Dynamically Fused Graph Network for Multi-hop Reasoning

Qiu, Lin; Xiao, Yunxuan; Qu, Yanru; Zhou, Hao; Li, Lei; Zhang, Weinan; Yu, Yong

doi:10.18653/v1/p19-1617

Cited by 134 publications

(149 citation statements)

References 19 publications

Supporting

Mentioning

149

Contrasting

Order By: Relevance

“…These works explored the entity graph construction problem in question answering. Qiu et al [32] constructed an entity graph to aggregate entities in a sentence and co-reference entity information in the multiple paragraphs. They used graph attention network [31] for dynamic reasoning on entity graph to get the answer.…”

Section: Related Workmentioning

confidence: 99%

“…To overcome these limitations, we propose a multiple granularity graph network to solve the interpretable multi-hop multi-documents question answering. Inspired by DFGN [32], we design a multi-granularity graph model to reason over the context. In addition to the entity graph, we construct a sentence graph to complement sentence information.…”

Section: Related Workmentioning

confidence: 99%

“…For comparative questions, the entities are the initiators of two comparison subjects. We use three methods as [32] to construct the entity graph. First, entities in the same sentence are connected.…”

Section: E Entity Graphmentioning

confidence: 99%

“…Cao et al [9] distinguished different relations by a relational graph convolutional neural network (GCN) [29]. Qiu et al [32] designed a dynamically fused graph network to get the answer. They used graph attention network [31] to aggregate entity information.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

et al. 2020

View full text Add to dashboard Cite

Interpretable multi-hop question answering requires step-by-step reasoning over multiple documents and finding scattered supporting facts to answer the question. Prior works have proposed the entity graph method to aggregate the entity information to improve the ability of reasoning. However, the entity graph loses some nonentity information that is also important to understand the semantics. Moreover, the entities distributed in the noisy sentences may mislead the reasoning process. 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. The CFGGN consists of a coarse-grain module to perform sentence-level reasoning and a fine-grain module to make entity-level reference. In sentence-level reasoning, the sentence graph is constructed to filter out the noisy sentences and capture the sentence features. 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. To enhance the interpretability of the overall process, we calculate the reasoning score for each step and present the reasoning path from the multiple documents to the final answer. Evaluation on the HotpotQA dataset in the distractor setting shows that our method outperforms the published SOTA entity-based method in five out of six metrics. INDEX TERMS Question answering, multi-hop questions, graph network, interpretable model.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: E Entity Graphmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The number of extracted entities is denoted as N, while the entity graph is constructed with entities as nodes. The edge, which is the same with the DFGN [42], is built because this link ensures that entities across multiple documents are connected. Different from the DFGN, additional background knowledge is adopted to enhance the nodes' relations, which will make our entity graph more exact.…”

Section: Constructing the Entity Graphmentioning

confidence: 99%

The Graph Reasoning Approach Based on the Dynamic Knowledge Auxiliary for Complex Fact Verification

Wang

Xia

et al. 2020

Electronics

View full text Add to dashboard Cite

Complex fact verification (FV) requires fusing scattered sequences and performing multi-hop reasoning over these composed sequences. Recently, by employing some FV models, knowledge is obtained from context to support the reasoning process based on pretrained models (e.g., BERT, XLNET), and this model outperforms previous out-of-the-art FV models. In practice, however, the limited training data cannot provide enough background knowledge for FV tasks. Once the background knowledge changed, the pretrained models’ parameters cannot be updated. Additionally, noise against common sense cannot be accurately filtered out due to the lack of necessary knowledge, which may have a negative impact on the reasoning progress. Furthermore, existing models often wrongly label the given claims as ‘not enough information’ due to the lack of necessary conceptual relationship between pieces of evidence. In the present study, a Dynamic Knowledge Auxiliary Graph Reasoning (DKAR) approach is proposed for incorporating external background knowledge in the current FV model, which explicitly identifies and fills the knowledge gaps between provided sources and the given claims, to enhance the reasoning ability of graph neural networks. Experiments show that DKAR put forward in this study can be combined with specific and discriminative knowledge to guide the FV system to successfully overcome the knowledge-gap challenges and achieve improvement in FV tasks. Furthermore, DKAR is adopted to complete the FV task on the Fake NewsNet dataset, showing outstanding advantages in a small sample and heterogeneous web text source.

show abstract

EventBERT: Incorporating Event-Based Semantics for Natural Language Understanding

Zou

Zhang

Zhao

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Natural language understanding tasks require a comprehensive understanding of natural language and further reasoning about it, on the basis of holistic information at different levels to gain comprehensive knowledge. In recent years, pre-trained language models (PrLMs) have shown impressive performance in natural language understanding. However, they rely mainly on extracting context-sensitive statistical patterns without explicitly modeling linguistic information, such as semantic relationships entailed in natural language. In this work, we propose EventBERT, an event-based semantic representation model that takes BERT as the backbone and refines with event-based structural semantics in terms of graph convolution networks. EventBERT benefits simultaneously from rich event-based structures embodied in the graph and contextual semantics learned in pre-trained model BERT. Experimental results on the GLUE benchmark show that the proposed model consistently outperforms the baseline model.

show abstract

Dynamically Fused Graph Network for Multi-hop Reasoning

Cited by 134 publications

References 19 publications

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

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

The Graph Reasoning Approach Based on the Dynamic Knowledge Auxiliary for Complex Fact Verification

EventBERT: Incorporating Event-Based Semantics for Natural Language Understanding

Contact Info

Product

Resources

About