Role-play exercises are widely utilized for training across a variety of domains; however, they have many shortcomings, including low availability, resource intensity, and lack of diversity. Large language model-driven virtual agents offer a potential avenue to mitigate these limitations and offer lower-risk role-play. The implications, however, of shifting this human-human collaboration to human-agent collaboration are still largely unexplored. In this work we focus on the context of psychotherapy, as psychotherapists-in-training extensively engage in role-play exercises with peers and/or supervisors to practice the interpersonal and therapeutic skills required for effective treatment. We provide a case study of a realistic ''virtual patient'' system for mental health training, evaluated by trained psychotherapists in comparison to their previous experiences with both real role-play partners and real patients. Our qualitative, reflexive analysis generated three themes and thirteen subthemes regarding key interpersonal skills of psychotherapy, the utility of the system compared to traditional role-play techniques, and factors which impacted psychotherapist-perceived ''humanness'' of the virtual patient. Although psychotherapists were optimistic about the system's potential to bolster therapeutic skills, this utility was impacted by the extent to which the virtual patient was perceived as human-like. We leverage the Computers Are Social Actors framework to discuss human-virtual-patient collaboration for practicing rapport, and discuss challenges of prototyping novel human-AI systems for clinical contexts which require a high degree of unpredictability. We pull from the ''SEEK'' three-factor theory of anthropomorphism to stress the importance of adequately representing a variety of cultural communities within mental health AI systems, in alignment with decolonial computing.

The combination of gestures, intonations, and textual content plays a key role in argument delivery.However, the current literature mostly considers textual content while assessing the quality of an argument, and is limited to datasets containing short sequences (18-48 words).In this paper, we study argument quality assessment in a multimodal context, and experiment on DBATES, a publicly available dataset of long debate videos.First, we propose a set of interpretable debate-centric features such as clarity, content variation, body movement cues, and pauses, inspired by theories of argumentation quality.Second, we design the Multimodal ARgument Quality assessor (MARQ) -a hierarchical neural network model that summarizes the multimodal signals on long sequences and enriches the multimodal embedding with debate-centric features.Our proposed MARQ model achieves an accuracy of 81.91% on the argument quality prediction task and outperforms established baseline models with an error rate reduction of 22.7%.Through ablation studies, we demonstrate the importance of multimodal cues in modeling argument quality.

Tahmid Hasan, Abhik Bhattacharjee, Kazi Samin, Masum Hasan, Madhusudan Basak, M. Sohel Rahman, Rifat Shahriyar. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020.

Firewalls are core elements in network security. However, managing firewall rules, particularly, in multifirewall enterprise networks, has become a complex and error-prone task. Firewall filtering rules have to be written, ordered, and distributed carefully in order to avoid firewall policy anomalies that might cause network vulnerability. Therefore, inserting or modifying filtering rules in any firewall requires thorough intrafirewall and interfirewall analysis to determine the proper rule placement and ordering in the firewalls. In this paper, we identify all anomalies that could exist in a single- or multifirewall environment. We also present a set of techniques and algorithms to automatically discover policy anomalies in centralized and distributed firewalls. These techniques are implemented in a software tool called the "Firewall Policy Advisor" that simplifies the management of filtering rules and maintains the security of next-generation firewalls.

Event correlation is a key functionality of a network management system that is used to determine the root cause of faults in a network, and to filter out redundant and spurious events. A number of event correlation systems have been proposed. The event correlation systems generally combine causal and temporal correlation models with the topology of a network. The power and robustness of the models used and the algorithms developed vary from system to system. However, in the absence of a simple, uniform, and precise presentation of the event-correlation problem, it is impossible to compare their relative power or even analyze them for their properties. In general, causal and temporal-based correlation models have not been rigorously presented or thoroughly investigated. In this paper we formalize the concepts of causal and temporal correlation using a single conceptual framework. We characterize various properties of the framework. We can characterize existing systems based on the formal properties of our framework, and we consider one system as an illustrative example.