Evidence-based medicine aims at making decisions about the care of individual patients based on the explicit use of the best available evidence in the patient clinical history and the medical literature results. Argumentation represents a natural way of addressing this task by (i) identifying evidence and claims in text, and (ii) reasoning upon the extracted arguments and their relations to make a decision. ACTA 2.0 is an automated tool which relies on Argument Mining methods to analyse the abstracts of clinical trials to extract argument components and relations to support evidence-based clinical decision making. ACTA 2.0 allows also for the identification of PICO (Patient, Intervention, Comparison, Outcome) elements, and the analysis of the effects of an intervention on the outcomes of the study. A REST API is also provided to exploit the tool’s functionalities.

In the last years, several empirical approaches have been proposed to tackle argument mining tasks, e.g., argument classification, relation prediction, argument synthesis. These approaches rely more and more on language models (e.g., BERT) to boost their performance. However, these language models require a lot of training data, and size is often a drawback of the available argument mining data sets. The goal of this paper is to assess the robustness of these language models for the argument classification task. More precisely, the aim of the current work is twofold: first, we generate adversarial examples addressing linguistic perturbations in the original sentences, and second, we improve the robustness of argument classification models using adversarial training. Two empirical evaluations are addressed relying on standard datasets for AM tasks, whilst the generated adversarial examples are qualitatively evaluated through a user study. Results prove the robust-ness of BERT for the argument classification task, yet highlighting that it is not invulnerable to simple linguistic perturbations in the input data.

Recent advances in language model (LM) pre-training from large-scale corpora have shown to improve various natural language processing tasks. They achieve performances comparable to non-expert humans on the GLUE benchmark for natural language understanding (NLU). While the improvement of the different contextualized representations comes from (i) the usage of more and more data, (ii) changing the types of lexical pre-training tasks or (iii) increasing the model size, NLU is more than memorizing word co-occurrences. But how much world knowledge and common sense can those language model capture? How much can those models infer from just the lexical information? To overcome this problem, some approaches include semantic information in the training process. In this paper, we highlight existing approaches to combine different types of semantics with language models during the pre-training or fine-tuning phase.

Argument(ation) Mining (AM) typically aims at identifying argumentative components in text and predicting the relations among them. Evidence-based decision making in the health-care domain targets at supporting clinicians in their deliberation process to establish the best course of action for the case under evaluation. Although the reasoning stage of this kind of frameworks received considerable attention, little effort has been devoted to the mining stage. We extended an existing dataset by annotating 500 abstracts of Randomized Controlled Trials (RCT) from the MEDLINE database, leading to a dataset of 4198 argument components and 2601 argument relations on different diseases (i.e., neoplasm, glau-coma, hepatitis, diabetes, hypertension). We propose a complete argument mining pipeline for RCTs, classifying argument components as evidence and claims, and predicting the relation, i.e., attack or support , holding between those argument components. We experiment with deep bidirectional transformers in combination with different neural architectures (i.e., LSTM, GRU and CRF) and obtain a macro F1-score of .87 for component detection and .68 for relation prediction , outperforming current state-of-the-art end-to-end AM systems.

Argumentative analysis of textual documents of various nature (e.g., persuasive essays, online discussion blogs, scientific articles) allows to detect the main argumentative components (i.e., premises and claims) present in the text and to predict whether these components are connected to each other by argumentative relations (e.g., support and attack), leading to the identification of (possibly complex) argumentative structures. Given the importance of argument-based decision making in medicine, in this demo paper we introduce ACTA, a tool for automating the argumentative analysis of clinical trials. The tool is designed to support doctors and clinicians in identifying the document(s) of interest about a certain disease, and in analyzing the main argumentative content and PICO elements.

Argument-based decision making has been employed to support a variety of reasoning tasks over medical knowledge. These include evidence-based justifications of the effects of treatments, the detection of conflicts in the knowledge base, and the enabling of uncertain and defeasible reasoning in the health-care sector. However, a common limitation of these approaches is that they rely on structured input information. Recent advances in argument mining have shown increasingly accurate results in detecting argument components and predicting their relations from unstructured, natural language texts. In this study, we discuss evidence and claim detection from Randomized Clinical Trials. To this end, we create a new annotated dataset about four different diseases (glaucoma, diabetes, hepatitis B, and hypertension), containing 976 argument components (697 containing evidence, 279 claims). Empirical results are promising, and show the portability of the proposed approach over different branches of medicine.

This paper discusses the design and evaluation of a coaching system used to train young politicians to apply appropriate multimodal rhetoric devices to improve their debate skills. The presented study is carried out to develop debate performance assessment methods and interaction models underlying a Virtual Debate Coach (VDC) application. We identify a number of criteria associated with three questions: (1) how convincing is a debater's argumentation; (2) how well are debate arguments structured; and (3) how well is an argument delivered. We collected and analysed multimodal data of trainees' debate behaviour, and contrasted it with that of skilled professional debaters. Observational, correlation and machine learning experiments were performed to identify multimodal correlates of convincing debate performance and link them to experts' assessments. A rich set of prosodic, motion, linguistic and structural features was considered for the system to operate on. The VDC system was positively evaluated in a trainee-based setting.