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

Antognini, Diego; Faltings, Boi

doi:10.18653/v1/d19-5404

Cited by 18 publications

(10 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LexRank) [8], our model performed better in the Rouge score. The state-of-the-art graph-based approach SemSentSum [34] is a fully datadriven model that uses cross-entropy as the objective function. As expected, it outperformed other traditional baselines in Rouge-2 and Rouge-L, but our model still performed better.…”

Section: E Qualitative Resultsmentioning

confidence: 99%

“…Previous works [34] [13] use cross-entropy loss for training. When we trained our model with cross-entropy, the loss tends to output scores close to 0 or 1 which may cause an obstacle for ranking.…”

Section: ) Trainingmentioning

confidence: 99%

“…Similarity TextRank [7] 0.7498±0.0577 Cont. LexRank [8] 0.7322±0.0586 MMR [46] 0.7517±0.0568 SemSentSum [34] 0.7502±0.0565 Ours(extractor) 0.7533±0.0571…”

Section: Modelmentioning

confidence: 99%

See 2 more Smart Citations

Template-Based Headline Generator for Multiple Documents

et al. 2022

View full text Add to dashboard Cite

In this paper, we develop a neural multi-document summarization model, named MuD2H (refers to Multi-Document to Headline) to generate an attractive and customized headline from a set of product descriptions. To the best of our knowledge, no one has used a technique for multi-document summarization to generate headlines in the past. Therefore, multi-document headline generation can be considered new problem setting. Our model implements a two-stage architecture, including an extractive stage and an abstractive stage. The extractive stage is a graph-based model that identified salient sentences, whereas the abstractive stage uses existing summaries as soft templates to guild the seq2seq model. A series of experiments are conducted by using KKday dataset. Experimental results show that the proposed method outperforms the others in terms of quantitative and qualitative aspects.

show abstract

Section: E Qualitative Resultsmentioning

confidence: 99%

Section: ) Trainingmentioning

confidence: 99%

See 1 more Smart Citation

Template-Based Headline Generator for Multiple Documents

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Hierarchical solutions. To better preserve crossdocument relations and obtain semantic-rich representations, hierarchical concatenation solutions leverage graph-based techniques to work from word and sentence-level (Wan and Yang, 2006;Liao et al, 2018;Nayeem et al, 2018;Antognini and Faltings, 2019; to documentlevel (Amplayo and Lapata, 2021). Other hierarchical approaches include multi-head pooling and inter-paragraph attention architectures (Liu and Lapata, 2019a), attention models with maximal marginal relevance (Fabbri et al, 2019), and attention across different granularity representations (Jin et al, 2020).…”

Section: Related Workmentioning

confidence: 99%

Discriminative Marginalized Probabilistic Neural Method for Multi-Document Summarization of Medical Literature

Moro¹,

Ragazzi²,

Valgimigli³

et al. 2022

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

Although current state-of-the-art Transformerbased solutions succeeded in a wide range for single-document NLP tasks, they still struggle to address multi-input tasks such as multidocument summarization. Many solutions truncate the inputs, thus ignoring potential summary-relevant contents, which is unacceptable in the medical domain where each information can be vital. Others leverage linear model approximations to apply multi-input concatenation, worsening the results because all information is considered, even if it is conflicting or noisy with respect to a shared background. Despite the importance and social impact of medicine, there are no ad-hoc solutions for multi-document summarization. For this reason, we propose a novel discriminative marginalized probabilistic method (DAMEN) trained to discriminate critical information from a cluster of topic-related medical documents and generate a multi-document summary via token probability marginalization. Results prove we outperform the previous state-of-theart on a biomedical dataset for multi-document summarization of systematic literature reviews. Moreover, we perform extensive ablation studies to motivate the design choices and prove the importance of each module of our method. 1

show abstract

“…Goo and Chen (2018) Graph-to-Sequence Generation Recent research efforts for text generation consider utilizing Graph Neural Networks (GNN) to better model structured data, such as AMR (Beck et al, 2018;Ribeiro et al, 2019), SQL (Xu et al, 2018), and knowledge graph (Koncel-Kedziorski et al, 2019). Additionally, there are many works employed GNN in non-structural scenarios, such as summarization (Yasunaga et al, 2017;Fernandes et al, 2018;Antognini and Faltings, 2019) and comment generation (Li et al, 2019b), by transforming the input into a meaningful graph. We propose the discourse graph to facilitate information flow over the graph.…”

Section: Related Workmentioning

confidence: 99%

Dialogue Discourse-Aware Graph Model and Data Augmentation for Meeting Summarization

Feng

Qin

et al. 2020

Preprint

View full text Add to dashboard Cite

Sequence-to-sequence methods have achieved promising results for textual abstractive meeting summarization. Different from documents like news and scientific papers, a meeting is naturally full of dialogue-specific structural information. However, previous works model a meeting in a sequential manner, while ignoring the rich structural information. In this paper, we develop a Dialogue Discourse-Aware Graph Convolutional Networks (DDA-GCN) for meeting summarization by utilizing dialogue discourse, which is a dialogue-specific structure that can provide pre-defined semantic relationships between each utterance. We first transform the entire meeting text with dialogue discourse relations into a discourse graph and then use DDA-GCN to encode the semantic representation of the graph. Finally, we employ a Recurrent Neural Network to generate the summary. In addition, we utilize the question-answer discourse relation to construct a pseudo-summarization corpus, which can be used to pre-train our model. Experimental results on the AMI dataset show that our model outperforms various baselines and can achieve state-of-the-art performance.

show abstract

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

Cited by 18 publications

References 30 publications

Template-Based Headline Generator for Multiple Documents

Template-Based Headline Generator for Multiple Documents

Discriminative Marginalized Probabilistic Neural Method for Multi-Document Summarization of Medical Literature

Dialogue Discourse-Aware Graph Model and Data Augmentation for Meeting Summarization

Contact Info

Product

Resources

About