Papers by Jiaying Gong
Prompt-based Zero-shot Relation Extraction with Semantic Knowledge Augmentation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing approaches to recognize unseen relations for which there are no training instances are lacking in the real-world setting. |
| Approach: | They propose a prompt-based model with semantic knowledge augmentation to recognize unseen relations under zero-shot setting. |
| Outcome: | The proposed model outperforms existing methods under zero-shot setting on three datasets. |
Visual Zero-Shot E-Commerce Product Attribute Value Extraction (2025.naacl-industry)
Copied to clipboard
| Challenge: | Existing zero-shot product attribute value extraction approaches require sellers to manually provide product descriptions. |
| Approach: | They propose a cross-modal zero-shot attribute value generation framework based on CLIP that uses product images as inputs for zero- shot inference. |
| Outcome: | The proposed framework significantly outperforms other vision-language models for zero-shot attribute value extraction. |
VTechAGP: An Academic-to-General-Audience Text Paraphrase Dataset and Benchmark Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing text simplification and paraphrase datasets focus on sentence-level translation. |
| Approach: | They propose a novel academic-to-general-audience text paraphrase dataset . they also propose DSPT5 dynamic soft prompt generative language model . |
| Outcome: | The proposed dataset is the first academic-to-general-audience text paraphrase dataset . it is based on document-level these and dissertation abstract pairs from 8 colleges . |
Few-Shot Relation Extraction with Hybrid Visual Evidence (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing few-shot relation extraction methods focus on uni-modal information such as text only. Existing methods focus only on text, requiring only a few labeled instances for training. |
| Approach: | They propose a multi-modal few-shot relation extraction model that leverages both textual and visual semantic information to learn a multiple-modal representation jointly. |
| Outcome: | The proposed model leverages both textual and visual semantic information to learn a multi-modal representation jointly. |
Clues Before Answers: Generation-Enhanced Multiple-Choice QA (2022.naacl-main)
Copied to clipboard
| Challenge: | Multiple-choice question answering (MCQA) uses text-to-text framework . but, there is an under-utilization of the decoder and knowledge that can be decoded . |
| Approach: | They propose a generative multiple-choice question answering model which generates a clue from the question and leverages it to enhance a reader for MCQA. |
| Outcome: | The proposed model outperforms text-to-text models on multiple MCQA datasets. |
Sci-LoRA: Mixture of Scientific LoRAs for Cross-Domain Lay Paraphrasing (2025.findings-acl)
Copied to clipboard
| Challenge: | Lay paraphrasing aims to make scientific information accessible to non-experts . existing studies focus on a single domain, such as biomedicine . |
| Approach: | a new lay paraphrasing model leverages a mixture of LoRAs fine-tuned on multiple scientific domains. |
| Outcome: | a new model outperforms state-of-the-art large language models in lay paraphrasing . the model can adjust the impact of different domains without explicit labels . |
MICE: Mixture of Image Captioning Experts Augmented e-Commerce Product Attribute Value Extraction (2025.acl-industry)
Copied to clipboard
| Challenge: | Existing visual attribute value extraction methods rely on product images and textual information, which can be ambiguous, inaccurate, or unavailable. |
| Approach: | They propose a framework that leverages a curated pool of image captioning models to generate accurate captions from product images. |
| Outcome: | The proposed framework significantly improves state-of-the-art large multimodal models in zero-shot and fine-tuning settings. |