• Corpus ID: 5221181

Scientific Argumentation Detection as Limited-domain Intention Recognition

  title={Scientific Argumentation Detection as Limited-domain Intention Recognition},
  author={Simone Teufel},
We describe the task of intention-based text understanding for scientific argumentation. The model of scientific argumentation presented here is based on the recognition of 28 concrete rhetorical moves in text. These moves can in turn be associated with higherlevel intentions. The intentions we aim to model operate in the limited domain of scientific argumentation and justification; it is the limitation of the domain which makes our intentions predictable and enumerable, unlike general… 

Figures from this paper

Extraction of Cognitive Operations from Scientific Texts

  • D. Devyatkin
  • Computer Science
    Communications in Computer and Information Science
  • 2019
This paper presents a new approach that does not model a text as a result of a researcher's cognitive activity embodied in it, but it models cognitive activity reflected in the scientific text, and proposes and evaluates a framework for detection of text fragments, which is related to cognitive operations in scientific texts.

A News Editorial Corpus for Mining Argumentation Strategies

A novel corpus with 300 editorials from three diverse news portals that provides the basis for mining argumentation strategies and reveals different strategies across the news portals, exemplifying the benefit of studying editorials—a so far underresourced text genre in argument mining.

Sentiment Flow - A General Model of Web Review Argumentation

The hypothesis is that people express their global sentiment on a topic with similar sequences of local sentiment independent of the domain, and model such sentiment flow robustly under uncertainty through abstraction.

Annotation of Rhetorical Moves in Biochemistry Articles

A detailed study with human annotators is conducted to confirm that the selection of semantic roles is effective in determining the underlying rhetorical structure of existing biomedical articles in an extensive dataset.

Argument Mining for Scholarly Document Processing: Taking Stock and Looking Ahead

Argument mining targets structures in natural language related to interpretation and persuasion which are central to scientific communication. Most scholarly discourse involves interpreting

Use of Claim Graphing and Argumentation Schemes in Biomedical Literature: A Manual Approach to Analysis

An investigation of the large scale argumentation structure found when examining five biochemistry journal publications suggests that argumentation schemes originally designed for genetic research articles may transfer to experimental biomedical literature in general.

MultiCite: Modeling realistic citations requires moving beyond the single-sentence single-label setting

Not only is it the largest collection of expert-annotated citation contexts to-date, MULTICITE contains multi-sentence, multi-label citation contexts annotated through-out entire full paper texts and can enable the development of new computational methods on three important CCA tasks.

Argument Mining on Clinical Trials1

A new annotated dataset is created about four different diseases, containing 976 argument components, to discuss evidence and claim detection from Randomized Clinical Trials and show the portability of the proposed approach over different branches of medicine.

Argumentative meanings and their stylistic configurations in clinical research publications

A schematised superstructure of the arguments from the corpus is presented, charting the configurations of stylistic features, which signal the elements of this superstructure, epistemic topoi.

Exploiting Citation Contexts for Physics Retrieval

It is found that relatively short citation contexts with moderate weights can improve retrieval performance, and the feasibility of identifying citation contexts in a large collection of physics papers is demonstrated, paving the way for future research that exploits citation contexts for retrieval.



Meta-discourse markers and problem-structuring in scientific articles

A formal description of the document structure of scientific articles from different disciplines is proposed, which could be of practical use for many applications in document management and for detecting document structure improvement in automatic abstracting.

Argumentative zoning information extraction from scientific text

It is demonstrated that this type of text analysis can be used for generating usertailored and task-tailored summaries and for performing more informative citation analyses, and the application of a robust discourse and argumentation analysis can make text understanding techniques for practical document management more robust.

Generating legal arguments and predictions from case texts

Methods for automatically finding abstract, legally relevant concepts in case texts are presented and it is found that replacing individual names by roles in the case texts led to better indexing, and that adding certain syntactic and semantic information, in the form of Propositional Patterns that capture a sense of "who did what", lead to better prediction.

Towards Domain-Independent Argumentative Zoning: Evidence from Chemistry and Computational Linguistics

This work presents a more informative AZ scheme with 15 categories in place of the original 7, and shows that it can be applied to the life sciences as well as to CL.

Identifying Sections in Scientific Abstracts using Conditional Random Fields

A novel approach to categorize sentences in scientific abstracts into four sections, objective, methods, results, and conclusions showed that CRFs could model the rhetorical structure of abstracts more suitably.

Towards Discipline-Independent Argumentative Zoning : Evidence from Chemistry and Computational Linguistics

This work presents a more informative AZ scheme with 15 categories in place of the original 7, and shows that it can be applied to the life sciences as well as to CL.

Unsupervised learning of rhetorical structure with un-topic models

It is demonstrated that the generality hypothesis is crucial for distinguishing between rhetorical and topical language and that features provided by the unsupervised model trained on a large corpus can improve the performance of a supervised AZ classifier.

Argumentation Schemes

This book takes the reader from the elementary exposition in the first chapter to the current state of the art in the research efforts to formalize and classify the schemes, outlined in the last three chapters.

The CoNLL-2010 Shared Task: Learning to Detect Hedges and their Scope in Natural Language Text

A general overview of the CoNLL-2010 Shared Task, including the annotation protocols of the training and evaluation datasets, the exact task definitions, the evaluation metrics employed and the overall results is provided.

Improved Information Structure Analysis of Scientific Documents Through Discourse and Lexical Constraints

This work explores a rich set of discourse and lexical constraints which it incorporates through the Generalized Expectation (GE) criterion to guide feature-based models with declarative domain knowledge encoded as posterior distribution constraints.