---
title: "GEAR: Graph-based Evidence Aggregating and — Zhou 2019"
description: "Fact verification (FV) means judging a claim as SUPPORTED, REFUTED or NOT ENOUGH INFO using sentences retrieved from Wikipedia."
authors: ["Jie Zhou", "Xu Han", "Cheng Yang", "Zhiyuan Liu", "Lifeng Wang", "Changcheng Li", "Maosong Sun"]
year: 2019
venue: "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics"
source: "https://aclanthology.org/P19-1085/"
doi: "10.18653/v1/p19-1085"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhou-2019-gear-graph-based-evidence-aggregating/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhou-2019-gear-graph-based-evidence-aggregating/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2019](https://md.research.elamur.ai/free/en/papers/2019/page/2/) / GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification

# GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification

**Authors:** [Jie Zhou](https://md.research.elamur.ai/free/en/authors/jie-zhou/), [Xu Han](https://md.research.elamur.ai/free/en/authors/xu-han/), [Cheng Yang](https://md.research.elamur.ai/free/en/authors/cheng-yang/), [Zhiyuan Liu](https://md.research.elamur.ai/free/en/authors/zhiyuan-liu/), Lifeng Wang, Changcheng Li, [Maosong Sun](https://md.research.elamur.ai/free/en/authors/maosong-sun/) · **Year:** 2019 · **Venue:** Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/P19-1085/) · [PDF](https://aclanthology.org/P19-1085.pdf) · [DOI 10.18653/v1/p19-1085](https://doi.org/10.18653/v1/p19-1085) · [OpenAlex](https://openalex.org/W2950336186)

**Citations:** 194 citations (openalex-snapshot · 2026-10-14) · [94](#cited-by) in our library, of the 140884 papers whose bibliographies we read

## Summary
Fact verification (FV) means judging a claim as SUPPORTED, REFUTED or NOT ENOUGH INFO using sentences retrieved from Wikipedia. Many claims can only be resolved by combining several sentences. Earlier FEVER systems treated the task as NLI but either concatenated all evidence or scored each claim–evidence pair separately, so the evidence pieces never exchanged information. The authors propose GEAR, which builds on a three-stage pipeline: document retrieval, sentence selection and claim verification. The first two stages reuse the approach of Hanselowski et al. (2018), with an added relevance-score threshold that removes noisy sentences. For verification, each evidence–claim pair is encoded with BERT. The encoded sentences become nodes in a fully connected graph, and an evidence reasoning network (ERNet) passes messages between them. An aggregator then pools the node states for classification. On the FEVER benchmark, GEAR reaches a test FEVER score of 67.10% and beats a strong BERT concatenation baseline. This indicates that explicit reasoning across evidence helps multi-sentence verification.

## Key points
- Three aggregators are proposed: attention (guided by the claim representation), max and mean. The best final model uses one ERNet layer with the attention aggregator and a sentence filter threshold of 10⁻³.
- Retrieval follows the UKP-Athene method. Entities found by an AllenNLP constituency parser are used as MediaWiki API queries, keeping the top 7 results per query. An ESIM-based sentence ranker, ensembled over 10 seeds, then keeps at most 5 sentences.
- The full pipeline scores 67.10% FEVER on the test set, 1.46% above BERT-Concat. BERT fine-tuning systems already exceed earlier shared-task entries by roughly 1%.
- An evidence-enhanced dev set, with ground-truth evidence injected, raises label accuracy by more than 1.4%. This shows that upstream retrieval remains a bottleneck.
- Code is released at github.com/thunlp/GEAR.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/)

## Cited by

Cited by

94 papers of our library cite it (of the 140884 whose bibliographies we read); 5 of them have a page here, 89 not yet.

