Summary of Heterogeneous Graph Reasoning For Fact Checking Over Texts and Tables, by Haisong Gong et al.
Heterogeneous Graph Reasoning for Fact Checking over Texts and Tables
by Haisong Gong, Weizhi Xu, Shu wu, Qiang Liu, Liang Wang
First submitted to arxiv on: 20 Feb 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel approach to fact-checking by reasoning over unstructured text and structured table information. The model, called HeterFC, uses a heterogeneous evidence graph to leverage the semantic information underlying different types of evidence. The authors introduce a relational graph neural network for information propagation and an attention-based method for integrating information from multiple sources. The paper also presents a multitask loss function to account for potential inaccuracies in evidence retrieval. Experiments on the large fact-checking dataset FEVEROUS demonstrate the effectiveness of HeterFC. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Fact-checking is important because it helps people figure out if what they’re reading or hearing is true or not. This paper is about a new way to do fact-checking that uses special computer models to look at different kinds of evidence, like text and tables. The model is called HeterFC and it’s designed to work well with lots of different types of information. The authors also came up with a way to make the model better by using something called attention, which helps the model focus on the most important parts of the evidence. |
Keywords
» Artificial intelligence » Attention » Graph neural network » Loss function
