Tong Sun

Open-Domain Question Answering with Pre-Constructed Question Spaces

2020 · arXiv (Cornell University)

Open-domain question answering aims at solving the task of locating the answers to user-generated questions in massive collections of documents. There are two families of solutions available: retriever-readers, and knowledge-graph-based approaches. A retriever-reader usually first …

MATSA: Multi-Agent Table Structure Attribution

2024

Large Language Models (LLMs) have significantly advanced QA tasks through in-context learning but often suffer from hallucinations.Attributing supporting evidence grounded in source documents has been explored for unstructured text in the past.However, tabular data present …

Prototype-Enhanced Few-Shot Relation Extraction Method Based on Cluster Loss Optimization

2025 · Symmetry

The purpose of few-shot relation extraction (RE) is to recognize the relationship between specific entity pairs in text when there are a limited number of labeled samples. A few-shot RE method based on a prototype …