Hierarchical Summarization for Longform Spoken Dialog

Li, Daniel; Chen, Thomas; Tung, Albert; Chilton, Lydia B.

doi:10.1145/3472749.3474771

Cited by 5 publications

(8 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wikum and Context Trees both explore hierarchical summarization as an approach to crowdsource summarizations of text [70] and help people skim discussions [77]. Li et al use bottom up hierarchical summarization to enable listeners to explore long-form dialog effectively, providing an overview and the ability to navigate to points of interest [43,44]. SceneSkim provides video summaries at three levels of detail (plot summary, script, and captions), helping film professionals in searching and browsing for specific moments within a film [58].…”

Section: Heirarchical Summaries and Descriptionsmentioning

confidence: 99%

“…Prior work has used hierarchical summaries to support searching, browsing, and skimming of long text [70,77], images [33,41,68], audio recordings [43,44], and videos [58,59]. Wikum and Context Trees both explore hierarchical summarization as an approach to crowdsource summarizations of text [70] and help people skim discussions [77].…”

Section: Heirarchical Summaries and Descriptionsmentioning

confidence: 99%

See 1 more Smart Citation

Making Short-Form Videos Accessible with Hierarchical Video Summaries

Van Daele,

Iyer,

Zhang

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

Section: Heirarchical Summaries and Descriptionsmentioning

confidence: 99%

Section: Heirarchical Summaries and Descriptionsmentioning

confidence: 99%

Making Short-Form Videos Accessible with Hierarchical Video Summaries

Van Daele,

Iyer,

Zhang

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…question answering [23,110], and guided reading [34] to support reading medical text [20,69], dialogue [63], news [12],…”

Section: Interactive Reading Interfacesmentioning

confidence: 99%

Paper Plain: Making Medical Research Papers Approachable to Healthcare Consumers with Natural Language Processing

August¹,

Wang²,

Bragg³

et al. 2022

Preprint

View full text Add to dashboard Cite

When seeking information not covered in patient-friendly documents, like medical pamphlets, healthcare consumers may turn to the research literature. Reading medical papers, however, can be a challenging experience. To improve access to medical papers, we introduce a novel interactive interface-Paper Plain 1 -with four features powered by natural language processing: definitions of unfamiliar terms, in-situ plain language section summaries, a collection of key questions that guide readers to answering passages, and plain language summaries of the answering passages. We evaluate Paper Plain, finding that participants who use Paper Plain have an easier time reading and understanding research papers without a loss in paper comprehension compared to those who use a typical PDF reader. Altogether, the study results suggest that guiding readers to relevant passages and providing plain language summaries, or "gists, " alongside the original paper content can make reading medical papers easier and give readers more confidence to approach these papers. CCS Concepts: • Human-centered computing → Empirical studies in interaction design; Interactive systems and tools; User studies.

show abstract

“…Experiments on the AMI Dataset show that the proposed strategy outperformed the state-ofthe-art on both extractive and abstractive models. The performance of summarized utterances and the reduction of occurrence repetition in summaries, were also highlighted in the experimental analyses [21]. Because these studies applied their methods on different corpus, it is not possible to compare them accurately and identify which machine or deep learning algorithm was the best.…”

Section: B Machine Learning and Deep Learning Based Summarization Modelsmentioning

confidence: 99%

“…ROUGE scores (ROUGE-1,ROUGE-2, ROUGE-SU) use n-gram overlap and skip-gram overlap to compare machine summaries to human gold-standard summaries were used in [12] [13]. A BERT Score is used to assess coherence, while the cosine similarity between sentence transformer embedding of a reference ASR segment and a model generated output summary is employed to determine what information is kept in [21]. Fig2.…”

Section: Evaluation Metricsmentioning

confidence: 99%

A Comparative Study for Speech Summarization Based on Machine Learning: A Survey

Altememi¹,

Al-Irhaim²

2022

AL-Rafidain Journal of Computer Sciences and Mathematics

View full text Add to dashboard Cite

The most important aspect of human communication is speech. Lengthy media such as speech takes a long time to read and understand. This difficulty is solved by providing a reduced summary with semantics. Speech summarization can either convert speech to text using automated speech recognition (ASR) and then build the summary, or it can process the speech signal directly and generate the summary. This survey will look at a various of recent studies that have used machine and deep learning algorithms to summarize speech. it discusses the speech summarizing literatures in terms of time restrictions, research methodology, and lack of interest in particular databases for literature searches. As newer deep learning approaches were not included in earlier surveys, this is a new survey in this discipline where different approaches with various datasets were explored for speech summarization and evaluated using subjective or objective methods.

show abstract

Hierarchical Summarization for Longform Spoken Dialog

Cited by 5 publications

References 17 publications

Making Short-Form Videos Accessible with Hierarchical Video Summaries

Making Short-Form Videos Accessible with Hierarchical Video Summaries

Paper Plain: Making Medical Research Papers Approachable to Healthcare Consumers with Natural Language Processing

A Comparative Study for Speech Summarization Based on Machine Learning: A Survey

Contact Info

Product

Resources

About