We introduce a corpus of the 2016 U.S. presidential debates and commentary, containing 4,648 argumentative propositions annotated with fine-grained proposition types. Modern machine learning pipelines for analyzing argument have difficulty distinguishing between types of propositions based on their factuality, rhetorical positioning, and speaker commitment. Inability to properly account for these facets leaves such systems inaccurate in understanding of fine-grained proposition types. In this paper, we demonstrate an approach to annotating for four complex proposition types, namely normative claims, desires, future possibility, and reported speech. We develop a hybrid machine learning and human workflow for annotation that allows for efficient and reliable annotation of complex linguistic phenomena, and demonstrate with preliminary analysis of rhetorical strategies and structure in presidential debates. This new dataset and method can support technical researchers seeking more nuanced representations of argument, as well as argumentation theorists developing new quantitative analyses.

As the demand for explainable deep learning grows in the evaluation of language technologies, the value of a principled grounding for those explanations grows as well. Here we study the state-of-the-art in explanation for neural models for NLP tasks from the viewpoint of philosophy of science. We focus on recent evaluation work that finds brittleness in explanations obtained through attention mechanisms. We harness philosophical accounts of explanation to suggest broader conclusions from these studies. From this analysis, we assert the impossibility of causal explanations from attention layers over text data. We then introduce NLP researchers to contemporary philosophy of science theories that allow robust yet non-causal reasoning in explanation, giving computer scientists a vocabulary for future research.

Most natural language processing research now recommends large Transformer-based models with fine-tuning for supervised classification tasks; older strategies like bag-of-words features and linear models have fallen out of favor. Here we investigate whether, in automated essay scoring (AES) research, deep neural models are an appropriate technological choice. We find that fine-tuning BERT produces similar performance to classical models at significant additional cost. We argue that while state-of-the-art strategies do match existing best results, they come with opportunity costs in computational resources. We conclude with a review of promising areas for research on student essays where the unique characteristics of Transformers may provide benefits over classical methods to justify the costs.