scholarly journals GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension

2020 ◽  
Author(s):  
Yu Chen ◽  
Lingfei Wu ◽  
Mohammed J. Zaki
Keyword(s):  
Structure Learning ◽  
State Of The Art ◽  
Graph Structure ◽  
Semantic Relationships ◽  
Word Sequence ◽  
Proposed Model ◽  
Learning Technique ◽  
Graph Structure Learning ◽  
Visualization Experiments ◽  
Graph Neural Networks

Conversational machine comprehension (MC) has proven significantly more challenging compared to traditional MC since it requires better utilization of conversation history. However, most existing approaches do not effectively capture conversation history and thus have trouble handling questions involving coreference or ellipsis. Moreover, when reasoning over passage text, most of them simply treat it as a word sequence without exploring rich semantic relationships among words. In this paper, we first propose a simple yet effective graph structure learning technique to dynamically construct a question and conversation history aware context graph at each conversation turn. Then we propose a novel Recurrent Graph Neural Network, and based on that, we introduce a flow mechanism to model the temporal dependencies in a sequence of context graphs. The proposed GraphFlow model can effectively capture conversational flow in a dialog, and shows competitive performance compared to existing state-of-the-art methods on CoQA, QuAC and DoQA benchmarks. In addition, visualization experiments show that our proposed model can offer good interpretability for the reasoning process.

scholarly journals Graph Dilated Network with Rejection Mechanism

2020 ◽  
Vol 10 (7) ◽  
pp. 2421
Author(s):  
Bencheng Yan ◽  
Chaokun Wang ◽  
Gaoyang Guo
Keyword(s):  
Neural Network ◽  
State Of The Art ◽  
Great Success ◽  
Convolution Kernel ◽  
Graph Structure ◽  
Proposed Model ◽  
Rejection Mechanism ◽  
Laplacian Smoothing ◽  
Graph Neural Networks ◽  
High Level

Recently, graph neural networks (GNNs) have achieved great success in dealing with graph-based data. The basic idea of GNNs is iteratively aggregating the information from neighbors, which is a special form of Laplacian smoothing. However, most of GNNs fall into the over-smoothing problem, i.e., when the model goes deeper, the learned representations become indistinguishable. This reflects the inability of the current GNNs to explore the global graph structure. In this paper, we propose a novel graph neural network to address this problem. A rejection mechanism is designed to address the over-smoothing problem, and a dilated graph convolution kernel is presented to capture the high-level graph structure. A number of experimental results demonstrate that the proposed model outperforms the state-of-the-art GNNs, and can effectively overcome the over-smoothing problem.

scholarly journals Knowledge Transfer for Out-of-Knowledge-Base Entities : A Graph Neural Network Approach

2017 ◽  
Author(s):  
Takuo Hamaguchi ◽  
Hidekazu Oiwa ◽  
Masashi Shimbo ◽  
Yuji Matsumoto
Keyword(s):  
Neural Network ◽  
Knowledge Base ◽  
State Of The Art ◽  
Test Time ◽  
Network Approach ◽  
Missing Information ◽  
Neural Network Approach ◽  
Training Time ◽  
Proposed Model ◽  
Graph Neural Networks

Knowledge base completion (KBC) aims to predict missing information in a knowledge base. In this paper, we address the out-of-knowledge-base (OOKB) entity problem in KBC: how to answer queries concerning test entities not observed at training time. Existing embedding-based KBC models assume that all test entities are available at training time, making it unclear how to obtain embeddings for new entities without costly retraining. To solve the OOKB entity problem without retraining, we use graph neural networks (Graph-NNs) to compute the embeddings of OOKB entities, exploiting the limited auxiliary knowledge provided at test time. The experimental results show the effectiveness of our proposed model in the OOKB setting. Additionally, in the standard KBC setting in which OOKB entities are not involved, our model achieves state-of-the-art performance on the WordNet dataset.

Speedup Robust Graph Structure Learning with Low-Rank Information

2021 ◽  
Author(s):  
Hui Xu ◽  
Liyao Xiang ◽  
Jiahao Yu ◽  
Anqi Cao ◽  
Xinbing Wang
Keyword(s):  
Structure Learning ◽  
Low Rank ◽  
Graph Structure ◽  
Graph Structure Learning

scholarly journals GRAPH STRUCTURE LEARNING FOR TASK ORDERING

2009 ◽  
Author(s):  
Yiming Yang ◽  
Abhimanyu Lad ◽  
Henry Shu ◽  
Bryan Kisiel ◽  
Chad Cumby ◽  
...  
Keyword(s):  
Structure Learning ◽  
Graph Structure ◽  
Graph Structure Learning ◽  
Task Ordering

scholarly journals Graph Transformer for Graph-to-Sequence Learning

2020 ◽  
Vol 34 (05) ◽  
pp. 7464-7471
Author(s):  
Deng Cai ◽  
Wai Lam
Keyword(s):  
Neural Networks ◽  
Information Exchange ◽  
State Of The Art ◽  
Structural Information ◽  
Representation Learning ◽  
Graph Representation ◽  
Text Generation ◽  
Proposed Model ◽  
Graph Neural Networks ◽  
Meaning Representation

The dominant graph-to-sequence transduction models employ graph neural networks for graph representation learning, where the structural information is reflected by the receptive field of neurons. Unlike graph neural networks that restrict the information exchange between immediate neighborhood, we propose a new model, known as Graph Transformer, that uses explicit relation encoding and allows direct communication between two distant nodes. It provides a more efficient way for global graph structure modeling. Experiments on the applications of text generation from Abstract Meaning Representation (AMR) and syntax-based neural machine translation show the superiority of our proposed model. Specifically, our model achieves 27.4 BLEU on LDC2015E86 and 29.7 BLEU on LDC2017T10 for AMR-to-text generation, outperforming the state-of-the-art results by up to 2.2 points. On the syntax-based translation tasks, our model establishes new single-model state-of-the-art BLEU scores, 21.3 for English-to-German and 14.1 for English-to-Czech, improving over the existing best results, including ensembles, by over 1 BLEU.

Sign in / Sign up

Export Citation Format

Share Document