| - | Carnegie Mellon University, Pittsburgh, PA Ph.D. Candidate in Computer Science, expected graduation: February 2007 Thesis: "Error Awareness and Recovery in Task-Oriented Spoken Dialog Systems" Advisors: Alex Rudnicky, Roni Rosenfeld Thesis Committee: Alex Rudnicky, Roni Rosenfeld, Jeff Schneider, Eric Horvitz M.S. in Computer Science, CMU, May 2003 |
| - |
"Politehnica" University, Timisoara, Romania B.S. in Computer Science, June 2000 Thesis: "Stochastically-Based Semantic Analysis in Human-Computer Dialog" Advisor: Marian Boldea |
| - | Bohus, D., Raux, A., Harris, T., Eskenazi, M., and Rudnicky, A. (2007) - Olympus: an open-source framework for conversational spoken language interface research, to appear in HLT-NAACL 2007 workshop on Bridging the Gap: Academic and Industrial Research in Dialog Technology, Rochester, NY |
| - | Bohus, D., Grau, S., Huggins-Daines, D., Keri, V., Krishna, G., Kumar, R., Raux, A., and Tomko, S. (2007) - Conquest - an Open-Source Dialog System for Conferences, to appear in Proceedings of HLT-NAACL 2007, Rochester, NY |
| - | Tetreault, J., and Bohus, D., (2007) - Estimating the Reliability of MDP Policies: a Confidence Interval Approach, to appear in HLT-NAACL 2007, Rochester, NY |
| - | Bohus, D., Langner, B., Raux, A., Black, A., Eskenazi, M. and Rudnicky A. (2006) - Online Supervised Learning of Non-understanding Recovery Policies, in SLT-2006, Palm Beach, Aruba |
| - | Bohus, D., and Rudnicky, A. (2006) - A K Hypotheses + Other Belief Updating Model, in AAAI Workshop on Statistical and Empirical Approaches to Spoken Dialogue Systems, 2006, Boston, MA |
| - | Raux, A., Bohus, D., Langner, B., Black, A., and Eskenazi, M. (2006) - Doing Research in a Deployed Spoken Dialog System: One Year of Let's Go! Public Experience, in Interspeech-2006, Pittsburgh, PA |
| - | Bohus, D., and Rudnicky, A. (2005) - Constructing Accurate Beliefs in Spoken Dialog Systems, in ASRU-2005, San Juan, Puerto Rico |
| - | Bohus, D., and Rudnicky, A. (2005) - Error Handling in the RavenClaw dialog management architecture, in HLT-EMNLP-2005, Vancouver, CA |
| - | Bohus, D., and Rudnicky, A. (2005) - Sorry, I Didn't Catch That! - An Investigation of Non-understanding Errors and Recovery Strategies, in SIGdial-2005, Lisbon, Portugal |
| - | Bohus, D., and Rudnicky, A. (2005) - A Principled Approach for Rejection Threshold Optimization in Spoken Dialog Systems, in Interspeech-2005, Lisbon, Portugal |
| - | Raux, A., Langner, B., Bohus, D., Black, A., and Eskenazi, M. (2005) - Let's Go Public! Taking a Spoken Dialog System to the Real World, in Interspeech-2005, Lisbon, Portugal |
| - | Bohus, D., and Rudnicky A. (2003) - RavenClaw: Dialog Management Using Hierarchical Task Decomposition and an Expectation Agenda, in Eurospeech-2003, Geneva, Switzerland |
| - | Aist, G., Dowding, J., Hockey, B.A., Rayner, M., Hieronymus, J., Bohus, D., Boven, B., Blaylock, N., Campana, E., Early, S., Gorrell, G., and Phan, S. (2003) - Talking through procedures: An intelligent Space Station procedure assistant, in Demo Session at EACL-2003, Budapest, Hungary |
| - | Bohus, D., and Rudnicky A. (2002) - LARRI: A Language-Based Maintenance and Repair Assistant, in IDS-2002, Kloster Irsee, Germany |
| - | Bohus, D., and Rudnicky, A. (2001) - Modeling the Cost of Misunderstandings in the CMU Communicator Dialog System, in ASRU-2001, Madonna di Campiglio, Italy |
| - | Carpenter P., Jin C., Wilson D., Zhang R., Bohus, D., and Rudnicky A. (2001) - Is This Conversation on Track?, in Eurospeech-2001, Aalborg, Denmark |
| - | Bohus, D., and Boldea, M. (2000) - A Web-based Text Corpora Development System, in LREC-2000, Athens, Greece |
| - | Aist, G., Bohus, D., Boven, B., Campana, E., Early, S., Phan, S. (2004) - Initial Development of a Voice-Activated Astronaut Assistant for Procedural Tasks: From Need to Concept to Prototype, in Journal of Interactive Instruction Development, Volume 16, Nr. 3, Winter 2004, pp 32-36 |
| - | Bohus, D. (2000) - Stochastic Speech Understanding for Human-Computer Dialogue, Romanian Journal of Information Science and Technology, Volume 4, No 3-4/2001, p.261 |
| - | Bohus, D., and Rudnicky, A. (2005) - Sorry, I Didn't Catch That! - An Investigation of Non-understanding Errors and Recovery Strategies, to appear in "Recent Trends in Discourse and Dialogue", editors Laila Dybkjaer and Wolfgang Minker, Springer. |
| - | Bohus, D., and Rudnicky A. (2002) - LARRI: A Language-Based Maintenance and Repair Assistant, in in "Spoken Multimodal Human-Computer Dialogue in Mobile Environments", Springer 2005, ISBN 1402030738 |
