Multi-Hop Fact Checking of Political Claims

@inproceedings{Ostrowski2021MultiHopFC,
  title={Multi-Hop Fact Checking of Political Claims},
  author={Wojciech Ostrowski and Arnav Arora and Pepa Atanasova and Isabelle Augenstein},
  booktitle={IJCAI},
  year={2021}
}
Recently, novel multi-hop models and datasets have been introduced to achieve more complex natural language reasoning with neural networks. One notable task that requires multi-hop reasoning is fact checking, where a chain of connected evidence pieces leads to the final verdict of a claim. However, existing datasets do not provide annotations for the gold evidence pieces, which is a critical aspect for improving the explainability of fact checking systems. The only exception is the FEVER… Expand
A Review on Fact Extraction and Verification
TLDR
The proposed methods are described by analyzing the technical perspectives of the different approaches and discussing the performance results on the FEVER dataset, which is the most well-studied and formally structured dataset on the fact extraction and verification task. Expand
Generating Label Cohesive and Well-Formed Adversarial Claims
TLDR
This work extends the HotFlip attack algorithm used for universal trigger generation by jointly minimising the target class loss of a fact checking model and the entailment class Loss of an auxiliary natural language inference model, and trains a conditional language model to generate semantically valid statements, which include the found universal triggers. Expand
COSMOS: Catching Out-of-Context Misinformation with Self-Supervised Learning
TLDR
A new method that automatically detects out-of-context image and text pairs and learns to selectively align individual objects in an image with textual claims, without explicit supervision is proposed. Expand
Automated Fact-Checking: A Survey
TLDR
This paper reviews relevant research on automated fact-checking covering both the claim detection and claim validation components. Expand
COSMOS: Catching Out-of-Context Misinformation with Self-Supervised Learning
TLDR
A new method that automatically detects out-of-context image and text pairs and proposes a self-supervised training strategy where the method learns to selectively align individual objects in an image with textual claims, without explicit supervision. Expand
Time-Aware Evidence Ranking for Fact-Checking
TLDR
This study investigates the hypothesis that the timestamp of an evidence page is crucial to how it should be ranked for a given claim and reveals that time-aware evidence ranking not only surpasses relevance assumptions based purely on semantic similarity or position in a search results list, but also improves veracity predictions of time-sensitive claims in particular. Expand
Claim Check-Worthiness Detection as Positive Unlabelled Learning
TLDR
The best performing method is a unified approach which automatically corrects for this using a variant of positive unlabelled learning that finds instances which were incorrectly labelled as not check-worthy. Expand

References

SHOWING 1-10 OF 39 REFERENCES
GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification
TLDR
A graph-based evidence aggregating and reasoning (GEAR) framework which enables information to transfer on a fully-connected evidence graph and then utilizes different aggregators to collect multi-evidence information is proposed. Expand
Where is Your Evidence: Improving Fact-checking by Justification Modeling
TLDR
The LIAR dataset is extended by automatically extracting the justification from the fact-checking article used by humans to label a given claim, and it is shown that modeling the extracted justification in conjunction with the claim provides a significant improvement regardless of the machine learning model used. Expand
FEVER: a Large-scale Dataset for Fact Extraction and VERification
TLDR
This paper introduces a new publicly available dataset for verification against textual sources, FEVER, which consists of 185,445 claims generated by altering sentences extracted from Wikipedia and subsequently verified without knowledge of the sentence they were derived from. Expand
DeSePtion: Dual Sequence Prediction and Adversarial Examples for Improved Fact-Checking
TLDR
This work shows that current systems for FEVER are vulnerable to three categories of realistic challenges for fact-checking – multiple propositions, temporal reasoning, and ambiguity and lexical variation – and introduces a resource with these types of claims, and presents a system designed to be resilient to these “attacks”. Expand
Generating Fact Checking Explanations
TLDR
This paper provides the first study of how justifications for verdicts on claims can be generated automatically based on available claim context, and how this task can be modelled jointly with veracity prediction. Expand
MultiFC: A Real-World Multi-Domain Dataset for Evidence-Based Fact Checking of Claims
TLDR
An in-depth analysis of the largest publicly available dataset of naturally occurring factual claims, collected from 26 fact checking websites in English, paired with textual sources and rich metadata, and labelled for veracity by human expert journalists is presented. Expand
Understanding Dataset Design Choices for Multi-hop Reasoning
TLDR
This paper investigates two recently proposed datasets, WikiHop and HotpotQA, and explores sentence-factored models for these tasks; by design, these models cannot do multi-hop reasoning, but they are still able to solve a large number of examples in both datasets. Expand
Transformer-XH: Multi-Evidence Reasoning with eXtra Hop Attention
TLDR
Transformer-XH is presented, which uses eXtra Hop attention to enable intrinsic modeling of structured texts in a fully data-driven way and leads to a simpler multi-hop QA system which outperforms previous state-of-the-art on the HotpotQA FullWiki setting. Expand
Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering
TLDR
A new graph-based recurrent retrieval approach that learns to retrieve reasoning paths over the Wikipedia graph to answer multi-hop open-domain questions and achieves significant improvement in HotpotQA, outperforming the previous best model by more than 14 points. Expand
Fact Checking: Task definition and dataset construction
TLDR
The task of fact checking is introduced and the construction of a publicly available dataset using statements fact-checked by journalists available online is detailed, including baseline approaches for the task and the challenges that need to be addressed. Expand
...
1
2
3
4
...