Neural Latent Extractive Document Summarization

By Xingxing Zhang, Mirella Lapata, Furu Wei, M. Zhou. 2018

169 citations recorded by the source corpus.

Extractive summarization models need sentence level labels, which are usually created with rule-based methods since most summarization datasets only have document summary pairs. These labels might be suboptimal. We propose a latent variable extractive model, where sentences are viewed as latent variables and sentences with activated variables are used to infer gold summaries. During training, the loss can come directly from gold summaries. Experiments on CNN/Dailymail dataset show our latent extractive model outperforms a strong extractive baseline trained on rule-based labels and also performs competitively with several recent models.

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

Fine-tune BERT for Extractive Summarization (2019, background): “…have been proposed for extractive summarization recently (Cheng and Lapata, 2016; Nallapati et al., 2017; Narayan et al., 2018; Dong et al., 2018; Zhang et al., 2018; Zhou et al., 2018), the improvement on automatic metrics like ROUGE has reached a bottleneck due to the complexity of the task.”
Better Rewards Yield Better Summaries: Learning to Summarise Without References (2019, neutral): “(Zhang et al., 2018) NA 41.”
Text Summarization with Pretrained Encoders (2019, background): “It is worth noting that our decoder applies neither a copy nor a coverage mechanism (See et al., 2017 (Nallapati et al., 2017) 39.60 16.20 35.30 R EFRESH (Narayan et al., 2018b) 40.00 18.20 36.60 L ATENT (Zhang et al., 2018) 41.05 18.77 37.54 N EU S UM (Zhou et al., 2018) 41.59 19.01 37.98 S UMO (Li”
HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization (2019, methodology): “The architecture is widely adopted in recent neural ex-tractive models and is extended with reinforcement learning (Narayan et al., 2018; Dong et al., 2018), latent variable models (Zhang et al., 2018), joint scoring (Zhou et al., 2018) and iterative document representation (Chen et al., 2018).”
GUIR @ LongSumm 2020: Learning to Generate Long Summaries from Scientific Documents (2020, methodology): “…where the system ﬁnds the salient sentences within the source 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,…”
Heterogeneous Graph Neural Networks for Extractive Document Summarization (2020, unknown): “60 LATENT (Zhang et al., 2018) 41.”
Learning by Semantic Similarity Makes Abstractive Summarization Better (2020, methodology): “Extractive summarization is a method of creating summaries by extracting important parts from the document (Zhang et al., 2018; Narayan et al., 2018; Liu and Lapata, 2019), whereas abstractive summarization is more like generating sentences using salient information from the document (See et al.”
Re-evaluating Evaluation in Text Summarization (2020, unknown): “We use CNN-LSTM-BiClassiﬁer (CLSTM-SL; Kedzie et al. (2018)), Latent (Zhang et al., 2018), Ban-ditSum (Dong et al., 2018), REFRESH (Narayan et al., 2018), NeuSum (Zhou et al., 2018), HIBERT (Zhang et al., 2019b), Bert-Sum-Ext (Liu and Lapata, 2019a), CNN-Transformer-BiClassiﬁer (CTrans-SL; Zhong et…”
Discourse-Aware Neural Extractive Text Summarization (2019, methodology): “Recently, some hybrid methods have been proposed to take advantage of both, by designing a two-stage pipeline to first select and then rewrite (or compress) candidate sentences (Chen and Bansal, 2018; Gehrmann et al., 2018; Zhang et al., 2018; Xu and Durrett, 2019).”
How to Compare Summarizers without Target Length? Pitfalls, Solutions and Re-Examination of the Neural Summarization Literature (2019, background): “(3) Neural latent extractive model ( latent ext ) and the same model with compression over the extracted sentences ( latent cmpr ) (Zhang et al., 2018).”
SummEval: Re-evaluating Summarization Evaluation (2020, background): “M3 - LATENT (Zhang et al., 2018b) propose a latent variable extractive model which views relevance labels of sentences in a document as binarylatent variables M4 - REFRESH (Narayan et al., 2018) propose using REINFORCE (Williams, 1992) to extract summaries, approximating the search space during trai”