- [A Survey on Automated Fact-Checking](https://md.research.elamur.ai/free/en/papers/guo-2022-survey-automated-fact-checking/)
- [A Survey on Stance Detection for Mis- and Disinformation Identification](https://md.research.elamur.ai/free/en/papers/hardalov-2022-survey-stance-detection-mis-disinformation/)
- [ARAFA: An LLM-Generated Arabic Fact-Checking Dataset](https://md.research.elamur.ai/free/en/papers/khalil-2026-arafa-llm-generated-arabic-fact/)
- [Fine-grained Fact Verification with Kernel Graph Attention Network](https://md.research.elamur.ai/free/en/papers/liu-2020-fine-grained-fact-verification-kernel/)
- [Fact-Checking Complex Claims with Program-Guided Reasoning](https://md.research.elamur.ai/free/en/papers/pan-2023-fact-checking-complex-claims-program/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{zhou2019gear,
  title = {{GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification}},
  author = {Zhou, Jie and Han, Xu and Yang, Cheng and Liu, Zhiyuan and Wang, Lifeng and Li, Changcheng and Sun, Maosong},
  booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics},
  year = {2019},
  doi = {10.18653/v1/p19-1085},
  url = {https://doi.org/10.18653/v1/p19-1085}
}
```

- [← previous GBI Treebanks as a Resource for New Applications](https://md.research.elamur.ai/free/en/papers/hbo-2019-wu-gbi-treebanks-resource-new-applications/)
- [next → GECOR: An End-to-End Generative Ellipsis and Co-reference Resolution Model for Task-Oriented Dialogue](https://md.research.elamur.ai/free/en/papers/quan-2019-gecor-end-end-generative-ellipsis/)
- [↑ back to papers of 2019](https://md.research.elamur.ai/free/en/papers/2019/page/2/)

## References

23 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Gabor Angeli and Christopher D Manning. 2014. Naturalli: Natural logic inference for common sense reasoning. In Proceedings of EMNLP, pages 534– 545. [find](https://scholar.google.com/scholar?q=Gabor+Angeli+and+Christopher+D+Manning%2E+2014%2E+Naturalli%3A+Natural+logic+inference+for+common+sense+reasoning%2E+In+Proceedings+of+EMNLP%2C+pages+534%E2%80%93+545%2E)
2. Diederik P Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Proceedings of ICLR. [find](https://scholar.google.com/scholar?q=Diederik+P+Kingma+and+Jimmy+Ba%2E+2015%2E+Adam%3A+A+method+for+stochastic+optimization%2E+In+Proceedings+of+ICLR%2E)
3. Thomas N Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of ICLR. [find](https://scholar.google.com/scholar?q=Thomas+N+Kipf+and+Max+Welling%2E+2017%2E+Semi%2Dsupervised+classification+with+graph+convolutional+networks%2E+In+Proceedings+of+ICLR%2E) [our card](https://md.research.elamur.ai/free/en/papers/kipf-2016-semi-supervised-classification-graph-convolutional/)
4. Samuel R Bowman, Gabor Angeli, Christopher Potts, and Christopher D Manning. 2015. A large annotated corpus for learning natural language inference. In Proceedings of EMNLP, pages 632–642. [find](https://scholar.google.com/scholar?q=Samuel+R+Bowman%2C+Gabor+Angeli%2C+Christopher+Potts%2C+and+Christopher+D+Manning%2E+2015%2E+A+large+annotated+corpus+for+learning+natural+language+inference%2E+In+Proceedings+of+EMNLP%2C+pages+632%E2%80%93642%2E)
5. Jackson Luken, Nanjiang Jiang, and Marie-Catherine de Marneffe. 2018. Qed: A fact verification system for the fever shared task. In Proceedings of the First Workshop on FEVER, pages 156–160. [find](https://scholar.google.com/scholar?q=Jackson+Luken%2C+Nanjiang+Jiang%2C+and+Marie%2DCatherine+de+Marneffe%2E+2018%2E+Qed%3A+A+fact+verification+system+for+the+fever+shared+task%2E+In+Proceedings+of+the+First+Workshop+on+FEVER%2C+pages+156%E2%80%93160%2E)
6. Danqi Chen, Adam Fisch, Jason Weston, and Antoine Bordes. 2017a. Reading Wikipedia to answer open-domain questions. In Proceedings of ACL, pages 1870–1879. [find](https://scholar.google.com/scholar?q=Danqi+Chen%2C+Adam+Fisch%2C+Jason+Weston%2C+and+Antoine+Bordes%2E+2017a%2E+Reading+Wikipedia+to+answer+open%2Ddomain+questions%2E+In+Proceedings+of+ACL%2C+pages+1870%E2%80%931879%2E) [our card](https://md.research.elamur.ai/free/en/papers/chen-2017-reading-wikipedia-answer-open-domain/)
