paper-with-me

홈 › Papers

BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering

2019-04-10 · NAACL 2019 6 · Yu Cao, Meng Fang, DaCheng Tao

Multi-hop reasoning question answering requires deep comprehension of relationships between various documents and queries. We propose a Bi-directional Attention Entity Graph Convolutional Network (BAG), leveraging relationships between nodes in an entity graph and attention information between a query and the entity graph, to solve this task. Graph convolutional networks are used to obtain a relation-aware representation of nodes for entity graphs built from documents with multi-level features. Bidirectional attention is then applied on graphs and queries to generate a query-aware nodes representation, which will be used for the final prediction. Experimental evaluation shows BAG achieves state-of-the-art accuracy performance on the QAngaroo WIKIHOP dataset.

📄 PDF Abstract BibTeX arXiv:1904.04969

Code (1)

caoyu1991/BAG 공식 구현 pytorch

Tasks

Question Answering

Similar Papers 제목 키워드 기반

Bipartite Flat-Graph Network for Nested Named Entity Recognition

2020-05-01 · ACL 2020 6 · Ying Luo, Hai Zhao

In this paper, we propose a novel bipartite flat-graph network (BiFlaG) for nested named entity recognition (NER), which contains two subgraph modules: a flat NER module for outermost entities and a graph module for all …

named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NER+2

Multimodal joint prediction of traffic spatial-temporal data with graph sparse attention mechanism and bidirectional temporal convolutional network

2024-12-24 · Dongran Zhang, Jiangnan Yan, Kemal Polat, Adi Alhudhaif 외

Traffic flow prediction plays a crucial role in the management and operation of urban transportation systems. While extensive research has been conducted on predictions for individual transportation modes, there is relat…

Feature CorrelationPrediction

Hierarchical Neighbor Propagation With Bidirectional Graph Attention Network for Relation Prediction

2021-04-25 · IEEE/ACM Transactions on Audio, Speech, and Language Processing 2021 4 · Zhiwen Xie, Runjie Zhu, Jin Liu, Guangyou Zhou 외

Abstract—The graph attention network (GAT) [1] has started to become a mainstream neural network architecture since 2018, yielding remarkable performance gains in various natural language processing (NLP) tasks. Altho…

Graph AttentionRelationRelation Prediction

MRAEA: An Efficient and Robust Entity Alignment Approach for Cross-lingual Knowledge Graph

2020-02-03 · The International Conference on Web Search and Data Mining (WSDM) 2020 2 · Xin Mao, Wenting Wang, Huimin Xu, Man Lan 외

Entity alignment to find equivalent entities in cross-lingual Knowledge Graphs (KGs) plays a vital role in automatically integrating multiple KGs. Existing translation-based entity alignment methods jointly model the cro…

Entity AlignmentEntity EmbeddingsGraph Neural NetworkKnowledge Graphs+1

Focusing and Diffusion: Bidirectional Attentive Graph Convolutional Networks for Skeleton-based Action Recognition

2019-12-24 · Jialin Gao, Tong He, Xi Zhou, Shiming Ge

A collection of approaches based on graph convolutional networks have proven success in skeleton-based action recognition by exploring neighborhood information and dense dependencies between intra-frame joints. However, …

Action RecognitionSkeleton Based Action Recognition