Augmented Abstractive Summarization With Document-LevelSemantic Graph
- URL: http://arxiv.org/abs/2109.06046v1
- Date: Mon, 13 Sep 2021 15:12:34 GMT
- Title: Augmented Abstractive Summarization With Document-LevelSemantic Graph
- Authors: Qiwei Bi, Haoyuan Li, Kun Lu, Hanfang Yang
- Abstract summary: Previous abstractive methods apply sequence-to-sequence structures to generate summary without a module.
We utilize semantic graph to boost the generation performance.
A novel neural decoder is presented to leverage the information of such entity graphs.
- Score: 3.0272794341021667
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Previous abstractive methods apply sequence-to-sequence structures to
generate summary without a module to assist the system to detect vital mentions
and relationships within a document. To address this problem, we utilize
semantic graph to boost the generation performance. Firstly, we extract
important entities from each document and then establish a graph inspired by
the idea of distant supervision \citep{mintz-etal-2009-distant}. Then, we
combine a Bi-LSTM with a graph encoder to obtain the representation of each
graph node. A novel neural decoder is presented to leverage the information of
such entity graphs. Automatic and human evaluations show the effectiveness of
our technique.
Related papers
- SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning [131.04781590452308]
We present SimTeG, a frustratingly Simple approach for Textual Graph learning.
We first perform supervised parameter-efficient fine-tuning (PEFT) on a pre-trained LM on the downstream task.
We then generate node embeddings using the last hidden states of finetuned LM.
arXiv Detail & Related papers (2023-08-03T07:00:04Z) - Scientific Paper Extractive Summarization Enhanced by Citation Graphs [50.19266650000948]
We focus on leveraging citation graphs to improve scientific paper extractive summarization under different settings.
Preliminary results demonstrate that citation graph is helpful even in a simple unsupervised framework.
Motivated by this, we propose a Graph-based Supervised Summarization model (GSS) to achieve more accurate results on the task when large-scale labeled data are available.
arXiv Detail & Related papers (2022-12-08T11:53:12Z) - GrannGAN: Graph annotation generative adversarial networks [72.66289932625742]
We consider the problem of modelling high-dimensional distributions and generating new examples of data with complex relational feature structure coherent with a graph skeleton.
The model we propose tackles the problem of generating the data features constrained by the specific graph structure of each data point by splitting the task into two phases.
In the first it models the distribution of features associated with the nodes of the given graph, in the second it complements the edge features conditionally on the node features.
arXiv Detail & Related papers (2022-12-01T11:49:07Z) - Graph sampling for node embedding [0.0]
We propose sampling approaches to node embedding, with or without explicit modelling of the feature vector.
We aim to extract useful information from both the eigenvectors related to the graph Laplacien and the given values associated with the graph.
arXiv Detail & Related papers (2022-10-19T12:54:37Z) - Embedding Graphs on Grassmann Manifold [31.42901131602713]
This paper develops a new graph representation learning scheme, namely EGG, which embeds approximated second-order graph characteristics into a Grassmann manifold.
The effectiveness of EGG is demonstrated using both clustering and classification tasks at the node level and graph level.
arXiv Detail & Related papers (2022-05-30T12:56:24Z) - Self-supervised Consensus Representation Learning for Attributed Graph [15.729417511103602]
We introduce self-supervised learning mechanism to graph representation learning.
We propose a novel Self-supervised Consensus Representation Learning framework.
Our proposed SCRL method treats graph from two perspectives: topology graph and feature graph.
arXiv Detail & Related papers (2021-08-10T07:53:09Z) - Accurate Learning of Graph Representations with Graph Multiset Pooling [45.72542969364438]
We propose a Graph Multiset Transformer (GMT) that captures the interaction between nodes according to their structural dependencies.
Our experimental results show that GMT significantly outperforms state-of-the-art graph pooling methods on graph classification benchmarks.
arXiv Detail & Related papers (2021-02-23T07:45:58Z) - Learning the Implicit Semantic Representation on Graph-Structured Data [57.670106959061634]
Existing representation learning methods in graph convolutional networks are mainly designed by describing the neighborhood of each node as a perceptual whole.
We propose a Semantic Graph Convolutional Networks (SGCN) that explores the implicit semantics by learning latent semantic-paths in graphs.
arXiv Detail & Related papers (2021-01-16T16:18:43Z) - Spectral Embedding of Graph Networks [76.27138343125985]
We introduce an unsupervised graph embedding that trades off local node similarity and connectivity, and global structure.
The embedding is based on a generalized graph Laplacian, whose eigenvectors compactly capture both network structure and neighborhood proximity in a single representation.
arXiv Detail & Related papers (2020-09-30T04:59:10Z) - Heterogeneous Graph Neural Networks for Extractive Document
Summarization [101.17980994606836]
Cross-sentence relations are a crucial step in extractive document summarization.
We present a graph-based neural network for extractive summarization (HeterSumGraph)
We introduce different types of nodes into graph-based neural networks for extractive document summarization.
arXiv Detail & Related papers (2020-04-26T14:38:11Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.