Explainable Fact Checking with Probabilistic Answer Set Programming

By Naser Ahmadi, Joohyung Lee, Paolo Papotti, Mohammed Saeed. 2019

59 citations recorded by the source corpus.

One challenge in fact checking is the ability to improve the transparency of the decision. We present a fact checking method that uses reference information in knowledge graphs (KGs) to assess claims and explain its decisions. KGs contain a formal representation of knowledge with semantic descriptions of entities and their relationships. We exploit such rich semantics to produce interpretable explanations for the fact checking output. As information in a KG is inevitably incomplete, we rely on logical rule discovery and on Web text mining to gather the evidence to assess a given claim. Uncertain rules and facts are turned into logical programs and the checking task is modeled as an inference problem in a probabilistic extension of answer set programs. Experiments show that the probabilistic inference enables the efficient labeling of claims with interpretable explanations, and the quality of the results is higher than state of the art baselines.

Subfields: Artificial Intelligence, Natural Language Processing, Knowledge Graphs & Representation

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

In Natural Language Processing

In Knowledge Graphs & Representation

Citations in the corpus

ProoFVer: Natural Logic Theorem Proving for Fact Verification (2021, neutral): “, 2021) or perform rule discovery (Ahmadi et al., 2019; Gad-Elrab et al., 2019).”
Explainable Automated Fact-Checking for Public Health Claims (2020, methodology): “These methods span the gamut form logic-based approaches such as probabilistic answer set programming (Ahmadi et al., 2019) and reasoning with Horn rules (Ah-madi et al., 2019; Gad-Elrab et al., 2019) to deep learning and attention-based approaches, e.g., leveraging co-attention networks and human…”
Automated Fact-Checking for Assisting Human Fact-Checkers (2021, methodology): “Three broad approaches to automated verification can be identified in the literature [Babakar and Moy, 2016]: reference approaches, where the claim is checked against a trusted source, such as a database [Ahmadi et al., 2019; Chen et al., 2020]; machine learning approaches, where a probabilistic mod”
RuleHub (2020, background): “KG dependencies (or logical rules) are used for identifying errors [28], adding new facts [20], executing queries faster [31], and reasoning for many tasks, such as explaining decisions in factchecking [5].”
Explainable Automated Fact-Checking: A Survey (2020, methodology): “ExpClaim (Ahmadi et al., 2019) is evaluated against and outperforms CredEye (Popat et al., 2018), and GCAN (Lu and Li, 2020) is shown to outperform dE-FEND (Shu et al., 2019).”