---
title: "Hierarchical Graph Network for Multi-hop Question Answering"
description: "The authors propose the Hierarchical Graph Network (HGN). 45 references, cited by 70 papers here."
authors: ["Yuwei Fang", "Siqi Sun", "Zhe Gan", "Rohit Pillai", "Shuohang Wang", "Jingjing Liu"]
year: 2020
venue: "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)"
source: "https://aclanthology.org/2020.emnlp-main.710/"
doi: "10.18653/v1/2020.emnlp-main.710"
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/fang-2020-hierarchical-graph-network-multi-hop/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/fang-2020-hierarchical-graph-network-multi-hop/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2020](https://md.research.elamur.ai/free/en/papers/2020/page/3/) / Hierarchical Graph Network for Multi-hop Question Answering

# Hierarchical Graph Network for Multi-hop Question Answering

**Authors:** [Yuwei Fang](https://md.research.elamur.ai/free/en/authors/yuwei-fang/), [Siqi Sun](https://md.research.elamur.ai/free/en/authors/siqi-sun/), [Zhe Gan](https://md.research.elamur.ai/free/en/authors/zhe-gan/), Rohit Pillai, [Shuohang Wang](https://md.research.elamur.ai/free/en/authors/shuohang-wang/) and [Jingjing Liu](https://md.research.elamur.ai/free/en/authors/jingjing-liu/) · **Year:** 2020 · **Venue:** [Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/) ([EMNLP 2020](https://md.research.elamur.ai/free/en/venues/emnlp/2020/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/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/2020.emnlp-main.710/) · [PDF](https://aclanthology.org/2020.emnlp-main.710.pdf) · [DOI 10.18653/v1/2020.emnlp-main.710](https://doi.org/10.18653/v1/2020.emnlp-main.710) · [OpenAlex](https://openalex.org/W3105055324)

**Citations:** 171 citations (OpenAlex, 2026-10-14) · [70](https://md.research.elamur.ai/free/en/papers/fang-2020-hierarchical-graph-network-multi-hop/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
Multi-hop question answering requires a model to combine evidence spread over several paragraphs. It must jointly predict the answer and the sentences that support it. Earlier graph-based systems mostly used entity-only or paragraph-entity graphs and applied them mainly to answer prediction, which helped little with supporting facts. The authors propose the Hierarchical Graph Network (HGN). For each question it builds one graph with four node types: question, paragraphs, sentences and entities. Relevant paragraphs are chosen by title matching and a RoBERTa-based ranker, and Wikipedia hyperlinks then lead to second-hop paragraphs. A pre-trained encoder initializes the nodes, and graph-attention message passing updates them. The updated nodes feed several jointly trained heads: paragraph selection, supporting-fact prediction, entity prediction and answer span extraction. On HotpotQA, HGN reports state-of-the-art results in both the Distractor and Fullwiki settings. Ablations show that the hierarchical graph beats both flat and no-graph variants. This matters because mixing granularity levels gives useful supervision for both evidence extraction and answering.

## Key points
- **Graph design:** the graph is built over at most four paragraphs and two hops. Second-hop paragraphs are found through Wikipedia hyperlinks, which replace noisy entity linking, and sentence-paragraph edges are bidirectional.
- **Ablation (dev, Distractor, RoBERTa-large):** Joint F1 rises from 71.02 without a graph to 74.37 with the full hierarchical graph. Simpler paragraph-sentence and paragraph-sentence-entity graphs score in between.
- **Encoder comparison (dev, Distractor):** HGN with ALBERT-xxlarge-v2 reaches 83.46 Ans F1, 89.2 Sup F1 and 75.79 Joint F1. HGN with BERT-base (66.90 Joint F1) outperforms DFGN with BERT-base (59.89), and HGN with RoBERTa (74.37) outperforms SAE with RoBERTa (72.75).
- **Question types:** bridge questions make up about 80% of the dev set, and HGN scores 73.31 Joint F1 on them. Yes/no comparison questions are the easiest, at 88.50 Joint F1.
- **Error analysis:** the authors manually examined 100 dev examples with zero answer F1 and sorted them into six categories: annotation, multiple answers, discrete reasoning, commonsense/external knowledge, multi-hop, and MRC span errors. Most failures fall into the last two. Code is available at github.com/yuwfan/HGN.

