CoChat
Sign Up
Cited by 161Misinformation and Its ImpactsTopic ModelingMultimodal Machine Learning Applications

The DOI matches its Crossref record; 48 of the 48 references it cites were found in a registry or an index.

Reasoning Over Semantic-Level Graph for Fact Checking

Open access
Zhong, Wanjun, Xu, Jingjing, Tang, Duyu, Xu, Zenan, Duan, Nan, Zhou, Ming, Wang, Jiahai, Yin, Jian·2020·Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
DOI 10.18653/v1/2020.acl-main.549
Open this paper in CoChat — free accountOpen PDF

Abstract

Fact checking is a challenging task because verifying the truthfulness of a claim requires reasoning about multiple retrievable evidence.In this work, we present a method suitable for reasoning about the semantic-level structure of evidence.Unlike most previous works, which typically represent evidence sentences with either string concatenation or fusing the features of isolated evidence sentences, our approach operates on rich semantic structures of evidence obtained by semantic role labeling.We propose two mechanisms to exploit the structure of evidence while leveraging the advances of pre-trained models like BERT, GPT or XLNet.Specifically, using XLNet as the backbone, we first utilize the graph structure to re-define the relative distances of words, with the intuition that semantically related words should have short distances.Then, we adopt graph convolutional network and graph attention network to propagate and aggregate information from neighboring nodes on the graph.We evaluate our system on FEVER, a benchmark dataset for fact checking, and find that rich structural information is helpful and both our graph-based mechanisms improve the accuracy.Our model is the state-of-the-art system in terms of both official evaluation metrics, namely claim verification accuracy and FEVER score.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.18653/v1/2020.acl-main.549

Cites

48 of 48 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 A motivating example for fact checking and the FEVER task. Verifying the claim requires understanding the semantic structure of multiple evidence sentences and the reasoning process over the structure.
Figure 1 A motivating example for fact checking and the FEVER task. Verifying the claim requires understanding the semantic structure of multiple evidence sentences and the reasoning process over the structure.CC-BY · From the PDF
Figure 2 Our pipeline for fact checking on FEVER. The main contribution of this work is a graph-based reasoning model for claim verification.
Figure 2 Our pipeline for fact checking on FEVER. The main contribution of this work is a graph-based reasoning model for claim verification.CC-BY · From the PDF
Figure 3 The constructed graph for the motivating example with two evidence sentences. Each box describes a 'tuple' which is extracted by SRL triggered by a verb. Blue solid lines indicate edges that connect arguments within a tuple and red dotted lines indicate edges that connect argument across different tuples.
Figure 3 The constructed graph for the motivating example with two evidence sentences. Each box describes a 'tuple' which is extracted by SRL triggered by a verb. Blue solid lines indicate edges that connect arguments within a tuple and red dotted lines indicate edges that connect argument across different tuples.CC-BY · From the PDF
Figure 4 An overview of our graph-based reasoning approach for claim verification. Taking a claim and evidence sentences as the input, we first calculate contextual word representations with graph-based distance ( § 3.2). After that, we use graph convolutional network to propagate information over the graph ( § 3.3), and use graph attention network to aggregate information ( § 3.4) before making the final prediction.
Figure 4 An overview of our graph-based reasoning approach for claim verification. Taking a claim and evidence sentences as the input, we first calculate contextual word representations with graph-based distance ( § 3.2). After that, we use graph convolutional network to propagate information over the graph ( § 3.3), and use graph attention network to aggregate information ( § 3.4) before making the final prediction.CC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 36 references

Cited by

Sorted by citations

Related

See all

Metadata

Authors
Zhong, W., Xu, J., Tang, D., Xu, Z., Duan, N., Zhou, M., Wang, J., & Yin, J.
Affiliations
  • Sun Yat-sen University (CN)
  • Peking University (CN)
  • Microsoft (United States) (US)
ORCID
Venue
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Publisher
Association for Computational Linguistics
Published
2020
Pages
6170-6180
ISSN
0736-587X (ISSN-L)
DOI
10.18653/v1/2020.acl-main.549
OpenAlex
W3034808961
Cited by
151
References
36
Citations by year
2026: 4 · 2025: 15 · 2024: 22 · 2023: 26 · 2022: 36 · 2021: 38 · 2020: 10
FWCI
58.32
Type
conference paper
Language
en
Open access
Licence
cc-by
Locations
Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
Funders
  • National Natural Science Foundation of China (U1611264, U1711262, U1811261, U1811264, U1711261, U1911203)
  • Basic and Applied Basic Research Foundation of Guangdong Province (2019B15 15130001)
Topics
  • Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
Keywords
fact-checking, claim verification, semantic role labeling, graph convolutional networks, graph attention networks, XLNet, FEVER dataset, word distance

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review