Extracting Core Claims from Scientific Articles

Jansen, Tom; Kuhn, Tobias

doi:10.1007/978-3-319-67468-1_3

Cited by 4 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given the lack of robust definitions of science-relatedness, we followed an iterative process of data exploration, literature review and preliminary labeling rounds. We started by selecting and observing samples of science-related texts coming from science-related datasets [7,14,21,[23][24][25]29] and reviewing related definitions together with researchers from various disciplines. We then manually classified them into categories, and held intermediate annotation rounds with new samples to test the agreement across categories.…”

Section: Category Definitions and Annotation Frameworkmentioning

confidence: 99%

“…Methodological research at the intersection of NLP, information retrieval and machine learning is aimed at detecting, classifying or verifying (scientific) claims and discourse [11,18,19,24,25], and is a key facilitator for large-scale interdisciplinary analysis of science discourse. Prior works often focus on actual scholarly publications [14,21], where the formality of language differs substantially from science claims in online news and social media, e.g., Twitter.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

SciTweets -- A Dataset and Annotation Framework for Detecting Scientific Online Discourse

Hafid¹,

Schellhammer²,

Bringay³

et al. 2022

Preprint

View full text Add to dashboard Cite

Scientific topics, claims and resources are increasingly debated as part of online discourse, where prominent examples include discourse related to COVID-19 or climate change. This has led to both significant societal impact and increased interest in scientific online discourse from various disciplines. For instance, communication studies aim at a deeper understanding of biases, quality or spreading pattern of scientific information whereas computational methods have been proposed to extract, classify or verify scientific claims using NLP and IR techniques. However, research across disciplines currently suffers from both a lack of robust definitions of the various forms of science-relatedness as well as appropriate ground truth data for distinguishing them. In this work, we contribute (a) an annotation framework and corresponding definitions for different forms of scientific relatedness of online discourse in Tweets, (b) an expert-annotated dataset of 1261 tweets obtained through our labeling framework reaching an average Fleiss Kappa 𝜅 of 0.63, (c) a multi-label classifier trained on our data able to detect sciencerelatedness with 89% F1 and also able to detect distinct forms of scientific knowledge (claims, references). With this work we aim to lay the foundation for developing and evaluating robust methods for analysing science as part of large-scale online discourse. CCS CONCEPTS• Computing methodologies → Natural language processing; Machine learning; Discourse, dialogue and pragmatics; • Networks → Online social networks.

show abstract

Section: Category Definitions and Annotation Frameworkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

SciTweets -- A Dataset and Annotation Framework for Detecting Scientific Online Discourse

Hafid¹,

Schellhammer²,

Bringay³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In literature rule-based approaches have also been used for claims extraction or classification [6], [7], [8], [9]. De Ribaupierre [7] annotated each sentence of a document and used syntactic rules to identify the discourse type of every sentence.…”

Section: Introductionmentioning

confidence: 99%

“…Risk of annotation noise can increase when there are a large number of rules. Jansen and Kuhn [6] proposed a rule-based approach to help researchers know about recent developments by extracting a core claim from the abstract. They used term frequency (tf) for keyword extraction.…”

Section: Introductionmentioning

confidence: 99%

An Efﬁcient Hybrid Bi-LSTM Attention Model for Claims Extraction from Research Articles through Deep Learning

Asif¹,

Khan²

2022

IJEMD-CSAI

View full text Add to dashboard Cite

The research literature is growing rapidly. A research article contains massive amounts of textual information. Claims are the most significant information in a research article that needs to be retrieved to understand the gist of the research work. A research article contains a number of claims in different sections (abstract, introduction, results, and discussion) of an article. A literature review shows that a few studies of claim extraction have been conducted and they are limited to extracting claims from the abstract section of the article only. In existing studies claims are classified either on the basis of the keywords or all the words. In existing works semantics and context are ignored, and Bag of Words (BoW) representation is used. Deep learning architectures such as Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) have the potential to produce better results through the use of deep learning. Attention mechanism and Bidirectional Long Short-Term Memory (Bi-LSTM) have been used for multiple tasks in Natural Language Processing (NLP) and give effective results. In this work, we propose a hybrid Bi-LSTM attention model. Bi-LSTM model captures the long-term sequences of words and the attention mechanism highlights the important words or keywords in text. A number of experiments have been performed on research articles claim and standard IBM datasets. We verified our proposed model on two datasets for claim/non-claim classification and our model gives 96.7% and 95% on both datasets. The results show that our proposed model through deep learning outperforms existing models.

show abstract

“…In both cases, about 70% of the created AIDA sentences received a perfect quality score. In a follow-up study, we worked on the extraction of AIDA sentences from paper abstracts with a simple rule-based approach [11].…”

Section: Introductionmentioning

confidence: 99%

Using the AIDA Language to Formally Organize Scientific Claims

Kuhn

2018

Preprint

Self Cite

View full text Add to dashboard Cite

Scientific communication still mainly relies on natural language written in scientific papers, which makes the described knowledge very difficult to access with automatic means. We can therefore only make limited use of formal knowledge organization methods to support researchers and other interested parties with features such as automatic aggregations, fact checking, consistency checking, question answering, and powerful semantic search. Existing approaches to solve this problem by improving the scientific communication methods have either very restricted coverage, require formal logic skills on the side of the researchers, or depend on unreliable machine learning for the formalization of knowledge. Here, I propose an approach to this problem that is general, intuitive, and flexible. It is based on a unique kind of controlled natural language, called AIDA, consisting of English sentences that are atomic, independent, declarative, and absolute. Such sentences can then serve as nodes in a network of scientific claims linked to publications, researchers, and domain elements. I present here some small studies on preliminary applications of this language. The results indicate that it is well accepted by users and provides a good basis for the creation of a knowledge graph of scientific findings.

show abstract

Extracting Core Claims from Scientific Articles

Cited by 4 publications

References 16 publications

SciTweets -- A Dataset and Annotation Framework for Detecting Scientific Online Discourse

SciTweets -- A Dataset and Annotation Framework for Detecting Scientific Online Discourse

An Efﬁcient Hybrid Bi-LSTM Attention Model for Claims Extraction from Research Articles through Deep Learning

Using the AIDA Language to Formally Organize Scientific Claims

Contact Info

Product

Resources

About