Contextual Argument Component Classification for Class Discussions

Proceedings of the 28th International Conference on Computational Linguistics, pages 1475–1480 Barcelona, Spain (Online), December 8-13, 2020 1475 Contextual Argument Component Classification for Class Discussions Luca Lugini and Diane Litman Department of Computer Science and Learning Research and Development Center University of Pittsburgh Pittsburgh, PA, USA Abstract Argument mining systems often consider contextual information, i.e. information outside of an argumentative discourse unit, when trained to accomplish tasks such as argument component identification, classification, and relation extraction. However, prior work has not carefully an- alyzed the utility of different contextual properties in context-aware models. In this work, we show how two different types of contextual information, local discourse context and speaker context, can be incorporated into a computational model for classifying argument components in multi-party classroom discussions. We find that both context types can improve performance, although the improvements are dependent on context size and position. 1 Motivation In a typical argument mining system, the first task is identifying spans of text consisting of argumentative discourse units (ADU), i.e. argument component identification (ACI). The next task, argument compo- nent classification (ACC), consists of assigning a label to each ADU according to an argument model, e.g. claims, evidence, etc. For example, row 1 in Table 1 is labeled claim since speaker 7 provides their personal view, while row 2 is labeled evidence because it references facts from a text. While “context” has been used in the argument mining literature to refer to several phenomena, we consider context to be auxiliary textual information outside the span of an ADU. It is generally accepted that context is important in argument mining. Stab and Gurevych (2014) as well as Nguyen and Litman (2016) use context features extracted from the sentence containing an ADU to improve ACC. Persing and Ng (2016), Habernal and Gurevych (2017) and Aker et al. (2017) similarly use contextual features in joint ACI/ACC models. Optiz and Frank (2019) analyze a previous argument mining system and find that, for its predictions, it relies on context more than it does on ADU content. Chakrabarty et al. (2019) indirectly model context in ACC by fine-tuning a BERT model to predict the next sentence (i.e. the context). Eger et al. (2017) analyzed several neural models for jointly performing ACI, ACC and argument relation extraction. All of these works share several limitations: (i) the context is either limited to a single configuration (e.g. one sentence before/after the ADU) or optimized along a single dimension (typically size but not position); (ii) only a subset of the features extracted for the target ADU are also extracted for context; (iii) context is typically based on ADU adjacency, although other ways of building context (e.g. based on speakers in multi-party dialogues) are possible. This work is licensed under a Creative Commons Attribution 4.0 International License. License details: http:// creativecommons.org/licenses/by/4.0/. Row ID ADU AC 1 7 I feel that she included herself in the book to give more of an unbiased point of view to it. claim 2 7 Because, obviously the …

Content truncated to 500 words