Papers by Shizhou Huang

7 papers
BCL: Bayesian In-Context Learning Framework for Information Extraction (2026.findings-acl)

Copied to clipboard

Challenge: Existing information extraction (IE) tasks rely on in-context learning with large language models.
Approach: They propose a Bayesian-based in-context learning framework that refines label representations across IE tasks using particle filtering and Bayes updates.
Outcome: The proposed framework improves performance over existing methods (up to 30%) it underperforms one-shot prompting by a substantial margin on NER tasks and CodeIE fails on RE tasks with near-zero micro-F1.
A Graph Interaction Framework on Relevance for Multimodal Named Entity Recognition with Multiple Images (2025.coling-main)

Copied to clipboard

Challenge: Existing methods to determine whether images are related to named entities are not effective in multi-image scenarios.
Approach: They propose a graph interaction framework on relevance for Multimodal Named Entity Recognition with multiple images to integrate human abilities into the model.
Outcome: The proposed framework achieves state-of-the-art on benchmark datasets and compares with CLIP and CLIP-based approaches.
Hypernetwork-Assisted Parameter-Efficient Fine-Tuning with Meta-Knowledge Distillation for Domain Knowledge Disentanglement (2024.findings-naacl)

Copied to clipboard

Challenge: Recent work on domain adaptation for text summarization fails to account for the huge gap between dialogue and general articles.
Approach: They propose a hypernetwork-assisted encoder-decoder architecture with parameter-efficient fine-tuning to disentangle domain-invariant knowledge from source domains while learning specific knowledge of the target domain.
Outcome: The proposed model can disentangle domain-invariant knowledge from source domains while learning specific knowledge of the target domain.
MRE-MI: A Multi-image Dataset for Multimodal Relation Extraction in Social Media Posts (2025.findings-naacl)

Copied to clipboard

Challenge: Existing approaches to Multimodal Relation Extraction focus on single image scenarios . current approaches focus on text paired with a single image, ignoring valuable insights provided by remaining images.
Approach: They propose a human-annotated dataset that includes multi-image and single-image instances for relation extraction.
Outcome: The proposed model significantly improves relation extraction in multi-image scenarios.
MNER-MI: A Multi-image Dataset for Multimodal Named Entity Recognition in Social Media (2024.lrec-main)

Copied to clipboard

Challenge: Recent research has focused on multimodal named entity recognition (MNER) but current approaches focus on text and a single accompanying image, leaving a significant research gap in multi-image scenarios.
Approach: They propose to construct a human-annotated MNER dataset with multiple images called MNER-MI and a temporal prompt model with multiple image to address the new challenges in multi-image scenarios.
Outcome: The proposed method achieves state-of-the-art results on both MNER-MI and MNER -MI-Plus, demonstrating its effectiveness.
Different Data, Different Modalities! Reinforced Data Splitting for Effective Multimodal Information Extraction from Social Media Posts (2022.coling-1)

Copied to clipboard

Challenge: Recent multimodal information extraction approaches overestimate the significance of images.
Approach: They propose a general data splitting strategy to divide social media posts into two sets to achieve better performance under information extraction models of the corresponding modalities.
Outcome: The proposed method outperforms existing models on two different multimodal information extraction tasks.
MGCL: Multi-Granularity Clue Learning for Emotion-Cause Pair Extraction via Cross-Grained Knowledge Distillation (2024.findings-emnlp)

Copied to clipboard

Challenge: Traditional methods often rely on coarse-grained clause-level annotations, which overlook valuable fine-grain clues.
Approach: They propose a method that captures fine-grained clues from a weakly-supervised perspective efficiently by using a teacher model to give sub-clause clues without needing fine-grain annotations.
Outcome: The proposed method achieves state-of-the-art performance while offering improved interpretability.

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