7. Christopher Malon. 2018. Team papelo: Transformer networks at fever. In Proceedings of the First Workshop on FEVER, pages 109–113. [find](https://scholar.google.com/scholar?q=Christopher+Malon%2E+2018%2E+Team+papelo%3A+Transformer+networks+at+fever%2E+In+Proceedings+of+the+First+Workshop+on+FEVER%2C+pages+109%E2%80%93113%2E)
8. Qian Chen, Xiaodan Zhu, Zhen-Hua Ling, Si Wei, Hui Jiang, and Diana Inkpen. 2017b. Enhanced lstm for Adina Williams, Nikita Nangia, and Samuel Bowman. 2018. A broad-coverage challenge corpus for sentence understanding through inference. In Proceedings of NAACL-HLT, pages 1112–1122. [find](https://scholar.google.com/scholar?q=Qian+Chen%2C+Xiaodan+Zhu%2C+Zhen%2DHua+Ling%2C+Si+Wei%2C+Hui+Jiang%2C+and+Diana+Inkpen%2E+2017b%2E+Enhanced+lstm+for+Adina+Williams%2C+Nikita+Nangia%2C+and+Samuel+Bowman%2E+2018%2E+A+broad%2Dcoverage+challenge+corpus+for+sente)
9. Tsendsuren Munkhdalai and Hong Yu. 2017. Neural tree indexers for text understanding. In Proceedings of EACL, pages 11–21. [find](https://scholar.google.com/scholar?q=Tsendsuren+Munkhdalai+and+Hong+Yu%2E+2017%2E+Neural+tree+indexers+for+text+understanding%2E+In+Proceedings+of+EACL%2C+pages+11%E2%80%9321%2E)
10. Yixin Nie and Mohit Bansal. 2017. Shortcut-stacked sentence encoders for multi-domain inference. In Proceedings of ACL, Workshop on Evaluating Vector Space Representations for NLP, pages 41–45. [find](https://scholar.google.com/scholar?q=Yixin+Nie+and+Mohit+Bansal%2E+2017%2E+Shortcut%2Dstacked+sentence+encoders+for+multi%2Ddomain+inference%2E+In+Proceedings+of+ACL%2C+Workshop+on+Evaluating+Vector+Space+Representations+for+NLP%2C+pages+41%E2%80%9345%2E)
11. Wenpeng Yin and Dan Roth. 2018. Twowingos: A two-wing optimization strategy for evidential claim verification. In Proceedings of EMNLP, pages 105– 114. [find](https://scholar.google.com/scholar?q=Wenpeng+Yin+and+Dan+Roth%2E+2018%2E+Twowingos%3A+A+two%2Dwing+optimization+strategy+for+evidential+claim+verification%2E+In+Proceedings+of+EMNLP%2C+pages+105%E2%80%93+114%2E) [our card](https://md.research.elamur.ai/free/en/papers/yin-2018-twowingos-two-wing-optimization-strategy/)
12. Yixin Nie, Haonan Chen, and Mohit Bansal. 2019. Combining fact extraction and verification with neural semantic matching networks. In Proceedings of AAAI. [find](https://scholar.google.com/scholar?q=Yixin+Nie%2C+Haonan+Chen%2C+and+Mohit+Bansal%2E+2019%2E+Combining+fact+extraction+and+verification+with+neural+semantic+matching+networks%2E+In+Proceedings+of+AAAI%2E)
13. Takuma Yoneda, Jeff Mitchell, Johannes Welbl, Pontus Stenetorp, and Sebastian Riedel. 2018. Ucl machine reading group: Four factor framework for fact finding (hexaf). In Proceedings of the First Workshop on FEVER, pages 97–102. [find](https://scholar.google.com/scholar?q=Takuma+Yoneda%2C+Jeff+Mitchell%2C+Johannes+Welbl%2C+Pontus+Stenetorp%2C+and+Sebastian+Riedel%2E+2018%2E+Ucl+machine+reading+group%3A+Four+factor+framework+for+fact+finding+%28hexaf%29%2E+In+Proceedings+of+the+First+Works)
14. Rasmus Palm, Ulrich Paquet, and Ole Winther. 2018. Recurrent relational networks. In Proceedings of NIPS, pages 3368–3378. [find](https://scholar.google.com/scholar?q=Rasmus+Palm%2C+Ulrich+Paquet%2C+and+Ole+Winther%2E+2018%2E+Recurrent+relational+networks%2E+In+Proceedings+of+NIPS%2C+pages+3368%E2%80%933378%2E)
15. Ankur Parikh, Oscar Täckström, Dipanjan Das, and Jakob Uszkoreit. 2016. A decomposable attention model for natural language inference. In Proceedings of EMNLP, pages 2249–2255. [find](https://scholar.google.com/scholar?q=Ankur+Parikh%2C+Oscar+Ta%CC%88ckstro%CC%88m%2C+Dipanjan+Das%2C+and+Jakob+Uszkoreit%2E+2016%2E+A+decomposable+attention+model+for+natural+language+inference%2E+In+Proceedings+of+EMNLP%2C+pages+2249%E2%80%932255%2E) [our card](https://md.research.elamur.ai/free/en/papers/parikh-2016-decomposable-attention-model-natural-language/)
