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

By Luyang huang, Lingfei Wu, Lu Wang. 2020

173 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Survey of Hallucination in Natural Language Generation (2022, methodology): “Examples of the augmented information include entity information [114], extracted relation triples from source document [19, 74] obtained by Fact Description Extraction, pre-executed operation results [136], synthetic data generated through replacement or perturbation [21, 95], retrieved external kn”
GO FIGURE: A Meta Evaluation of Factuality in Summarization (2020, background): “A number of works have highlighted the effectiveness of QA and cloze task objectives for evaluating or improving factuality on speciﬁc domains (Eyal et al., 2019; Huang et al., 2020).”
Text Data Augmentation for Deep Learning (2021, background): “Huang et al. [43] provide another interesting example of constructing a knowledge graph from the long context provided as input to abstractive summarization.”
CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization (2021, background): “Three types of remedies have been proposed: running a separately learned error correction component (Dong et al., 2020), removing noisy training samples (Nan et al., 2021; Goyal and Durrett, 2021), and modifying the Transformer architecture (Huang et al., 2020; Zhu et al., 2021).”
A Survey of Knowledge-enhanced Text Generation (2020, methodology): “In practical,K is usually set asK = 2 [65, 173, 183] orK = 1 [56, 84, 180] (see performance comparisons with different K in Figure 3 of [5]).”