Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward

05/03/2020
by   Luyang Huang, et al.
0

Sequence-to-sequence models for abstractive summarization have been studied extensively, yet the generated summaries commonly suffer from fabricated content, and are often found to be near-extractive. We argue that, to address these issues, the summarizer should acquire semantic interpretation over input, e.g., via structured representation, to allow the generation of more informative summaries. In this paper, we present ASGARD, a novel framework for Abstractive Summarization with Graph-Augmentation and semantic-driven RewarD. We propose the use of dual encoders—a sequential document encoder and a graph-structured encoder—to maintain the global context and local characteristics of entities, complementing each other. We further design a reward based on a multiple choice cloze test to drive the model to better capture entity interactions. Results show that our models produce significantly higher ROUGE scores than a variant without knowledge graph as input on both New York Times and CNN/Daily Mail datasets. We also obtain better or comparable performance compared to systems that are fine-tuned from large pretrained language models. Human judges further rate our model outputs as more informative and containing fewer unfaithful errors.

READ FULL TEXT
research
09/04/2019

An Entity-Driven Framework for Abstractive Summarization

Abstractive summarization systems aim to produce more coherent and conci...
research
10/14/2018

Robust Neural Abstractive Summarization Systems and Evaluation against Adversarial Information

Sequence-to-sequence (seq2seq) neural models have been actively investig...
research
04/05/2021

Efficient Attentions for Long Document Summarization

The quadratic computational and memory complexities of large Transformer...
research
09/22/2021

Enriching and Controlling Global Semantics for Text Summarization

Recently, Transformer-based models have been proven effective in the abs...
research
09/13/2021

Augmented Abstractive Summarization With Document-LevelSemantic Graph

Previous abstractive methods apply sequence-to-sequence structures to ge...
research
06/27/2020

Mind The Facts: Knowledge-Boosted Coherent Abstractive Text Summarization

Neural models have become successful at producing abstractive summaries ...
research
03/30/2022

Entity-driven Fact-aware Abstractive Summarization of Biomedical Literature

As part of the large number of scientific articles being published every...

Please sign up or login with your details

Forgot password? Click here to reset