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

## Institutions

- [Microsoft](https://md.research.elamur.ai/free/en/companies/microsoft/) — Company, Redmond, United States · 240 works · 123,537 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,086 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,889 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 1,282 works

🧭 Topics (1): [❓ Question answering](https://md.research.elamur.ai/free/en/topics/question-answering/) · 242 works

## Cite

Cite as: Yuwei Fang, Siqi Sun, Zhe Gan, Rohit Pillai, Shuohang Wang and Jingjing Liu. 2020. Hierarchical Graph Network for Multi-hop Question Answering. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP).

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

```bibtex
@inproceedings{fang2020hierarchical,
  title = {{Hierarchical Graph Network for Multi-hop Question Answering}},
  author = {Yuwei Fang, Siqi Sun, Zhe Gan, Rohit Pillai, Shuohang Wang and Jingjing Liu},
  booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year = {2020},
  doi = {10.18653/v1/2020.emnlp-main.710},
  url = {https://doi.org/10.18653/v1/2020.emnlp-main.710}
}
```

- [← previous A review of sentiment analysis research in Arabic language](https://md.research.elamur.ai/free/en/papers/oueslati-2020-review-sentiment-analysis-research-arabic/)
- [next → Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reports](https://md.research.elamur.ai/free/en/papers/zhang-2020-optimizing-factual-correctness-summary-study/)
- [↑ back to papers of 2020](https://md.research.elamur.ai/free/en/papers/2020/page/3/)

