Investigating the Role of Argumentation in the Rhetorical Analysis of Scientific Publications with Neural Multi-Task Learning Models

Exponential growth in the number of scientific publications yields the need for effective automatic analysis of rhetorical aspects of scientific writing. Acknowledging the argumentative nature of scientific text, in this work we investigate the link between the argumentative structure of scientific publications and rhetorical aspects such as discourse categories or citation contexts. To this end, we (1) augment a corpus of scientific publications annotated with four layers of rhetoric annotations with argumentation annotations and (2) investigate neural multi-task learning architectures combining argument extraction with a set of rhetorical classification tasks. By coupling rhetorical classifiers with the extraction of argumentative components in a joint multi-task learning setting, we obtain significant performance gains for different rhetorical analysis tasks.

[1]  Iryna Gurevych,et al.  Argumentation Mining in User-Generated Web Discourse , 2016, CL.

[2]  Simone Teufel.  Towards Discipline-Independent Argumentative Zoning : Evidence from Chemistry and Computational Linguistics , 2009 .

[3]  Marc Moens,et al.  Articles Summarizing Scientific Articles: Experiments with Relevance and Rhetorical Status , 2002, CL.

[4]  Iryna Gurevych,et al.  What is the Essence of a Claim? Cross-Domain Claim Identification , 2017, EMNLP.

[5]  G. Gilbert.  Referencing as Persuasion , 1977 .

[6]  Nazli Goharian,et al.  Scientific Article Summarization Using Citation-Context and Article’s Discourse Structure , 2015, EMNLP.

[7]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[8]  Claire Cardie,et al.  Argument Mining with Structured SVMs and RNNs , 2017, ACL.

[9]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[10]  Horacio Saggion,et al.  A Multi-Layered Annotated Corpus of Scientific Papers , 2016, LREC.

[11]  John Thickstun,et al.  CONDITIONAL RANDOM FIELDS , 2016 .

[12]  Goran Glavas,et al.  University of Mannheim @ CLSciSumm-17: Citation-Based Summarization of Scientific Articles Using Semantic Textual Similarity , 2017, BIRNDL@SIGIR.

[13]  Manfred Stede,et al.  Joint prediction in MST-style discourse parsing for argumentation mining , 2015, EMNLP.

[14]  Lutz Bornmann,et al.  Growth rates of modern science: A bibliometric analysis based on the number of publications and cited references , 2014, J. Assoc. Inf. Sci. Technol..

[15]  G. Gilbert,et al.  The Transformation of Research Findings into Scientific Knowledge , 1976 .

[16]  Johannes Bjerva,et al.  Will my auxiliary tagging task help? Estimating Auxiliary Tasks Effectivity in Multi-Task Learning , 2017, NODALIDA.

[17]  Zhipeng Luo,et al.  Conditional Random Fields , 2014 .

[18]  Chris Reed,et al.  Argumentation Schemes , 2008 .

[19]  Roberto Cipolla,et al.  Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[20]  Anna Rumshisky,et al.  Here’s My Point: Joint Pointer Architecture for Argument Mining , 2016, EMNLP.

[21]  Simone Teufel,et al.  Corpora for the Conceptualisation and Zoning of Scientific Papers , 2010, LREC.

[22]  S. Toulmin.  The uses of argument , 1960 .

[23]  Horacio Saggion,et al.  Dr. Inventor Framework: Extracting Structured Information from Scientific Publications , 2015, Discovery Science.

[24]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[25]  Iryna Gurevych,et al.  Neural End-to-End Learning for Computational Argumentation Mining , 2017, ACL.

[26]  Hinrich Schütze,et al.  Towards a Generic and Flexible Citation Classifier Based on a Faceted Classification Scheme , 2012, COLING.

[27]  Alexander S. Yeh,et al.  More accurate tests for the statistical significance of result differences , 2000, COLING.

[28]  Bart Verheij,et al.  The Toulmin Argument Model in Artificial Intelligence , 2009, Argumentation in Artificial Intelligence.

[29]  Iryna Gurevych,et al.  Multi-Task Learning for Argumentation Mining in Low-Resource Settings , 2018, NAACL.

[30]  Joydeep Ghosh,et al.  Cluster Ensembles --- A Knowledge Reuse Framework for Combining Multiple Partitions , 2002, J. Mach. Learn. Res..

[31]  J. Anscombre,et al.  L'argumentation dans la langue , 1976 .

