GraphDocExplore: A Framework for the Experimental Comparison of
            Graph-based Document Exploration Techniques

Falke, Tobias; Gurevych, Iryna

doi:10.18653/v1/d17-2004

Cited by 10 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To create concept maps, Novak and Cañas [15] outlined a general process that starts with constructing a main focus question of the concept map, identifying the key concepts applying to the related domain for which "usually 15 to 25 concepts will suffice", then constructing a preliminary concept map by placing concepts around, and finally adding links between concepts to help illustrate how concepts are related to one another. This process can be time consuming, and other works, such the work of Falke and Gurevych [9], propose a method to automatically extract concept maps for document summarization, allowing for document collections to be more easily explored.…”

Section: Concept Mapsmentioning

confidence: 99%

Paper Maps: Improving the Readability of Scientific Papers via Concept Maps

Amabili¹,

Sultanum²

2021

Preprint

View full text Add to dashboard Cite

Given the wealth of scientific publications, perusing papers is becoming a larger and more complex burden, especially for junior researchers. In this work, we suggest a visualization-based method to mitigate this problem via the use of paper maps, i.e., concept maps for the summarization of scientific papers. We provide design principles of paper maps and discuss design considerations based on exploratory design studies. We also conducted an initial evaluation for assessing the effectiveness of paper maps in summarizing scientific papers, suggesting that paper maps can improve the readability of scientific papers.

show abstract

Section: Concept Mapsmentioning

confidence: 99%

Paper Maps: Improving the Readability of Scientific Papers via Concept Maps

Amabili¹,

Sultanum²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…While the before-mentioned interactive exploration systems target mainly structured data, there are currently not many systems apart from [6] and [5] that allow data scientists of varying skill levels and novice users to interactively explore unstructured text document collections. Most of the existing interactive text exploration systems, however, only allow users to apply classical keyword searches [6] and rank the documents according to static metrics (e.g., frequency [1] or centrality [15]).…”

Section: Figure 1: Scalability Of Text Summarization Modelsmentioning

confidence: 99%

Sherlock

et al. 2018

View full text Add to dashboard Cite

There exists an ever-growing set of data-centric systems that allow data scientists of varying skill levels to interactively manipulate, analyze and explore large structured data sets. However, there are currently not many systems that allow data scientists and novice users to interactively explore large unstructured text document collections from heterogeneous sources. In this demo paper, we present a new system for interactive text summarization called Sherlock. The task of automatically producing textual summaries is an important step to understand a collection of multiple topic-related documents. It has many real-world applications in journalism, medicine, and many more. However, none of the existing summarization systems allow users to provide feedback at interactive speed. We therefore integrate a new approximate summarization model into Sherlock that can guarantee interactive speeds even for large text collections to keep the user engaged in the process.

show abstract

“…However, in many use cases the relevant data sources are not structured but are only present as a collection of texts. There already exist systems for text exploration like [3] and [2] that allow data scientists of varying skill levels and novice users to interactively analyze unstructured text document collectionshowever, those systems concentrate mainly on keyword searches and document ranking.…”

Section: Introductionmentioning

confidence: 99%

Interactive Summarization of Large Document Collections

Hättasch

Meyer

Binnig

2019

Proceedings of the Workshop on Human-in-the-Loop Data Analytics

View full text Add to dashboard Cite

We present a new system for custom summarizations of large text corpora at interactive speed. The task of producing textual summaries is an important step to understand large collections of topicrelated documents and has many real-world applications in journalism, medicine, and many more. Key to our system is that the summarization model is refined by user feedback and called multiple times to improve the quality of the summaries iteratively. To that end, the human is brought into the loop to gather feedback in every iteration about which aspects of the intermediate summaries satisfy their individual information needs. Our system consists of a sampling component and a learned model to produce a textual summary. As we show in our evaluation, our system can provide a similar quality level as existing summarization models that are working on the full corpus and hence cannot provide interactive speeds.

show abstract

GraphDocExplore: A Framework for the Experimental Comparison of Graph-based Document Exploration Techniques

Abstract: Graphs have long been proposed as a tool to browse and navigate in a collection of documents in order to support exploratory search.

Cited by 10 publications

References 15 publications

Paper Maps: Improving the Readability of Scientific Papers via Concept Maps

Paper Maps: Improving the Readability of Scientific Papers via Concept Maps

Sherlock

Interactive Summarization of Large Document Collections

Contact Info

Product

Resources

About