16. Matthew Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. Deep contextualized word representations. In Proceedings of NAACL-HLT, pages 2227–2237. [find](https://scholar.google.com/scholar?q=Matthew+Peters%2C+Mark+Neumann%2C+Mohit+Iyyer%2C+Matt+Gardner%2C+Christopher+Clark%2C+Kenton+Lee%2C+and+Luke+Zettlemoyer%2E+2018%2E+Deep+contextualized+word+representations%2E+In+Proceedings+of+NAACL%2DHLT%2C+pages+2227%E2%80%9322)
17. Alec Radford, Karthik Narasimhan, Tim Salimans, and Ilya Sutskever. 2018. Improving language understanding by generative pre-training. In Proceedings of Technical report, OpenAI. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Karthik+Narasimhan%2C+Tim+Salimans%2C+and+Ilya+Sutskever%2E+2018%2E+Improving+language+understanding+by+generative+pre%2Dtraining%2E+In+Proceedings+of+Technical+report%2C+OpenAI%2E)
18. Lei Sha, Baobao Chang, Zhifang Sui, and Sujian Li. 2016. Reading and thinking: Re-read lstm unit for textual entailment recognition. In Proceedings of COLING, pages 2870–2879. [find](https://scholar.google.com/scholar?q=Lei+Sha%2C+Baobao+Chang%2C+Zhifang+Sui%2C+and+Sujian+Li%2E+2016%2E+Reading+and+thinking%3A+Re%2Dread+lstm+unit+for+textual+entailment+recognition%2E+In+Proceedings+of+COLING%2C+pages+2870%E2%80%932879%2E)
19. Yi Tay, Anh Tuan Luu, and Siu Cheung Hui. 2018. Compare, compress and propagate: Enhancing neural architectures with alignment factorization for natural language inference. In Proceedings of EMNLP, pages 1565–1575. [find](https://scholar.google.com/scholar?q=Yi+Tay%2C+Anh+Tuan+Luu%2C+and+Siu+Cheung+Hui%2E+2018%2E+Compare%2C+compress+and+propagate%3A+Enhancing+neural+architectures+with+alignment+factorization+for+natural+language+inference%2E+In+Proceedings+of+EMNLP%2C+pa)
20. James Thorne, Andreas Vlachos, Christos Christodoulopoulos, and Arpit Mittal. 2018a. Fever: a large-scale dataset for fact extraction and verification. In Proceedings of NAACL-HLT, pages 809–819. [find](https://scholar.google.com/scholar?q=James+Thorne%2C+Andreas+Vlachos%2C+Christos+Christodoulopoulos%2C+and+Arpit+Mittal%2E+2018a%2E+Fever%3A+a+large%2Dscale+dataset+for+fact+extraction+and+verification%2E+In+Proceedings+of+NAACL%2DHLT%2C+pages+809%E2%80%93819%2E) [our card](https://md.research.elamur.ai/free/en/papers/thorne-2018-fever-large-scale-dataset-fact/)
21. James Thorne, Andreas Vlachos, Oana Cocarascu, Christos Christodoulopoulos, and Arpit Mittal. 2018b. The Fact Extraction and VERification (FEVER) shared task. In Proceedings of the First Workshop on FEVER, pages 1–9. [find](https://scholar.google.com/scholar?q=James+Thorne%2C+Andreas+Vlachos%2C+Oana+Cocarascu%2C+Christos+Christodoulopoulos%2C+and+Arpit+Mittal%2E+2018b%2E+The+Fact+Extraction+and+VERification+%28FEVER%29+shared+task%2E+In+Proceedings+of+the+First+Workshop+on+F) [our card](https://md.research.elamur.ai/free/en/papers/thorne-2018-fact-extraction-verification-fever-shared/)
22. Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2018. Graph attention networks. In Proceedings of ICLR. [find](https://scholar.google.com/scholar?q=Petar+Velickovic%2C+Guillem+Cucurull%2C+Arantxa+Casanova%2C+Adriana+Romero%2C+Pietro+Lio%2C+and+Yoshua+Bengio%2E+2018%2E+Graph+attention+networks%2E+In+Proceedings+of+ICLR%2E)
23. Quan Wang, Zhendong Mao, Bin Wang, and Li Guo. 2017. Knowledge graph embedding: A survey of approaches and applications. IEEE TKDE, 29(12):2724–2743. [find](https://scholar.google.com/scholar?q=Quan+Wang%2C+Zhendong+Mao%2C+Bin+Wang%2C+and+Li+Guo%2E+2017%2E+Knowledge+graph+embedding%3A+A+survey+of+approaches+and+applications%2E+IEEE+TKDE%2C+29%2812%29%3A2724%E2%80%932743%2E)