## References

45 references, 26 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Akari Asai, Kazuma Hashimoto, Hannaneh Hajishirzi, Richard Socher, and Caiming Xiong. 2020. [Learning to retrieve reasoning paths over wikipedia graph for question answering](https://md.research.elamur.ai/free/en/papers/asai-2019-learning-retrieve-reasoning-paths-over/). In ICLR.
2. Iz Beltagy, Matthew E. Peters, and Arman Cohan. 2020. [Longformer: The long-document transformer](https://md.research.elamur.ai/free/en/papers/beltagy-2020-longformer-long-document-transformer/). arXiv preprint arXiv:2004.05150.
3. Danqi Chen, Adam Fisch, Jason Weston, and Antoine Bordes. 2017. [Reading Wikipedia to answer open-domain questions](https://md.research.elamur.ai/free/en/papers/chen-2017-reading-wikipedia-answer-open-domain/). In ACL.
4. Jifan Chen and Greg Durrett. 2019. [Understanding dataset design choices for multi-hop reasoning](https://md.research.elamur.ai/free/en/papers/chen-2019-understanding-dataset-design-choices-multi/). In NAACL.
5. Jifan Chen, Shih-ting Lin, and Greg Durrett. 2019. Multi-hop question answering via reasoning chains. arXiv preprint arXiv:1910.02610. — [arXiv:1910.02610](https://arxiv.org/abs/1910.02610) [find](https://scholar.google.com/scholar?q=Jifan+Chen%2C+Shih%2Dting+Lin%2C+and+Greg+Durrett%2E+2019%2E+Multi%2Dhop+question+answering+via+reasoning+chains%2E+arXiv+preprint+arXiv%3A1910%2E02610%2E+%E2%80%94+%5BarXiv%3A1910%2E02610%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1910%2E02610%29)
6. Eunsol Choi, Daniel Hewlett, Jakob Uszkoreit, Illia Polosukhin, Alexandre Lacoste, and Jonathan Berant. 2017. Coarse-to-fine question answering for long documents. In ACL. [find](https://scholar.google.com/scholar?q=Eunsol+Choi%2C+Daniel+Hewlett%2C+Jakob+Uszkoreit%2C+Illia+Polosukhin%2C+Alexandre+Lacoste%2C+and+Jonathan+Berant%2E+2017%2E+Coarse%2Dto%2Dfine+question+answering+for+long+documents%2E+In+ACL%2E)
7. Nicola De Cao, Wilker Aziz, and Ivan Titov. 2019. [Question answering by reasoning across documents with graph convolutional networks](https://md.research.elamur.ai/free/en/papers/cao-2019-question-answering-reasoning-across-documents/). In NAACL.
8. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. [Bert: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). In NAACL.
9. Bhuwan Dhingra, Qiao Jin, Zhilin Yang, William W Cohen, and Ruslan Salakhutdinov. 2018. [Neural models for reasoning over multiple mentions using coreference](https://md.research.elamur.ai/free/en/papers/dhingra-2018-neural-models-reasoning-over-multiple/). In NAACL.
10. Ming Ding, Chang Zhou, Qibin Chen, Hongxia Yang, and Jie Tang. 2019. Cognitive graph for multi-hop reading comprehension at scale. In ACL. [find](https://scholar.google.com/scholar?q=Ming+Ding%2C+Chang+Zhou%2C+Qibin+Chen%2C+Hongxia+Yang%2C+and+Jie+Tang%2E+2019%2E+Cognitive+graph+for+multi%2Dhop+reading+comprehension+at+scale%2E+In+ACL%2E)
11. Yair Feldman and Ran El-Yaniv. 2019. Multi-hop paragraph retrieval for [open-domain question answering](https://md.research.elamur.ai/free/en/papers/chen-2020-open-domain-question-answering/). arXiv preprint arXiv:1906.06606.
12. Michael Glass, Alfio Gliozzo, Rishav Chakravarti, Anthony Ferritto, Lin Pan, GP Bhargav, Dinesh Garg, and Avirup Sil. 2019. Span selection pre-training for question answering. arXiv preprint arXiv:1909.04120. [find](https://scholar.google.com/scholar?q=Michael+Glass%2C+Alfio+Gliozzo%2C+Rishav+Chakravarti%2C+Anthony+Ferritto%2C+Lin+Pan%2C+GP+Bhargav%2C+Dinesh+Garg%2C+and+Avirup+Sil%2E+2019%2E+Span+selection+pre%2Dtraining+for+question+answering%2E+arXiv+preprint+arXiv%3A190)