[32]  Vincent Ng,et al.  End-to-End Argumentation Mining in Student Essays , 2016, NAACL.

[33]  Dragomir R. Radev,et al.  NLP-driven citation analysis for scientometrics , 2016, Natural Language Engineering.

[34]  Paolo Torroni,et al.  Argumentation Mining , 2016, ACM Trans. Internet Techn..

[35]  Dragomir R. Radev,et al.  Purpose and Polarity of Citation: Towards NLP-based Bibliometrics , 2013, NAACL.

[36]  Diyi Yang,et al.  Hierarchical Attention Networks for Document Classification , 2016, NAACL.

[37]  Daniel Ferrés,et al.  Multi-level mining and visualization of scientific text collections: Exploring a bi-lingual scientific repository , 2017, WOSP@JCDL.

[38]  Iryna Gurevych,et al.  Linking the Thoughts: Analysis of Argumentation Structures in Scientific Publications , 2015, ArgMining@HLT-NAACL.

[39]  George Hripcsak,et al.  Technical Brief: Agreement, the F-Measure, and Reliability in Information Retrieval , 2005, J. Am. Medical Informatics Assoc..

[40]  Anders Søgaard,et al.  Deep multi-task learning with low level tasks supervised at lower layers , 2016, ACL.

[41]  Simone Teufel,et al.  Towards Domain-Independent Argumentative Zoning: Evidence from Chemistry and Computational Linguistics , 2009, EMNLP.

[42]  James B. Freeman,et al.  Dialectics and the Macrostructure of Arguments , 1991 .

[43]  Stephen E. Toulmin,et al.  The Uses of Argument, Updated Edition , 2008 .

[44]  Marie-Francine Moens,et al.  Argumentation mining: the detection, classification and structure of arguments in text , 2009, ICAIL.

[45]  Horacio Saggion,et al.  Knowledge Extraction and Modeling from Scientific Publications , 2016 .

[46]  Paolo Torroni,et al.  Argument Mining: A Machine Learning Perspective , 2015, TAFA.

[47]  Hai Zhuge,et al.  Summarization of scientific documents by detecting common facts in citations , 2014, Future Gener. Comput. Syst..

[48]  Barbara Plank,et al.  When is multitask learning effective? Semantic sequence prediction under varying data conditions , 2016, EACL.

[49]  Trevor J. M. Bench-Capon.  Specification and Implementation of Toulmin Dialogue Game , 1999 .

[50]  Awais Athar,et al.  Sentiment Analysis of Citations using Sentence Structure-Based Features , 2011, ACL.

[51]  Goran Glavas,et al.  Investigating Convolutional Networks and Domain-Specific Embeddings for Semantic Classification of Citations , 2017, WOSP@JCDL.

[52]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[53]  Luis Gravano,et al.  Predicting the impact of scientific concepts using full‐text features , 2016, J. Assoc. Inf. Sci. Technol..

[54]  Phan Minh Dung,et al.  On the Acceptability of Arguments and its Fundamental Role in Nonmonotonic Reasoning, Logic Programming and n-Person Games , 1995, Artif. Intell..

[55]  Jean Carletta,et al.  An annotation scheme for discourse-level argumentation in research articles , 1999, EACL.

[56]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[57]  Dietrich Rebholz-Schuhmann,et al.  Automatic recognition of conceptualization zones in scientific articles and two life science applications , 2012, Bioinform..

[58]  Jan Snajder,et al.  Back up your Stance: Recognizing Arguments in Online Discussions , 2014, ArgMining@ACL.

[59]  Iryna Gurevych,et al.  Argumentation Mining in Persuasive Essays and Scientific Articles from the Discourse Structure Perspective , 2014, ArgNLP.

[60]  Iryna Gurevych,et al.  Which argument is more convincing? Analyzing and predicting convincingness of Web arguments using bidirectional LSTM , 2016, ACL.

[61]  Simone Teufel,et al.  Automatic classification of citation function , 2006, EMNLP.

[62]  Dragomir R. Radev,et al.  Coherent Citation-Based Summarization of Scientific Papers , 2011, ACL.

[63]  Iryna Gurevych,et al.  Parsing Argumentation Structures in Persuasive Essays , 2016, CL.

[64]  Horacio Saggion,et al.  On the Discoursive Structure of Computer Graphics Research Papers , 2015, LAW@NAACL-HLT.