Oct 2, 2020 · In this paper, we propose an abstractive summarization model based on discourse relation and graph convolutional networks (GCN).
Oct 14, 2020 · This paper proposes to use discourse relation in text summarization tasks, which can make the model focus on the important part of the text.
Abstractive Summarization via Discourse Relation and Graph ...
www.researchgate.net › ... › Discourse
Based on the traditional LSTM encoder, this paper adds graph convolutional networks to obtain the structural information of the text. In addition, this paper ...
To this end, we present a structure-aware sequence-to-sequence model, in which we equip abstractive conversation summarization models with rich conversation ...
Missing: Convolutional | Show results with:Convolutional
Each utterance is encoded via transformer encoder; discourse relation graphs and action graphs are encoded through Graph Attention Networks (a). The multi ...
Missing: Convolutional | Show results with:Convolutional
Dec 7, 2020 · A Dialogue Discourse-Aware Graph Convolutional Networks (DDA-GCN) for meeting summarization is developed by utilizing dialogue discourse, ...
Apr 16, 2021 · We propose to explicitly model the rich structures in conversations for more precise and accurate conversation summarization.
Missing: Convolutional Networks.
We propose a neural multi-document sum- marization (MDS) system that incorpo- rates sentence relation graphs. We employ a Graph Convolutional Network (GCN).
Dec 7, 2020 · In this paper, we develop a Dialogue Discourse-Aware Graph Convolutional Networks (DDA-GCN) for meeting summarization by utilizing dialogue ...
Missing: via | Show results with:via
They are shorter compared to conversations, which usually cover multiple topics between different speakers (over ten turns) (Feng et al., 2020).
People also ask
What is the difference between graph convolutional network and convolutional neural network?
What is the difference between abstractive text summarization and extractive text summarization?
What are graph convolutional networks good at?