Filters








1,217 Hits in 3.1 sec

Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networks [article]

Linfeng Song, Zhiguo Wang, Mo Yu, Yue Zhang, Radu Florian, Daniel Gildea
2018 arXiv   pre-print
Multi-hop reading comprehension focuses on one type of factoid question, where a system needs to properly integrate multiple pieces of evidence to correctly answer a question.  ...  To perform evidence integration on our graphs, we investigate two recent graph neural networks, namely graph convolutional network (GCN) and graph recurrent network (GRN).  ...  Evidence integration with graph network Tackling multi-hop reading comprehension requires inferring on global context.  ... 
arXiv:1809.02040v1 fatcat:d2izcf5dvbgxjafoaxn6yjzzgu

A Survey on Explainability in Machine Reading Comprehension [article]

Mokanarangan Thayaparan, Marco Valentino, André Freitas
2020 arXiv   pre-print
This paper presents a systematic review of benchmarks and approaches for explainability in Machine Reading Comprehension (MRC).  ...  In addition, we identify persisting open research questions and highlight critical directions for future work.  ...  ., 2020; reading comprehension tasks.  ... 
arXiv:2010.00389v1 fatcat:jzxjysnma5ee5auvplfxxfar2u

Identifying Supporting Facts for Multi-hop Question Answering with Document Graph Networks [article]

Mokanarangan Thayaparan, Marco Valentino, Viktor Schlegel, Andre Freitas
2019 arXiv   pre-print
This paper proposes Document Graph Network (DGN), a message passing architecture for the identification of supporting facts over a graph-structured representation of text.  ...  supporting multi-hop reasoning.  ...  Acknowledgements The authors would like to express their gratitude towards members of the AI Systems lab at the University of Manchester for many fruitful and intense discussions.  ... 
arXiv:1910.00290v1 fatcat:meqmwwjbljef3aubn6everxakm

Efficient Context-Aware Neural Machine Translation with Layer-Wise Weighting and Input-Aware Gating

Hongfei Xu, Deyi Xiong, Josef van Genabith, Qiuhui Liu
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
Existing Neural Machine Translation (NMT) systems are generally trained on a large amount of sentence-level parallel data, and during prediction sentences are independently translated, ignoring cross-sentence  ...  Instead of separately performing source context and input encoding, we propose to iteratively and jointly encode the source input and its contexts and to generate input-aware context representations with  ...  PathNet [Kundu et al., 2019] proposed a typical path-based approach for multi-hop reading comprehension.  ... 
doi:10.24963/ijcai.2020/540 dblp:conf/ijcai/TangSMXYL20 fatcat:be5qe2nhczawjmuvjr4xpaktlq

Multi-hop Reading Comprehension across Documents with Path-based Graph Convolutional Network [article]

Zeyun Tang, Yongliang Shen, Xinyin Ma, Wei Xu, Jiale Yu, Weiming Lu
2020 arXiv   pre-print
Multi-hop reading comprehension across multiple documents attracts much attention recently. In this paper, we propose a novel approach to tackle this multi-hop reading comprehension problem.  ...  This graph can combine both the idea of the graph-based and path-based approaches, so it is better for multi-hop reasoning.  ...  Table 1 : 1 An example of multi-hop reading comprehension across documents. graph, and then employ Graph Neural Networks based message passing algorithms to perform multi-step reasoning.  ... 
arXiv:2006.06478v2 fatcat:n6ryecpfa5eblocqokm2x4r5ri

Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs [article]

Ming Tu, Guangtao Wang, Jing Huang, Yun Tang, Xiaodong He, Bowen Zhou
2019 arXiv   pre-print
We employ Graph Neural Networks (GNN) based message passing algorithms to accumulate evidences on the proposed HDE graph.  ...  Multi-hop reading comprehension (RC) across documents poses new challenge over single-document RC because it requires reasoning over multiple documents to reach the final answer.  ...  Acknowledgements We would like to thank Johannes Welbl for running evaluation on our submitted model.  ... 
arXiv:1905.07374v2 fatcat:epznpgcp7vgovminxdcn53t5yq

Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs

Ming Tu, Guangtao Wang, Jing Huang, Yun Tang, Xiaodong He, Bowen Zhou
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
We employ Graph Neural Networks (GNN) based message passing algorithms to accumulate evidences on the proposed HDE graph.  ...  Multi-hop reading comprehension (RC) across documents poses new challenge over singledocument RC because it requires reasoning over multiple documents to reach the final answer.  ...  Acknowledgements We would like to thank Johannes Welbl from University College London for running evaluation on our submitted model.  ... 
doi:10.18653/v1/p19-1260 dblp:conf/acl/TuWHTHZ19 fatcat:os2vkhkzynh5bl2xk44yzhdpkq

Tackling Graphical Natural Language Processing's Problems with Recurrent Neural Networks

Ali Sami Sosa, Saja Majeed Mohammed, Haider Hadi Abbas, Israa Al Barazanchi
2019 Journal of Southwest Jiaotong University  
decoded with graph recurrent neural network.  ...  In this paper, we propose a novel graph neural network, named graph recurrent network.  ...  For example, it is needed to correctly answer a question. A more challenging yet practical extension is multi-hop reading comprehension (MHRC) [8] .  ... 
doi:10.35741/issn.0258-2724.54.5.35 fatcat:6vimnp7scrahhbfl2cdmwa3q5u

