Summary Explorer: Visualizing the State of the Art in Text Summarization
- URL: http://arxiv.org/abs/2108.01879v1
- Date: Wed, 4 Aug 2021 07:11:19 GMT
- Title: Summary Explorer: Visualizing the State of the Art in Text Summarization
- Authors: Shahbaz Syed, Tariq Yousef, Khalid Al-Khatib, Stefan J\"anicke, Martin
Potthast
- Abstract summary: This paper introduces Summary Explorer, a new tool to support the manual inspection of text summarization systems.
The underlying design of the tool considers three well-known summary quality criteria (coverage, faithfulness, and position bias) encapsulated in a guided assessment based on tailored visualizations.
- Score: 23.45323725326221
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: This paper introduces Summary Explorer, a new tool to support the manual
inspection of text summarization systems by compiling the outputs of
55~state-of-the-art single document summarization approaches on three benchmark
datasets, and visually exploring them during a qualitative assessment. The
underlying design of the tool considers three well-known summary quality
criteria (coverage, faithfulness, and position bias), encapsulated in a guided
assessment based on tailored visualizations. The tool complements existing
approaches for locally debugging summarization models and improves upon them.
The tool is available at https://tldr.webis.de/
Related papers
- RTSUM: Relation Triple-based Interpretable Summarization with Multi-level Salience Visualization [12.890135367392524]
We present RTSUM, an unsupervised summarization framework that utilizes relation triples as the basic unit for summarization.
We also develop a web demo for an interpretable summarizing tool, providing fine-grained interpretations with the output summary.
arXiv Detail & Related papers (2023-10-21T02:46:03Z) - Summary Workbench: Unifying Application and Evaluation of Text
Summarization Models [24.40171915438056]
New models and evaluation measures can be easily integrated as Docker-based plugins.
Visual analyses combining multiple measures provide insights into the models' strengths and weaknesses.
arXiv Detail & Related papers (2022-10-18T04:47:25Z) - CNewSum: A Large-scale Chinese News Summarization Dataset with
Human-annotated Adequacy and Deducibility Level [15.969302324314516]
We present a large-scale Chinese news summarization dataset CNewSum.
It consists of 304,307 documents and human-written summaries for the news feed.
Its test set contains adequacy and deducibility annotations for the summaries.
arXiv Detail & Related papers (2021-10-21T03:37:46Z) - iFacetSum: Coreference-based Interactive Faceted Summarization for
Multi-Document Exploration [63.272359227081836]
iFacetSum integrates interactive summarization together with faceted search.
Fine-grained facets are automatically produced based on cross-document coreference pipelines.
arXiv Detail & Related papers (2021-09-23T20:01:11Z) - Aspect-Controllable Opinion Summarization [58.5308638148329]
We propose an approach that allows the generation of customized summaries based on aspect queries.
Using a review corpus, we create a synthetic training dataset of (review, summary) pairs enriched with aspect controllers.
We fine-tune a pretrained model using our synthetic dataset and generate aspect-specific summaries by modifying the aspect controllers.
arXiv Detail & Related papers (2021-09-07T16:09:17Z) - SummVis: Interactive Visual Analysis of Models, Data, and Evaluation for
Text Summarization [14.787106201073154]
SummVis is an open-source tool for visualizing abstractive summaries.
It enables fine-grained analysis of the models, data, and evaluation metrics associated with text summarization.
arXiv Detail & Related papers (2021-04-15T17:13:00Z) - Unsupervised Opinion Summarization with Content Planning [58.5308638148329]
We show that explicitly incorporating content planning in a summarization model yields output of higher quality.
We also create synthetic datasets which are more natural, resembling real world document-summary pairs.
Our approach outperforms competitive models in generating informative, coherent, and fluent summaries.
arXiv Detail & Related papers (2020-12-14T18:41:58Z) - Topic-Guided Abstractive Text Summarization: a Joint Learning Approach [19.623946402970933]
We introduce a new approach for abstractive text summarization, Topic-Guided Abstractive Summarization.
The idea is to incorporate neural topic modeling with a Transformer-based sequence-to-sequence (seq2seq) model in a joint learning framework.
arXiv Detail & Related papers (2020-10-20T14:45:25Z) - Summarizing Text on Any Aspects: A Knowledge-Informed Weakly-Supervised
Approach [89.56158561087209]
We study summarizing on arbitrary aspects relevant to the document.
Due to the lack of supervision data, we develop a new weak supervision construction method and an aspect modeling scheme.
Experiments show our approach achieves performance boosts on summarizing both real and synthetic documents.
arXiv Detail & Related papers (2020-10-14T03:20:46Z) - Summary-Source Proposition-level Alignment: Task, Datasets and
Supervised Baseline [94.0601799665342]
Aligning sentences in a reference summary with their counterparts in source documents was shown as a useful auxiliary summarization task.
We propose establishing summary-source alignment as an explicit task, while introducing two major novelties.
We create a novel training dataset for proposition-level alignment, derived automatically from available summarization evaluation data.
We present a supervised proposition alignment baseline model, showing improved alignment-quality over the unsupervised approach.
arXiv Detail & Related papers (2020-09-01T17:27:12Z) - Few-Shot Learning for Opinion Summarization [117.70510762845338]
Opinion summarization is the automatic creation of text reflecting subjective information expressed in multiple documents.
In this work, we show that even a handful of summaries is sufficient to bootstrap generation of the summary text.
Our approach substantially outperforms previous extractive and abstractive methods in automatic and human evaluation.
arXiv Detail & Related papers (2020-04-30T15:37:38Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.