Fine-grained Fact Verification with Kernel Graph Attention Network
By Zhenghao Liu, Chenyan Xiong, Maosong Sun, Zhiyuan Liu. 2019
254 citations recorded by the source corpus.
Fact Verification requires fine-grained natural language inference capability that finds subtle clues to identify the syntactical and semantically correct but not well-supported claims. This paper presents Kernel Graph Attention Network (KGAT), which conducts more fine-grained fact verification with kernel-based attentions. Given a claim and a set of potential evidence sentences that form an evidence graph, KGAT introduces node kernels, which better measure the importance of the evidence node, and edge kernels, which conduct fine-grained evidence propagation in the graph, into Graph Attention Networks for more accurate fact verification. KGAT achieves a 70.38% FEVER score and significantly outperforms existing fact verification models on FEVER, a large-scale benchmark for fact verification. Our analyses illustrate that, compared to dot-product attentions, the kernel-based attention concentrates more on relevant evidence sentences and meaningful clues in the evidence graph, which is the main source of KGAT’s effectiveness. All source codes of this work are available at https://github.com/thunlp/KernelGAT.
Subfields: Artificial Intelligence, Retrieval-Augmented Generation, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Mohit Bansal
- Jianfeng Gao
- Luke S. Zettlemoyer
- Sebastian Riedel
- Caiming Xiong
- Graham Neubig
- Yejin Choi
- Percy Liang
In Retrieval-Augmented Generation
- Sebastian Riedel
- Wen-tau Yih
- Patrick Lewis
- Barlas Oğuz
- Andreas Vlachos
- Douwe Kiela
- Yashar Mehdad
- Caiming Xiong
In Natural Language Processing
- Mohit Bansal
- Jianfeng Gao
- Sebastian Riedel
- Andreas Vlachos
- Caiming Xiong
- Luke S. Zettlemoyer
- Wen-tau Yih
- Graham Neubig
Citations in the corpus
- Reasoning Over Semantic-Level Graph for Fact Checking (2019, methodology): “We employ pre-trained models like RoBERTa (Liu et al. 2019) and XLNet (Yang et al. 2019) as the sentence encoder.”
- ProoFVer: Natural Logic Theorem Proving for Fact Verification (2021, background): “ProoFVer outperforms current state-of-theart (SOTA) fact verification models (Liu et al., 2020; Ye et al., 2020; Zhong et al., 2020) in both performance and robustness.”
- Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval (2020, methodology): “…C for the exact numbers. the results in verification label accuracy (LA) and the FEVER score 9 in Table 7, where the numbers of competitive baselines, GEAR (Zhou et al., 2019), graph attention network (GAT) (Veliˇckovi´c et al., 2017) and variants of KGAT are from the KGAT (Liu et al., 2020) paper.”
- CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims (2020, methodology): “We adopt a pipeline approach for our evidence retrieval and claim validation system similar to the baseline system proposed by fever [1] and similar to virtually all competing implementations that followed [7, 8, 9, 10, 11].”
- A Multi-Level Attention Model for Evidence-Based Fact Checking (2021, methodology): “Following (Stammbach and Neumann, 2019; Soleimani et al., 2019; Liu et al., 2020), we prefixed the Wikipedia article titles to the candidate sentences to alleviate the co-reference resolution problem.”
- Program Enhanced Fact Verification with Verbalization and Graph Attention Network (2020, background): “Others formulates fact verification as graph reasoning (Zhou et al., 2019; Liu et al., 2020).”
- DialFact: A Benchmark for Fact-Checking in Dialogue (2021, methodology): “We use their model which uses kernel graph attention network (KGAT) (Liu et al., 2020) and fine-tune it on Colloquial claims.”
- Explainable Automated Fact-Checking: A Survey (2020, methodology): “This document retrieval module is re-used in a number of works (Alonso-Reina et al., 2019; Soleimani et al., 2020; Liu et al., 2020).”
- Fool Me Twice: Entailment from Wikipedia Gamification (2021, background): “For the second component of the task, we follow state-of-the-art entailment models (Zhou et al., 2019; Liu et al., 2020; Eisenschlos et al., 2020):”
- Are Factuality Checkers Reliable? Adversarial Meta-evaluation of Factuality in Summarization (2021, background): “The summary sentences that need to be verified are also called claims below to keep consistent with the field of fact verification (Zhou et al., 2019; Schuster et al., 2019; Liu et al., 2020).”
- Exploring the Potential of Large Language Models (LLMs)in Learning on Graphs (2023, methodology): “After investigating the output of LLMs, we find that a part of the wrong predictions made by LLMs are very reasonable.”