An Empirical Study of Span Representations in Argumentation Structure Parsing

For several natural language processing (NLP) tasks, span representation design is attracting considerable attention as a promising new technique; a common basis for an effective design has been established. With such basis, exploring task-dependent extensions for argumentation structure parsing (ASP) becomes an interesting research direction. This study investigates (i) span representation originally developed for other NLP tasks and (ii) a simple task-dependent extension for ASP. Our extensive experiments and analysis show that these representations yield high performance for ASP and provide some challenging types of instances to be parsed.

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

[2]  Pascal Denis,et al.  Learning Connective-based Word Representations for Implicit Discourse Relation Identification , 2016, EMNLP.

[3]  Livio Robaldo,et al.  The Penn Discourse TreeBank 2.0. , 2008, LREC.

[4]  William C. Mann,et al.  Rhetorical Structure Theory: Description and Construction of Text Structures , 1987 .

[5]  Chris Reed,et al.  Combining Argument Mining Techniques , 2015, ArgMining@HLT-NAACL.

[6]  Dan Klein,et al.  Constituency Parsing with a Self-Attentive Encoder , 2018, ACL.

[7]  Qi Li,et al.  Discourse Parsing with Attention-based Hierarchical Neural Networks , 2016, EMNLP.

[8]  Dan Klein,et al.  A Minimal Span-Based Neural Constituency Parser , 2017, ACL.

[9]  Philipp Koehn,et al.  Statistical Significance Tests for Machine Translation Evaluation , 2004, EMNLP.

[10]  Yueting Zhuang,et al.  Discourse Marker Augmented Network with Reinforcement Learning for Natural Language Inference , 2018, ACL.

[11]  Luke S. Zettlemoyer,et al.  End-to-end Neural Coreference Resolution , 2017, EMNLP.

[12]  Iryna Gurevych,et al.  Robust Argument Unit Recognition and Classification , 2019, ArXiv.

[13]  Omer Levy,et al.  Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling , 2018, ACL.

[14]  Hiroyuki Shindo,et al.  A Span Selection Model for Semantic Role Labeling , 2018, EMNLP.

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

[16]  Luke S. Zettlemoyer,et al.  Deep Contextualized Word Representations , 2018, NAACL.

[17]  Baobao Chang,et al.  Graph-based Dependency Parsing with Bidirectional LSTM , 2016, ACL.

[18]  A. Peldszus.  An Annotated Corpus of Argumentative Microtexts , 2015 .

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

[20]  Camille Pradel,et al.  Mining Discourse Markers for Unsupervised Sentence Representation Learning , 2019, NAACL.

[21]  Diane J. Litman,et al.  Context-aware Argumentative Relation Mining , 2016, ACL.

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

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

[24]  James B. Freeman,et al.  Argument Structure: Representation and Theory , 2011, Argumentation Library.

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

[26]  Manfred Stede,et al.  From Argument Diagrams to Argumentation Mining in Texts: A Survey , 2013, Int. J. Cogn. Informatics Nat. Intell..

[27]  Rashmi Prasad,et al.  The Penn Discourse Treebank , 2004, LREC.

[28]  Luke S. Zettlemoyer,et al.  Higher-Order Coreference Resolution with Coarse-to-Fine Inference , 2018, NAACL.