13. Kosuke Nishida, Kyosuke Nishida, Masaaki Nagata, Atsushi Otsuka, Itsumi Saito, Hisako Asano, and Junji Tomita. 2019. Answering while summarizing: Multi-task learning for multi-hop qa with evidence extraction. In ACL. [find](https://scholar.google.com/scholar?q=Kosuke+Nishida%2C+Kyosuke+Nishida%2C+Masaaki+Nagata%2C+Atsushi+Otsuka%2C+Itsumi+Saito%2C+Hisako+Asano%2C+and+Junji+Tomita%2E+2019%2E+Answering+while+summarizing%3A+Multi%2Dtask+learning+for+multi%2Dhop+qa+with+evidence+ext)
14. Ameya Godbole, Dilip Kavarthapu, Rajarshi Das, Zhiyu Gong, Abhishek Singhal, Hamed Zamani, Mo Yu, Tian Gao, Xiaoxiao Guo, Manzil Zaheer, et al. 2019. Multi-step entity-centric information retrieval for multi-hop question answering. arXiv preprint arXiv:1909.07598. [find](https://scholar.google.com/scholar?q=Ameya+Godbole%2C+Dilip+Kavarthapu%2C+Rajarshi+Das%2C+Zhiyu+Gong%2C+Abhishek+Singhal%2C+Hamed+Zamani%2C+Mo+Yu%2C+Tian+Gao%2C+Xiaoxiao+Guo%2C+Manzil+Zaheer%2C+et+al%2E+2019%2E+Multi%2Dstep+entity%2Dcentric+information+retrieval+fo)
15. Peng Qi, Xiaowen Lin, Leo Mehr, Zijian Wang, and Christopher D. Manning. 2019. [Answering complex open-domain questions through iterative query generation](https://md.research.elamur.ai/free/en/papers/qi-2019-answering-complex-open-domain-questions/). In EMNLP.
16. Quentin Grail, Julien Perez, and Eric Gaussier. 2020. Latent question reformulation and information accumulation for multi-hop machine reading. [https://openreview.net/forum?id=S1x63TEYvr](https://openreview.net/forum?id=S1x63TEYvr). [↗](https://openreview.net/forum?id=S1x63TEYvr)
17. Yichen Jiang and Mohit Bansal. 2019a. [Avoiding reasoning shortcuts: Adversarial evaluation, training, and model development for multi-hop qa](https://md.research.elamur.ai/free/en/papers/jiang-2019-avoiding-reasoning-shortcuts-adversarial-evaluation/). In ACL.
18. Yichen Jiang and Mohit Bansal. 2019b. Self-assembling modular networks for interpretable multi-hop reasoning. In EMNLP. [find](https://scholar.google.com/scholar?q=Yichen+Jiang+and+Mohit+Bansal%2E+2019b%2E+Self%2Dassembling+modular+networks+for+interpretable+multi%2Dhop+reasoning%2E+In+EMNLP%2E)
19. Thomas N Kipf and Max Welling. 2017. [Semi-supervised classification with graph convolutional networks](https://md.research.elamur.ai/free/en/papers/kipf-2016-semi-supervised-classification-graph-convolutional/). In ICLR.
20. Guokun Lai, Qizhe Xie, Hanxiao Liu, Yiming Yang, and Eduard Hovy. 2017. [Race: Large-scale reading comprehension dataset from examinations](https://md.research.elamur.ai/free/en/papers/lai-2017-race-large-scale-reading-comprehension/). In EMNLP.
21. Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2020. Albert: A lite bert for self-supervised learning of language representations. In ICLR. [find](https://scholar.google.com/scholar?q=Zhenzhong+Lan%2C+Mingda+Chen%2C+Sebastian+Goodman%2C+Kevin+Gimpel%2C+Piyush+Sharma%2C+and+Radu+Soricut%2E+2020%2E+Albert%3A+A+lite+bert+for+self%2Dsupervised+learning+of+language+representations%2E+In+ICLR%2E)
22. Xiaodong Liu, Yelong Shen, Kevin Duh, and Jianfeng Gao. 2018. Stochastic answer networks for machine reading comprehension. In ACL. [find](https://scholar.google.com/scholar?q=Xiaodong+Liu%2C+Yelong+Shen%2C+Kevin+Duh%2C+and+Jianfeng+Gao%2E+2018%2E+Stochastic+answer+networks+for+machine+reading+comprehension%2E+In+ACL%2E)
23. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692. [find](https://scholar.google.com/scholar?q=Yinhan+Liu%2C+Myle+Ott%2C+Naman+Goyal%2C+Jingfei+Du%2C+Mandar+Joshi%2C+Danqi+Chen%2C+Omer+Levy%2C+Mike+Lewis%2C+Luke+Zettlemoyer%2C+and+Veselin+Stoyanov%2E+2019%2E+Roberta%3A+A+robustly+optimized+bert+pretraining+approach%2E+a)
