An entity-guided text summarization framework with relational heterogeneous graph neural network

02/07/2023
by   Jingqiang Chen, et al.
0

Two crucial issues for text summarization to generate faithful summaries are to make use of knowledge beyond text and to make use of cross-sentence relations in text. Intuitive ways for the two issues are Knowledge Graph (KG) and Graph Neural Network (GNN) respectively. Entities are semantic units in text and in KG. This paper focuses on both issues by leveraging entities mentioned in text to connect GNN and KG for summarization. Firstly, entities are leveraged to construct a sentence-entity graph with weighted multi-type edges to model sentence relations, and a relational heterogeneous GNN for summarization is proposed to calculate node encodings. Secondly, entities are leveraged to link the graph to KG to collect knowledge. Thirdly, entities guide a two-step summarization framework defining a multi-task selector to select salient sentences and entities, and using an entity-focused abstractor to compress the sentences. GNN is connected with KG by constructing sentence-entity graphs where entity-entity edges are built based on KG, initializing entity embeddings on KG, and training entity embeddings using entity-entity edges. The relational heterogeneous GNN utilizes both edge weights and edge types in GNN to calculate graphs with weighted multi-type edges. Experiments show the proposed method outperforms extractive baselines including the HGNN-based HGNNSum and abstractive baselines including the entity-driven SENECA on CNN/DM, and outperforms most baselines on NYT50. Experiments on sub-datasets show the density of sentence-entity edges greatly influences the performance of the proposed method. The greater the density, the better the performance. Ablations show effectiveness of the method.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/13/2022

Pruned Graph Neural Network for Short Story Ordering

Text coherence is a fundamental problem in natural language generation a...
research
11/06/2019

Multi-Paragraph Reasoning with Knowledge-enhanced Graph Neural Network

Multi-paragraph reasoning is indispensable for open-domain question answ...
research
04/27/2022

Learning to Borrow – Relation Representation for Without-Mention Entity-Pairs for Knowledge Graph Completion

Prior work on integrating text corpora with knowledge graphs (KGs) to im...
research
01/17/2021

Heterogeneous Similarity Graph Neural Network on Electronic Health Records

Mining Electronic Health Records (EHRs) becomes a promising topic becaus...
research
04/12/2022

Trigger-GNN: A Trigger-Based Graph Neural Network for Nested Named Entity Recognition

Nested named entity recognition (NER) aims to identify the entity bounda...
research
04/03/2021

Medical Entity Disambiguation Using Graph Neural Networks

Medical knowledge bases (KBs), distilled from biomedical literature and ...
research
10/04/2020

Knowledge-Enhanced Personalized Review Generation with Capsule Graph Neural Network

Personalized review generation (PRG) aims to automatically produce revie...

Please sign up or login with your details

Forgot password? Click here to reset