Snowy colonnade

Benjamin Kane


URCS Grad Student


Bio

I'm a second-year PhD student of Computer Science at the University of Rochester, with a focus on Artificial Intelligence. Before that, I graduated from the University of Rochester with a BS in Computer Science as well as a BA in Economics, giving me an interest in the practical applications of intelligent agents towards the social sciences and real-world domains. Currently, my general research interests lie within knowledge representation & commonsense reasoning, natural language understanding, and dialogue planning.


Under the advisorship of Dr. Lenhart Schubert and Dr. Aaron Steven White, some projects that I have worked on include:

  • Blocks World dialogue system: Creation of an end-to-end dialogue system capable of holding a spatial question-answering dialogue with a human about physical blocks which can be freely arranged on a table. Designed a semantic parser capable of processing a wide range of spatial questions into unscoped logical form (ULF) representations using hierarchical pattern transduction trees. Improved dialogue context and episodic memory in dialogue system to enable the system to answer questions about historical actions and relations. (Collaboration with Georgiy Platonov)

  • SOPHIE (end-of-life communication dialogue system): Creation of a dialogue system and virtual human capable of acting as a cancer patient in practice doctor-patient dialogues. Developed in conjunction with collaborators in the ROC HCI lab and the UR Medical Center (URMC), with the goal of helping doctors to improve communication in end-of-life dialogue scenarios. (Collaboration with ROC HCI and URMC Center for Communication and Disparities Research)

  • Veridicality, Negation-Raising, and Fine-Grained Inference: Collection of lexical-scale human annotations targeting the belief & desire properties of different English verbs. Empirical analysis of the relations between these lexical semantic properties and the veridicality and negation-raising inferences that are licensed, using a neural LSTM-based NLI model with RoBERTa embeddings. (Collaboration with Will Gantt and Ruoyang Hu)


In my free time, I'm an avid martial artist, and currently train in Brazilian Jiu Jitsu and Isshin-ryƫ Karate. I also enjoy music (I play flute and synthesizers), photography, and am an administrator/texture developer/builder for WesterosCraft.


CV

Click here to view CV.


CSC 400 Mock NSF Proposal

Managing intensive rotational grazing using reinforcement learning based livestock simulations


Papers

Conference
  1. Platonov G.; Kane B.; Gindi A.; Schubert L. K. A Spoken Dialogue System for Spatial Question Answering in a Physical Blocks World. SIGDIAL. July 1-3, 2020, Virtual.

  2. Razavi S. Z.; Kane B.; Schubert L. K. Investigating Linguistic and Semantic Features for Turn-Taking Prediction in Open-Domain Human-Computer Conversation. InterSpeech. September 15-19, 2019, Graz, Austria.

Workshop
  1. Kim G. L.; Kane B.; Duong V.; Mendiratta M.; McGuire G.; Sackstein S.; Platonov G.; Schubert L. K. Generating Discourse Inferences from Unscoped Episodic Logical Formulas. 1st Int. Workshop on Designing Meaning Representations (DMR), at the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019). Aug 1, 2019, Florence, Italy.

  2. Razavi S. Z.; Schubert L. K.; Kane B.; Rafayet Ali M.; Van Orden K. A.; Ma T. Dialogue Design and Management for Multi-Session Casual Conversation with Older Adults. Workshop on User-Aware Conversational Agents (User2Agent), at the 24th Int. Conf. on Intelligent User Interfaces (ACM IUI 2019). March 17-20, 2019, Los Angeles, USA.

  3. Kane B.; Luo, J. 2018. Do the Communities We Choose Shape our Political Beliefs? A Study of the Politicization of Topics in Online Social Groups. Workshop on Big Social Media Data Management and Analysis (BSMDMA), at the IEEE International Conference on Big Data. December 10-13, 2018, Seattle, USA.

Preprint
  1. Kane B.; Platonov G.; Schubert L. K. History-Aware Question Answering in a Blocks World Dialogue System. arXiv:2005.12501.