24. Sewon Min, Eric Wallace, Sameer Singh, Matt Gardner, Hannaneh Hajishirzi, and Luke Zettlemoyer. 2019a. [Compositional questions do not necessitate multi-hop reasoning](https://md.research.elamur.ai/free/en/papers/min-2019-compositional-questions-do-not-necessitate/). In ACL.
25. Sewon Min, Victor Zhong, Richard Socher, and Caiming Xiong. 2018. [Efficient and robust question answering from minimal context over documents](https://md.research.elamur.ai/free/en/papers/min-2018-efficient-robust-question-answering-minimal/). In ACL.
26. Sewon Min, Victor Zhong, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2019b. [Multi-hop reading comprehension through question decomposition and rescoring](https://md.research.elamur.ai/free/en/papers/min-2019-multi-hop-reading-comprehension-through/). In ACL.
27. Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. [Squad: 100,000+ questions for machine comprehension of text](https://md.research.elamur.ai/free/en/papers/rajpurkar-2016-squad-100-000-questions-machine/). In EMNLP.
28. Minjoon Seo, Aniruddha Kembhavi, Ali Farhadi, and Hannaneh Hajishirzi. 2017. [Bidirectional attention flow for machine comprehension](https://md.research.elamur.ai/free/en/papers/seo-2016-bidirectional-attention-flow-machine-comprehension/). In ICLR.
29. Nan Shao, Yiming Cui, Ting Liu, Wang, and Guoping Hu Hu. 2020. Is graph structure necessary for multi-hop reasoningt. arXiv preprint arXiv:2004.03096. — [arXiv:2004.03096](https://arxiv.org/abs/2004.03096) [find](https://scholar.google.com/scholar?q=Nan+Shao%2C+Yiming+Cui%2C+Ting+Liu%2C+Wang%2C+and+Guoping+Hu+Hu%2E+2020%2E+Is+graph+structure+necessary+for+multi%2Dhop+reasoningt%2E+arXiv+preprint+arXiv%3A2004%2E03096%2E+%E2%80%94+%5BarXiv%3A2004%2E03096%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2004%2E0)
30. Linfeng Song, Zhiguo Wang, Mo Yu, Yue Zhang, Radu Florian, and Daniel Gildea. 2018. Exploring graph-structured passage representation for multi-hop reading comprehension with graph neural networks. arXiv preprint arXiv:1809.02040. — [arXiv:1809.02040](https://arxiv.org/abs/1809.02040) [find](https://scholar.google.com/scholar?q=Linfeng+Song%2C+Zhiguo+Wang%2C+Mo+Yu%2C+Yue+Zhang%2C+Radu+Florian%2C+and+Daniel+Gildea%2E+2018%2E+Exploring+graph%2Dstructured+passage+representation+for+multi%2Dhop+reading+comprehension+with+graph+neural+networks%2E+ar)
31. Swabha Swayamdipta, Ankur P. Parikh, and Tom Kwiatkowski. 2018. Multi-mention learning for reading comprehension with neural cascades. In ICLR. [find](https://scholar.google.com/scholar?q=Swabha+Swayamdipta%2C+Ankur+P%2E+Parikh%2C+and+Tom+Kwiatkowski%2E+2018%2E+Multi%2Dmention+learning+for+reading+comprehension+with+neural+cascades%2E+In+ICLR%2E)
32. Alon Talmor and Jonathan Berant. 2018. [The web as a knowledge-base for answering complex questions](https://md.research.elamur.ai/free/en/papers/talmor-2018-web-as-knowledge-base-answering/). In NAACL.
33. Adam Trischler, Tong Wang, Xingdi Yuan, Justin Harris, Alessandro Sordoni, Philip Bachman, and Kaheer Suleman. 2016. [Newsqa: A machine comprehension dataset](https://md.research.elamur.ai/free/en/papers/trischler-2017-newsqa-machine-comprehension-dataset/). arXiv preprint arXiv:1611.09830.
34. Ming Tu, Kevin Huang, Guangtao Wang, Jing Huang, Xiaodong He, and Bowen Zhou. 2020. Select, answer and explain: Interpretable multi-hop reading comprehension over multiple documents. In AAAI. [find](https://scholar.google.com/scholar?q=Ming+Tu%2C+Kevin+Huang%2C+Guangtao+Wang%2C+Jing+Huang%2C+Xiaodong+He%2C+and+Bowen+Zhou%2E+2020%2E+Select%2C+answer+and+explain%3A+Interpretable+multi%2Dhop+reading+comprehension+over+multiple+documents%2E+In+AAAI%2E)
