Discourse-Aware Neural Extractive Text Summarization

By Jiacheng Xu, Zhe Gan, Yu Cheng, Jingjing Liu. Annual Meeting of the Association for Computational Linguistics, 2019

302 citations recorded by the source corpus.

Recently BERT has been adopted for document encoding in state-of-the-art text summarization models. However, sentence-based extractive models often result in redundant or uninformative phrases in the extracted summaries. Also, long-range dependencies throughout a document are not well captured by BERT, which is pre-trained on sentence pairs instead of documents. To address these issues, we present a discourse-aware neural summarization model - DiscoBert. DiscoBert extracts sub-sentential discourse units (instead of sentences) as candidates for extractive selection on a finer granularity. To capture the long-range dependencies among discourse units, structural discourse graphs are constructed based on RST trees and coreference mentions, encoded with Graph Convolutional Networks. Experiments show that the proposed model outperforms state-of-the-art methods by a significant margin on popular summarization benchmarks compared to other BERT-base models.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/76037594f29a663fbd2799de2e5c7463c02a8a1d

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

Citations in the corpus

GUIR @ LongSumm 2020: Learning to Generate Long Summaries from Scientific Documents (2020, methodology): “…and concate-nates them to form the summary (Zhou et al., 2018; Dong et al., 2018; Zhang et al., 2018; Narayan et al., 2018; Liu and Lapata, 2019; Xu et al., 2020); and 2) Abstractive: where the model conducts text generation, paraphrasing, and produces novel words that are not necessarily…”
DAGN: Discourse-Aware Graph Network for Logical Reasoning (2021, methodology): “…of texts and hence is beneﬁcial for many of the natural language tasks, for instance, text summarization (Cohan et al., 2018; Joty et al., 2019; Xu et al., 2020a; Feng et al., 2020), neural machine translation (Voita et al., 2018), and coherent text generation (Wang et al., 2020; Bosselut et…”
DialogSum: A Real-Life Scenario Dialogue Summarization Dataset (2021, background): “Model-generated summaries have the Discourse Relation Reasonable summaries should convey important relations between main events, and identifying discourse relations and using proper phrases to express them in summaries can be challenging for summarization systems (Xu et al., 2020).”
On Generating Extended Summaries of Long Documents (2020, background): “In the past few years, there has been a significant progress on both extractive (e.g., Nallapati, Zhai, and Zhou 2017; Zhou et al. 2018; Liu and Lapata 2019; Xu et al. 2020; Jia et al. 2020) and abstractive (e.”