Philip R. Cohen

Philip R. Cohen

Auto-generated profile, based on publicly available information

Philip R. Cohen

Openstream.ai, Bridgewater, United States

Research Focus & Metrics

Academic Career Length

23Years (2004-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 March 2016 in Oncotarget
Verified
Journal Article
Open access
PDF file
PCPhilip R. Cohen
Philip R. Cohen
BTBrett N. Tomson
Brett N. Tomson
SESheryl K. Elkin
Sheryl K. Elkin
EMErica Marchlik
Erica Marchlik
JCJennifer Carter
Jennifer Carter
RKRazelle Kurzrock
Razelle Kurzrock
Genomic portfolio of Merkel cell carcinoma as determined by comprehensive genomic profiling: implications for targeted therapeutics

17 February 2025 in International Journal of Artificial Intelligence in Education
Verified
Journal Article
Open access
PDF file
RLRachel Love
Rachel Love
ELEdith Law
Edith Law
PCPhilip R. Cohen
Philip R. Cohen
DKDana Kulić
Dana Kulić
Conversational teachable agents offer a promising platform to support learning, both in the classroom and in remote settings. In this context, the agent takes the role of the novice, while the student takes on the role of teacher, eliciting the Protégé effect, a pedagogical phenomenon known to increase engagement in the teaching task, and also improve cognitive outcomes. In prior work, interactions with teachable agents show frequent use of interface elements to support learning, and few examples utilise natural language as the sole interaction modality between both user and agent. This work investigates the effect of teaching using natural language while interacting with a virtual agent via the Curiosity Notebook on learning outcomes and engagement. A method of teaching by selecting sentences from source material is compared to paraphrasing from the source material and typing. The results indicate that teaching by paraphrasing in natural language is perceived as being more helpful for learning, but that this perception of improvement is not reflected in actual learning gain over a fixed interaction. Participants also show a short-term preference for teaching via sentence-selection, which they perceive as requiring less effort. There is a positive relationship between the amount of paraphrasing users engage in and improved learning outcomes.

1 January 2023
Verified
Conference Paper
Open access
PDF file
LHLevon Haroutunian
Levon Haroutunian
ZLZhuang Li
Zhuang Li
LGLucian Galescu
Lucian Galescu
PCPhilip R. Cohen
Philip R. Cohen
RTRaj Tumuluri
Raj Tumuluri
GHGholamreza Haffari
Gholamreza Haffari
Levon Haroutunian, Zhuang Li, Lucian Galescu, Philip Cohen, Raj Tumuluri, Gholamreza Haffari. Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

22 July 2025 in ACM Transactions on Human-Robot Interaction
Verified
Journal Article
Open access
RLRachel Love
Rachel Love
PCPhilip R. Cohen
Philip R. Cohen
GVGentiane Venture
Gentiane Venture
DKDana Kulić
Dana Kulić
Teachable robots in education have the ability to increase student engagement and learning through personalised interactions and the use of social behaviours, such as speech, gaze and emotional expressions. Adaptation of these behaviours is motivated by an interest in tailoring the learning experience to an individual user and improving user outcomes. This work proposes an adaptive response-selection algorithm for a teachable robot which aims to increase user task engagement. A Q-learning algorithm learns an individualised policy and is rewarded based on the user’s paraphrasing behaviour and response time when teaching the robot. A user study is conducted across two user groups, recruited from Australia and Japan. This study evaluates the performance of the adaptive approach for response selection against a non-adaptive method and explores the differences in response and perception of the teaching task between the two participant groups. The results show that measures of task engagement increase more when using the adaptive approach compared to a non-adaptive method of response selection, but that this difference is not consistent across both participant groups. The adaptive approach is also shown to have a positive effect on user perceptions of the interaction.

28 June 2004
Verified
Book Chapter
Closed access
RLRichard Levandowski
Richard Levandowski
PCPhilip Cohen
Philip Cohen

22 November 2025 in Autonomous Agents and Multi-Agent Systems
Verified
Journal Article
Open access
PDF file
PCPhilip R. Cohen
Philip R. Cohen
LGLucian Galescu
Lucian Galescu
MSMaayan Shvo
Maayan Shvo
Eva is a multimodal conversational framework for building planning-based systems that help users accomplish their domain goals through collaborative dialogue. We argue that planning-based systems can do this by inferring users’ intentions, adopting goals to achieve them, developing plans to achieve those goals, detecting whether obstacles are present, finding plans to overcome them, and planning their actions, including speech acts. In the Eva framework, conversational agents can maintain and reason with their own beliefs, goals and intentions, and explicitly reason about those of their users. Belief reasoning is accomplished with a modal Horn-clause meta-interpreter. The planning and reasoning subsystems obey the principles of persistent goals and intentions, including the formation and decomposition of intentions to perform complex actions, as well as the conditions under which they can be given up. In virtue of its planning process, Eva treats its speech acts just like its other actions – physical acts affect physical states, digital acts affect digital states, and speech acts affect mental and social states. This general framework enables systems to plan a variety of speech acts including requests, informs, questions, confirmations, recommendations, offers, acceptances, greetings, and emotive expressions. Each of these has a formally specified semantics which is used during the planning and reasoning processes. Because Eva-based agents can keep track of different users’ mental states, they can engage in multi-party dialogues. Importantly, the framework supports systems’ explanations of their actions because they have created plans standing behind each of them. As a reaction to the near-universal focus on using large language models for every application, a trend has emerged recently towards integrated neuro-symbolic architectures. The Eva framework is an example of such an architecture in the area of collaborative dialogue systems.