35. Ming Tu, Guangtao Wang, Jing Huang, Yun Tang, Xiaodong He, and Bowen Zhou. 2019. Multi-hop reading comprehension across multiple documents by reasoning over heterogeneous graphs. In ACL. [find](https://scholar.google.com/scholar?q=Ming+Tu%2C+Guangtao+Wang%2C+Jing+Huang%2C+Yun+Tang%2C+Xiaodong+He%2C+and+Bowen+Zhou%2E+2019%2E+Multi%2Dhop+reading+comprehension+across+multiple+documents+by+reasoning+over+heterogeneous+graphs%2E+In+ACL%2E)
36. Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2018. Graph attention networks. In ICLR. [find](https://scholar.google.com/scholar?q=Petar+Velic%CC%8Ckovic%CC%81%2C+Guillem+Cucurull%2C+Arantxa+Casanova%2C+Adriana+Romero%2C+Pietro+Lio%2C+and+Yoshua+Bengio%2E+2018%2E+Graph+attention+networks%2E+In+ICLR%2E)
37. Shuohang Wang and Jing Jiang. 2017. [Machine comprehension using match-lstm and answer pointer](https://md.research.elamur.ai/free/en/papers/wang-2016-machine-comprehension-using-match-lstm/). In ICLR.
38. Shuohang Wang, Luowei Zhou, Zhe Gan, Yen-Chun Chen, Yuwei Fang, Siqi Sun, Yu Cheng, and Jingjing Liu. 2020. Cluster-former: Clustering-based sparse transformer for long-range dependency encoding. arXiv preprint arXiv:2009.06097. — [arXiv:2009.06097](https://arxiv.org/abs/2009.06097) [find](https://scholar.google.com/scholar?q=Shuohang+Wang%2C+Luowei+Zhou%2C+Zhe+Gan%2C+Yen%2DChun+Chen%2C+Yuwei+Fang%2C+Siqi+Sun%2C+Yu+Cheng%2C+and+Jingjing+Liu%2E+2020%2E+Cluster%2Dformer%3A+Clustering%2Dbased+sparse+transformer+for+long%2Drange+dependency+encoding%2E+arXi)
39. Johannes Welbl, Pontus Stenetorp, and Sebastian Riedel. 2018. [Constructing datasets for multi-hop reading comprehension across documents](https://md.research.elamur.ai/free/en/papers/welbl-2018-constructing-datasets-multi-hop-reading/). TACL.
40. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier-ric Cistac, Tim Rault, Rémi Louf, Morgan Funtowicz, and Jamie Brew. 2019. [Transformers: State-ofthe-art natural language processing](https://md.research.elamur.ai/free/en/papers/wolf-2020-transformers-state-art-natural-language/). arXiv preprint arXiv:1910.03771.
41. Yunxuan Xiao, Yanru Qu, Lin Qiu, Hao Zhou, Lei Li, Weinan Zhang, and Yong Yu. 2019. [Dynamically fused graph network for multi-hop reasoning](https://md.research.elamur.ai/free/en/papers/qiu-2019-dynamically-fused-graph-network-multi/). In ACL.
42. Wenhan Xiong, Mo Yu, Xiaoxiao Guo, Hong Wang, Shiyu Chang, Murray Campbell, and William Yang Wang. 2019. Simple yet effective bridge reasoning for open-domain multi-hop question answering. arXiv preprint arXiv:1909.07597. [find](https://scholar.google.com/scholar?q=Wenhan+Xiong%2C+Mo+Yu%2C+Xiaoxiao+Guo%2C+Hong+Wang%2C+Shiyu+Chang%2C+Murray+Campbell%2C+and+William+Yang+Wang%2E+2019%2E+Simple+yet+effective+bridge+reasoning+for+open%2Ddomain+multi%2Dhop+question+answering%2E+arXiv+prepr)
43. Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W Cohen, Ruslan Salakhutdinov, and Christopher D Manning. 2018. [Hotpotqa: A dataset for diverse, explainable multi-hop question answering](https://md.research.elamur.ai/free/en/papers/yang-2018-hotpotqa-dataset-diverse-explainable-multi/). In EMNLP.
44. Mohit Bansal Yixin Nie, Songhe Wang. 2019. [Revealing the importance of semantic retrieval for machine reading at scale](https://md.research.elamur.ai/free/en/papers/nie-2019-revealing-importance-semantic-retrieval-machine/). In EMNLP.
45. Manzil Zaheer, Guru Guruganesh, Avinava Dubey, Joshua Ainslie, Chris Alberti, Santiago Ontanon, Philip Pham, Anirudh Ravula, Qifan Wang, Li Yang, et al. 2020. [Big bird: Transformers for longer sequences](https://md.research.elamur.ai/free/en/papers/zaheer-2020-big-bird-transformers-longer-sequences/). arXiv preprint arXiv:2007.14062.

*Updated 24 October 2026*