Graph-free Multi-hop Reading Comprehension: A Select-to-Guide Strategy [article]

Bohong Wu, Zhuosheng Zhang, Hai Zhao
2021 arXiv   pre-print
Multi-hop reading comprehension (MHRC) requires not only to predict the correct answer span in the given passage, but also to provide a chain of supporting evidences for reasoning interpretability.  ...  conforming to the nature of multi-hop reasoning.  ...  For Multi-hop Reading Comprehension, graph based methods were dominant, as it is quite natural to interpretate multi-hop reasoning steps as jumping over entity nodes.  ... 
arXiv:2107.11823v1 fatcat:7t4qikfdizabpf2hsoc2m3h4ku

Coarse and Fine Granularity Graph Reasoning for Interpretable Multi-hop Question Answering

Min Zhang, Feng Li, Yang Wang, Zequn Zhang, Yanhai Zhou, Xiaoyu Li
2020 IEEE Access  
In this paper, we propose the Coarse and Fine Granularity Graph Network (CFGGN), a novel interpretable model that combines both sentence information and entity information to answer the multi-hop questions  ...  In entity-level reference, a dynamic entity graph is used for the entity-level reasoning. We design a fusion module to integrate information of different granularity.  ...  ACKNOWLEDGMENT The authors thank their colleagues for helpful suggestions and discussions with regard to this work.  ... 
doi:10.1109/access.2020.2981134 fatcat:ixvp4axhsrfhreexfrihtuox2q

From LSAT: The Progress and Challenges of Complex Reasoning [article]

Siyuan Wang, Zhongkun Liu, Wanjun Zhong, Ming Zhou, Zhongyu Wei, Zhumin Chen, Nan Duan
2021 arXiv   pre-print
Further analysis also shows the effectiveness of combining the pre-trained models with the task-specific reasoning module, and integrating symbolic knowledge into discrete interpretable reasoning steps  ...  We further shed a light on the potential future directions, like unsupervised symbolic knowledge extraction, model interpretability, few-shot learning and comprehensive benchmark for complex reasoning.  ...  We then attempt a neural method utilizing a graph network for modeling constraints between participants.  ... 
arXiv:2108.00648v1 fatcat:q6oy5rzbs5dcfc2cdkrslhmmpi

Answering Any-hop Open-domain Questions with Iterative Document Reranking [article]

Ping Nie, Yuyu Zhang, Arun Ramamurthy, Le Song
2021 arXiv   pre-print
Existing approaches for open-domain question answering (QA) are typically designed for questions that require either single-hop or multi-hop reasoning, which make strong assumptions of the complexity of  ...  To improve the retrieval accuracy, we propose a graph-based reranking model that perform multi-document interaction as the core of our iterative reranking framework.  ...  Graph Neural Networks for QA.  ... 
arXiv:2009.07465v5 fatcat:m3hosnzbwvdx3k3g7x7tlm5zhi

Integrative Analysis of Patient Health Records and Neuroimages via Memory-based Graph Convolutional Network [article]

Xi Sheryl Zhang, Jingyuan Chou, Fei Wang
2019 arXiv   pre-print
In this paper, we proposed a framework, Memory-Based Graph Convolution Network (MemGCN), to perform integrative analysis with such multi-modal data.  ...  To further enhance the analytical power of MemGCN, we also designed a multi-hop strategy that allows multiple reading and updating on the memory can be performed at each iteration.  ...  The authors would like to thank the support from Amazon Web Service Machine Learning for Research Award (AWS MLRA).  ... 
arXiv:1809.06018v4 fatcat:tqawiaohcfcrfo4kazsx2fhm5y

Hierarchical Graph Network for Multi-hop Question Answering [article]

Yuwei Fang, Siqi Sun, Zhe Gan, Rohit Pillai, Shuohang Wang, Jingjing Liu
2020 arXiv   pre-print
In this paper, we present Hierarchical Graph Network (HGN) for multi-hop question answering.  ...  Given this hierarchical graph, the initial node representations are updated through graph propagation, and multi-hop reasoning is performed via traversing through the graph edges for each subsequent sub-task  ...  Graph Neural Network Recent studies on multi-hop QA also build graphs based on entities and reasoning over the constructed graph using graph neural networks (Kipf and Welling, 2017; Veličković et al.,  ... 
arXiv:1911.03631v4 fatcat:r5agg5orufhmtlu6n266l4zeam

A Cognitive Method for Automatically Retrieving Complex Information on a Large Scale

Yongyue Wang, Beitong Yao, Tianbo Wang, Chunhe Xia, Xianghui Zhao
2020 Sensors  
retrieving reasoning paths over the cognitive graph to provide users with verified multi-hop reasoning chains.  ...  Complex information retrieval (IR) tasks requiring multi-hop reasoning need to fuse multiple scattered text across two or more documents. However, there are two challenges for multi-hop retrieval.  ...  Other frameworks, such as Memory Networks [36] , deal with multi-hop reasoning.  ... 
doi:10.3390/s20113057 pmid:32481652 fatcat:nxm2wll22jffdo2hhue7rgbadq
« Previous Showing results 1 — 15 out of 1,217 results