An Entity-Driven Framework for Abstractive Summarization

Sharma, Eva; Huang, Luyang; Hu, Zhe; Wang, Lu

doi:10.48550/arxiv.1909.02059

Cited by 8 publications

(8 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, although named entities have been extensively studied to convey the semantics of an article (news, scientific, social media) and the saliency of individual sentences [18] within an article, they have not been widely used as part of modeling abstractive summarization. [17] performed entityaware single-document abstractive summarization using reinforcement learning for training. Their pipeline-based approach consists of an entity-aware content selection module and abstract generation module.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Entity-driven Fact-aware Abstractive Summarization of Biomedical Literature

Alambo¹,

Banerjee²,

Thirunarayan³

et al. 2022

Preprint

View full text Add to dashboard Cite

As part of the large number of scientific articles being published every year, the publication rate of biomedical literature has been increasing. Consequently, there has been considerable effort to harness and summarize the massive amount of biomedical research articles. While transformer-based encoderdecoder models in a vanilla source document-to-summary setting have been extensively studied for abstractive summarization in different domains, their major limitations continue to be entity hallucination (a phenomenon where generated summaries constitute entities not related to or present in source article(s)) and factual inconsistency. This problem is exacerbated in a biomedical setting where named entities and their semantics (which can be captured through a knowledge base) constitute the essence of an article. The use of named entities and facts mined from background knowledge bases pertaining to the named entities to guide abstractive summarization has not been studied in biomedical article summarization literature. In this paper, we propose an entity-driven fact-aware framework for training end-to-end transformer-based encoder-decoder models for abstractive summarization of biomedical articles. We call the proposed approach, whose building block is a transformerbased model, EFAS, Entity-driven Fact-aware Abstractive Summarization. We conduct a set of experiments using five state-ofthe-art transformer-based encoder-decoder models (two of which are specifically designed for long document summarization) and demonstrate that injecting knowledge into the training/inference phase of these models enables the models to achieve significantly better performance than the standard source document-tosummary setting in terms of entity-level factual accuracy, N-gram novelty, and semantic equivalence while performing comparably on ROUGE metrics. The proposed approach is evaluated on ICD-11-Summ-1000, a dataset we build for abstractive summarization of biomedical literature, and PubMed-50k, a segment of a large-scale benchmark dataset for abstractive summarization of biomedical literature.

show abstract

Section: Related Workmentioning

confidence: 99%

“…The use of named entities to guide abstractive summarization of news articles has been explored in recent studies by [17]- [20]. However, these studies do not leverage named entitydriven facts from background knowledge bases to guide abstractive summary generation.…”

Section: Introductionmentioning

confidence: 99%

Entity-driven Fact-aware Abstractive Summarization of Biomedical Literature

Alambo¹,

Banerjee²,

Thirunarayan³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Automatic text summarization is a challenging task of condensing the salient information from the source document into a shorter format. Two main categories are typically involved in the text summarization task, one is extractive approach (Cheng and Lapata, 2016;Nallapati et al, 2016a;Xiao and Carenini, 2019;Cui et al, 2020) which directly extracts salient sentences from the input text as the summary, and the other is abstractive approach (Sutskever et al, 2014;See et al, 2017;Cohan et al, 2018;Sharma et al, 2019;Zhao et al, 2020) which imitates human behaviour to produce new sentences based on the extracted information from the source document. Traditional extractive summarization methods are mostly unsupervised, extracting sentences based on n-grams overlap (Nenkova and Vanderwende, 2005), relying on graph-based methods for sentence ranking (Mihalcea and Tarau, 2004;Erkan and Radev, 2004), or identifying important sentences with a latent semantic analysis technique (Steinberger and Jezek, 2004).…”

Section: Introductionmentioning

confidence: 99%

Leveraging Information Bottleneck for Scientific Document Summarization

Ju¹,

Liu²,

Koh³

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper presents an unsupervised extractive approach to summarize scientific long documents based on the Information Bottleneck principle. Inspired by previous work which uses the Information Bottleneck principle for sentence compression, we extend it to document level summarization with two separate steps. In the first step, we use signal(s) as queries to retrieve the key content from the source document. Then, a pre-trained language model conducts further sentence search and edit to return the final extracted summaries. Importantly, our work can be flexibly extended to a multi-view framework by different signals. Automatic evaluation on three scientific document datasets verifies the effectiveness of the proposed framework. The further human evaluation suggests that the extracted summaries cover more content aspects than previous systems.

show abstract

“…The other idea is to use a select and generate framework, where an extractor selects salient sentences, then an abstractor generates a summary. The most recent frameworks based on this hybrid paradigm either follow a two-stage pipeline (Chen and Bansal 2018;Sharma et al 2019) or an end-to-end learning approach (Hsu et al 2018;Shen et al 2019;Gehrmann, Deng, and Rush 2018). The most appealing advantage is to explicitly obtain desirable content of the sources, such as entity-aware selection (Sharma et al 2019) or word selection through latent switch variables (Gehrmann, Deng, and Rush 2018;Shen et al 2019).…”

Section: Introductionmentioning

confidence: 99%

Exploring Explainable Selection to Control Abstractive Summarization

Haonan

Bai

Lapata

et al. 2021

AAAI

View full text Add to dashboard Cite

Like humans, document summarization models can interpret a document’s contents in a number of ways. Unfortunately, the neural models of today are largely black boxes that provide little explanation of how or why they generated a summary in the way they did. Therefore, to begin prying open the black box and to inject a level of control into the substance of the final summary, we developed a novel select-and-generate framework that focuses on explainability. By revealing the latent centrality and interactions between sentences, along with scores for novelty and relevance, users are given a window into the choices a model is making and an opportunity to guide those choices in a more desirable direction. A novel pair-wise matrix captures the sentence interactions, centrality and attribute scores, and a mask with tunable attribute thresholds allows the user to control which sentences are likely to be included in the extraction. A sentence-deployed attention mechanism in the abstractor ensures the final summary emphasizes the desired content. Additionally, the encoder is adaptable, supporting both Transformer- and BERT-based configurations. In a series of experiments assessed with ROUGE metrics and two human evaluations, ESCA outperformed eight state-of-the-art models on the CNN/DailyMail and NYT50 benchmark datasets.

show abstract

An Entity-Driven Framework for Abstractive Summarization

Cited by 8 publications

References 31 publications

Entity-driven Fact-aware Abstractive Summarization of Biomedical Literature

Entity-driven Fact-aware Abstractive Summarization of Biomedical Literature

Leveraging Information Bottleneck for Scientific Document Summarization

Exploring Explainable Selection to Control Abstractive Summarization

Contact Info

Product

Resources

About