Graph-based Neural Multi-Document Summarization

Yasunaga, Michihiro; Zhang, Rui; Meelu, Kshitijh; Pareek, Ayush; Srinivasan, K.; Radev, Dragomir

doi:10.18653/v1/k17-1045

Cited by 209 publications

(200 citation statements)

References 30 publications

Supporting

Mentioning

200

Contrasting

Order By: Relevance

“…A neural extractive summarizer learns to predict a binary label for each source sentence indicating if it is to be included in the summary. These studies build distributed sentence representations using neural networks (Cheng and Lapata, 2016;Yasunaga et al, 2017) and use reinforcement learning to optimize the evaluation metric (Narayan et al, 2018b) and improve summary coherence (Wu and Hu, 2018). However, sentence extraction can be coarse and in many cases, only a part of the sentence is worthy to be added to the summary.…”

Section: Related Workmentioning

confidence: 99%

Guiding Extractive Summarization with Question-Answering Rewards

Arumae¹,

Liu²

2019

Proceedings of the 2019 Conference of the North

View full text Add to dashboard Cite

Highlighting while reading is a natural behavior for people to track salient content of a document. It would be desirable to teach an extractive summarizer to do the same. However, a major obstacle to the development of a supervised summarizer is the lack of ground-truth. Manual annotation of extraction units is costprohibitive, whereas acquiring labels by automatically aligning human abstracts and source documents can yield inferior results. In this paper we describe a novel framework to guide a supervised, extractive summarization system with question-answering rewards. We argue that quality summaries should serve as a document surrogate to answer important questions, and such question-answer pairs can be conveniently obtained from human abstracts. The system learns to promote summaries that are informative, fluent, and perform competitively on question-answering. Our results compare favorably with those reported by strong summarization baselines as evaluated by automatic metrics and human assessors.

show abstract

Section: Related Workmentioning

confidence: 99%

Guiding Extractive Summarization with Question-Answering Rewards

Arumae¹,

Liu²

2019

Proceedings of the 2019 Conference of the North

View full text Add to dashboard Cite

show abstract

“…All of these models are significantly underperforming compared to SemSentSum. In addition, we include state-ofthe-art models : RegSum (Hong and Nenkova, 2014) and GCN+PADG (Yasunaga et al, 2017). We outperform both in terms of ROUGE-1.…”

Section: Summarization Performancementioning

confidence: 99%

“…More specifically, extractive summarization systems output summaries in two steps : via sentence ranking, where an importance score is assigned to each sentence, and via the subsequent sentence selection, where the most appropriate sentence is chosen, by considering 1) their importance and 2) their frequency among all documents. Due to data sparcity, models heavily rely on well-designed features at the word level (Hong and Nenkova, 2014;Cao et al, 2015;Christensen et al, 2013;Yasunaga et al, 2017) or take advantage of other large, manually annotated datasets and then apply transfer learning (Cao et al, 2017). Additionally, most of the time, all sentences in the same collection of documents are processed independently and therefore, their relationships are lost.…”

Section: Introductionmentioning

confidence: 99%

Learning to Create Sentence Semantic Relation Graphs for Multi-Document Summarization

Antognini¹,

Faltings²

2019

Proceedings of the 2nd Workshop on New Frontiers in Summarization

View full text Add to dashboard Cite

Linking facts across documents is a challenging task, as the language used to express the same information in a sentence can vary significantly, which complicates the task of multidocument summarization. Consequently, existing approaches heavily rely on hand-crafted features, which are domain-dependent and hard to craft, or additional annotated data, which is costly to gather. To overcome these limitations, we present a novel method, which makes use of two types of sentence embeddings : universal embeddings, which are trained on a large unrelated corpus, and domainspecific embeddings, which are learned during training. To this end, we develop Sem-SentSum, a fully data-driven model able to leverage both types of sentence embeddings by building a sentence semantic relation graph. SemSentSum achieves competitive results on two types of summary, consisting of 665 bytes and 100 words. Unlike other state-of-the-art models, neither hand-crafted features nor additional annotated data are necessary, and the method is easily adaptable for other tasks. To our knowledge, we are the first to use multiple sentence embeddings for the task of multidocument summarization.

show abstract

“…For extractive methods, Nallapati et al [22] use recurrent neural networks (RNNs) to read the article and get the representations of the sentences and select important sentences. Yasunaga et al [23] combine RNNs with graph convolutional networks (CNNs) to compute the salience of each sentence. Narayan et al [24] propose a framework composed of a hierarchical encoder based on CNNs and an attention-based extractor with attention over external information.…”

Section: Related Workmentioning

confidence: 99%

Learning Syntactic and Dynamic Selective Encoding for Document Summarization

Xu¹,

He²,

Han³

et al. 2019

2019 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Text summarization aims to generate a headline or a short summary consisting of the major information of the source text. Recent studies employ the sequence-to-sequence framework to encode the input with a neural network and generate abstractive summary. However, most studies feed the encoder with the semantic word embedding but ignore the syntactic information of the text. Further, although previous studies proposed the selective gate to control the information flow from the encoder to the decoder, it is static during the decoding and cannot differentiate the information based on the decoder states. In this paper, we propose a novel neural architecture for document summarization. Our approach has the following contributions: first, we incorporate syntactic information such as constituency parsing trees into the encoding sequence to learn both the semantic and syntactic information from the document, resulting in more accurate summary; second, we propose a dynamic gate network to select the salient information based on the context of the decoder state, which is essential to document summarization. The proposed model has been evaluated on CNN/Daily Mail summarization datasets and the experimental results show that the proposed approach outperforms baseline approaches.

show abstract

Graph-based Neural Multi-Document Summarization

Cited by 209 publications

References 30 publications

Guiding Extractive Summarization with Question-Answering Rewards

Guiding Extractive Summarization with Question-Answering Rewards

Learning to Create Sentence Semantic Relation Graphs for Multi-Document Summarization

Learning Syntactic and Dynamic Selective Encoding for Document Summarization

Contact Info

Product

Resources

About