Citance-Contextualized Summarization of Scientific Papers
- URL: http://arxiv.org/abs/2311.02408v3
- Date: Mon, 13 Nov 2023 08:40:04 GMT
- Title: Citance-Contextualized Summarization of Scientific Papers
- Authors: Shahbaz Syed, Ahmad Dawar Hakimi, Khalid Al-Khatib, Martin Potthast
- Abstract summary: Abstracts are not intended to show the relationship between a paper and the references cited in it.
We propose a new contextualized summarization approach that can generate an informative summary conditioned on a given sentence containing the citation of a reference.
- Score: 33.85387549129378
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Current approaches to automatic summarization of scientific papers generate
informative summaries in the form of abstracts. However, abstracts are not
intended to show the relationship between a paper and the references cited in
it. We propose a new contextualized summarization approach that can generate an
informative summary conditioned on a given sentence containing the citation of
a reference (a so-called "citance"). This summary outlines the content of the
cited paper relevant to the citation location. Thus, our approach extracts and
models the citances of a paper, retrieves relevant passages from cited papers,
and generates abstractive summaries tailored to each citance. We evaluate our
approach using $\textbf{Webis-Context-SciSumm-2023}$, a new dataset containing
540K~computer science papers and 4.6M~citances therein.
Related papers
- Cleaning English Abstracts of Scientific Publications [0.15293427903448018]
We introduce an open-source, easy-to-integrate language model designed to clean English-language scientific abstracts.<n>We demonstrate that our model is both conservative and precise, alters similarity rankings of cleaned abstracts and improves information content of standard-length embeddings.
arXiv Detail & Related papers (2025-12-30T20:45:50Z) - AugAbEx : Way Forward for Extractive Case Summarization [4.0360727591181]
We aim to augment seven existing case summarization datasets, which include abstractive summaries, by incorporating corresponding extractive summaries.<n>We commit to release the augmented datasets in the public domain for use by the research community.
arXiv Detail & Related papers (2025-11-15T16:49:42Z) - Event-based evaluation of abstractive news summarization [8.25219440625445]
We evaluate the quality of abstractive summaries by calculating overlapping events between generated summaries, reference summaries, and the original news articles.<n>Our approach provides more insight into the event information contained in the summaries.
arXiv Detail & Related papers (2025-07-01T19:49:23Z) - QuOTeS: Query-Oriented Technical Summarization [0.2936007114555107]
We propose QuOTeS, an interactive system designed to retrieve sentences related to a summary of the research from a collection of potential references.
QuOTeS integrates techniques from Query-Focused Extractive Summarization and High-Recall Information Retrieval to provide Interactive Query-Focused Summarization of scientific documents.
The results show that QuOTeS provides a positive user experience and consistently provides query-focused summaries that are relevant, concise, and complete.
arXiv Detail & Related papers (2023-06-20T18:43:24Z) - A comprehensive review of automatic text summarization techniques:
method, data, evaluation and coding [1.9241821314180376]
We provide a literature review about Automatic Text Summarization (ATS) systems.
We consider a citation-based approach and present the diverse approaches to ATS guided by the mechanisms they use to generate a summary.
We also present an extensive review of the datasets available for summarization tasks and the methods used to evaluate the quality of the summaries.
arXiv Detail & Related papers (2023-01-04T19:20:18Z) - Salience Allocation as Guidance for Abstractive Summarization [61.31826412150143]
We propose a novel summarization approach with a flexible and reliable salience guidance, namely SEASON (SaliencE Allocation as Guidance for Abstractive SummarizatiON)
SEASON utilizes the allocation of salience expectation to guide abstractive summarization and adapts well to articles in different abstractiveness.
arXiv Detail & Related papers (2022-10-22T02:13:44Z) - A Survey on Neural Abstractive Summarization Methods and Factual
Consistency of Summarization [18.763290930749235]
summarization is the process of shortening a set of textual data computationally, to create a subset (a summary)
Existing summarization methods can be roughly divided into two types: extractive and abstractive.
An extractive summarizer explicitly selects text snippets from the source document, while an abstractive summarizer generates novel text snippets to convey the most salient concepts prevalent in the source.
arXiv Detail & Related papers (2022-04-20T14:56:36Z) - Topic-Guided Abstractive Multi-Document Summarization [21.856615677793243]
A critical point of multi-document summarization (MDS) is to learn the relations among various documents.
We propose a novel abstractive MDS model, in which we represent multiple documents as a heterogeneous graph.
We employ a neural topic model to jointly discover latent topics that can act as cross-document semantic units.
arXiv Detail & Related papers (2021-10-21T15:32:30Z) - ConvoSumm: Conversation Summarization Benchmark and Improved Abstractive
Summarization with Argument Mining [61.82562838486632]
We crowdsource four new datasets on diverse online conversation forms of news comments, discussion forums, community question answering forums, and email threads.
We benchmark state-of-the-art models on our datasets and analyze characteristics associated with the data.
arXiv Detail & Related papers (2021-06-01T22:17:13Z) - Enhancing Scientific Papers Summarization with Citation Graph [78.65955304229863]
We redefine the task of scientific papers summarization by utilizing their citation graph.
We construct a novel scientific papers summarization dataset Semantic Scholar Network (SSN) which contains 141K research papers in different domains.
Our model can achieve competitive performance when compared with the pretrained models.
arXiv Detail & Related papers (2021-04-07T11:13:35Z) - What's New? Summarizing Contributions in Scientific Literature [85.95906677964815]
We introduce a new task of disentangled paper summarization, which seeks to generate separate summaries for the paper contributions and the context of the work.
We extend the S2ORC corpus of academic articles by adding disentangled "contribution" and "context" reference labels.
We propose a comprehensive automatic evaluation protocol which reports the relevance, novelty, and disentanglement of generated outputs.
arXiv Detail & Related papers (2020-11-06T02:23:01Z) - Topic-Centric Unsupervised Multi-Document Summarization of Scientific
and News Articles [3.0504782036247438]
We propose a topic-centric unsupervised multi-document summarization framework to generate abstractive summaries.
The proposed algorithm generates an abstractive summary by developing salient language unit selection and text generation techniques.
Our approach matches the state-of-the-art when evaluated on automated extractive evaluation metrics and performs better for abstractive summarization on five human evaluation metrics.
arXiv Detail & Related papers (2020-11-03T04:04:21Z) - From Standard Summarization to New Tasks and Beyond: Summarization with
Manifold Information [77.89755281215079]
Text summarization is the research area aiming at creating a short and condensed version of the original document.
In real-world applications, most of the data is not in a plain text format.
This paper focuses on the survey of these new summarization tasks and approaches in the real-world application.
arXiv Detail & Related papers (2020-05-10T14:59:36Z)
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.