a multimodal vision-language model that examines temporal features and cultural image transcreation.
Outcome: The novel model performs better than non-experts on visual cutural understanding but falls short to human experts on cultural image transcreation task.

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