| - | Bohus, D. (2004) - Error Awareness and Recovery in Task-Oriented Spoken Dialogue Systems, Ph.D Thesis Proposal, Carnegie Mellon University, Pittsburgh, PA |
| - | Bohus, D., and Rudnicky, A. (2004) - Task-Independent Conversational Strategies in the RavenClaw Dialogue Management Framework, unpublished manuscript |
| - | Bohus, D., and Rudnicky A. (2002) - Integrating Multiple Knowledge Sources for Utterance-Level Confidence Annotation in the CMU Communicator Spoken Dialog System, Technical Report CS-190, Carnegie Mellon University, Pittsburgh, PA |
| - | Bohus, D. (2000) - Stochastically-Based Semantic Analysis in Human-Computer Dialog, Graduate Thesis, Politechnica University of Timisoara, Romania |
| - | Belief Updating in Spoken Dialog Systems, IHMC invited talk, IHMC, April, 2006 |
| - | Constructing Accurate Beliefs in Task-Oriented Spoken Dialog Systems, AT&T research invited talk, AT&T, October 2005 |
| - | Misunderstandings, Corrections and Beliefs in Spoken Language Interfaces, Conversational Interfaces class, invited talk, CMU, September 2005 |
| - | A Scalable Reinforcement Learning Approach for Error Handling in Spoken Dialog Systems, invited talk, EU PASCAL workshop on Principled Methods for Trading Exploration and Exploitation, London, UK, July 2005 |
| - |
Belief Updating in Task-Oriented Spoken Dialog Systems, invited talk, Cambridge, UK, July 2005 |
| - |
Thesis Research, Carnegie Mellon University, 2003 - present A persistent and important problem in the development of spoken language interfaces is their lack of robustness when faced with understanding-errors. The problem stems mostly from the unreliability of current speech recognition technology and is present across all domains and interaction types. My dissertation research aims to address this problem by: (1) endowing spoken language interfaces with better error awareness, (2) constructing and evaluating a rich repertoire of error recovery strategies, and (3) developing scalable, data-driven approaches for making error handling decisions. |
| - |
Research in Dialog Management, Carnegie Mellon University, 2000 - present Developed RavenClaw, a dialog management framework for complex, task-oriented spoken dialog systems. RavenClaw isolates the domain-specific aspects of dialog control from domain-independent conversational behaviors. To date, this framework has been used to construct and successfully deploy several spoken dialog systems spanning different domains and interaction types (see www.ravenclaw-olympus.org). Furthermore, RavenClaw provides the infrastructure for a number of research projects investigating issues like error-handling, turn-taking and multi-participant dialog. |
| - |
Summer Internship, Adaptive Systems and Interaction, Microsoft Research, 2003 With Tim Paek and Eric Horvitz, I addressed the problem of belief updating in spoken dialog systems. We designed and performed a user study aimed at validating the scalability of a Dynamic Bayesian Network approach for updating the system beliefs throughout a conversation. |
| - |
Summer Internship, SSRP program, NASA Ames/RIACS, 2002 With Gregory Aist, I developed a dialog management component for the initial prototype of the Intelligent Procedure Assistant (IPA) system. The IPA is a multi-modal spoken dialog system aimed at providing guidance and support to astronauts on the International Space Station during the execution of large procedural tasks. |
| - |
Teaching Assistant, 15-211 Data Structures and Algorithms, Spring 2003 Prepared and delivered weekly recitations; held office hours; contributed to the design and grading of lab assignments and exams. |
| - |
Teaching Assistant, 15-381 Artificial Intelligence, Fall 2003 Held office hours; delivered one lecture; contributed to the design and grading of lab assignments and exams. |
| - | Student Liaison for the Special Interest Group on Discourse and Dialogue (SIGdial), 2004-present |
| - | Scientific review committee member for SLT-2006, NAACL-HLT 2007, ICASSP-2007, and the Journal of Dialogue Systems. |
| - | Advisory committee member for the 2006 Young Researchers’ Roundtable on Spoken Dialog Systems |
| - | Organizer for the 1st Young Researchers’ Workshop on Spoken Dialog Systems (2005) |
| - | Organizer for the Dialogs on Dialogs Student Reading Group at Carnegie Mellon University |
| - |
Admissions committee member in the Computer Science Department at Carnegie Mellon University, 2004 and 2005 |
| - |
Student member of AAAI, IEEE, ACL and ISCA |