RESEARCH AREAS:

DIALOGUE INTERACTION in INTERACTIVE STORIES & GAMES : Current projects include Character Creator and Spyfeet. Character Creator focuses on increasing the creativity of authors of interactive stories by providing tools that automatically generate linguistic variations of utterances specific to a character that the author specifies. We are exploring both rule-based and corpus-based approaches to specify parameters for a character's linguistic style. Spyfeet is an outdoor augmented-reality mobile game whose long term goal is the integration of expressive language generation with the structure of narrative role-playing games in order to solve the 'authoring bottleneck' for interactive stories and games. Our immediate goal is to develop a prototype system that makes exercise fun, and to understand how narrative structures and role-playing components can increase a user's self-efficacy for exercise.

MULTIMODAL HUMAN COMPUTER INTERACTION: As we move towards mobile and pervasive computing, techniques for speech-enabled and dialogue-based multi-modal interaction promise to be critical. However many open research problems still remain before speech-enabled multi-modal interfaces can be truly usable for a wide variety of applications. The NSF-Funded SKIPPER project provides pedestrian directions from a mobile phone running the Android operating system. Our research is focusing on user adaptation and entrainment, use of politeness in SKIPPER dialogue strategies, and automatic landmark salience identification, My work on the MATCH system while at AT&T focused on providing users with information on restaurant and entertainment options, as well as directions, was focused on user-adaptive information presentation in a multimodal environment. This work is summarized in an article in a special issue of the journal Cognitive Science .

RECOGNITION AND GENERATION OF PERSONALITY, LINGUISTIC STYLE AND POLITENESS: Publications .
There are three strands of this work, politeness, personality and individual preferences for the system style when generating responses. Algorithms for generating and recognizing these types of individual differences are applicable to agents in dialogue systems, computer games, interactive drama systems, serious games, and virtual reality tutorial applications. The next generation of games such as Facade should be able to benefit from such algorithms.

One strand of our work examines the applications of "Politeness: Some Universals in Language Usage" by Brown and Levinson to algorithms for dialogue or interactive entertainment agents that talk. The theory contributes directly to a set of algorithms for expressing agent personality via communicative action selection. These algorithms were implemented in agents in a virtual theatre called VIVA in Mitsubishi's Diamond Park and in Sheffield's Virtual Reality Lab . Interesting and unexpected interactions emerge when politeness strategies are combined with Cahn's variations in expressive style of synthesized speech. Here's a demo . The original politeness generator was written up in the Dallas Morning News and the Newark Star Ledger. A second strand is work on Personality Generation and Recognition, in collaboration with Francois Mairesse. Here's a demo . We are examining personality recognition in texts and dialogues, out-of-domain adaptation of personality models, and personality generation in dialogue, with our new generator PERSONAGE. A third strand is work on customizing dialogue system output generation to individual differences using the SPaRKy generator. We have been able to show that automatic training methods not only support adaption to new domains, but also to individual preferences in content planning and structuring and sentence planning operations. Here's some software and resources for download .

SPOKEN LANGUAGE GENERATION FOR DIALOGUE SYSTEMS: Publications .
My thesis used corpus analysis and dialogue simulation techniques with cognitive models of the hearer to investigate constraints on content selection in dialogue. The dialogue simulation experiments focused on the effect of different user simulations, and different task complexities, on the communicative effectiveness of dialogue strategies that include mutually known (hence redundant) information. In this work, I first proposed that dialogue strategies could be stochastically optimized with machine learning techniques such as reinforcement learning. Follow-on work at AT\&T on the ELVIS system (EmaiL Voice Interactive System) provided the first empirical results demonstrating that reinforcement learning could be used to optimize dialogue management and spoken language generation in dialogue systems, by using the feedback from a human user to calculate a reward function. I gave a keynote address at AAAI 1997 on our first reinforcement learning results, published at ACL in 1998 . Here are some sample ELVIS dialogues . This approach led to a great deal of subsequent work, including collaborations with Michael Kearns, Satinder Singh and Diane Litman applying reinforcement learning to the NJFun System. See below on Reinforcement Learning .

In joint work with Owen Rambow, Amanda Stent and Rashmi Prasad, we applied similar ideas to the development of two different trainable sentence planners (SPoT, SPaRKy) for spoken language generation in dialogue, with an optimization technique in which sentence plans are first generated by a randomized sentence plan generator, and then ranked by a sentence plan ranker that is automatically trainable from human feedback.

A collaboration with Ryuichiro Higashinaka and Rashmi Prasad, supported by a grant from NTT Basic Research Labs, investigated methods to automatically learn a generation dictionary for spoken dialogue systems by mining webpages of user reviews. Summarized in ACM TSLP.

I have also investigated methods from decision theory to content planning for the MATCH multimodal dialogue system for tourist information, in collaboration with Johanna Moore and Steve Whittaker. This work led to an article in a special issue of the Cognitive Science Journal in honour of Prof. Aravind K. Joshi . This work was done with Michael Johnston and other members of the MATCH team at AT&T.

See also Lingistic Style, Politeness and Personality for generation methods for embodied agents with personality and politeness for interactive drama systems and dialogue applications.

REINFORCEMENT LEARNING IN SPOKEN DIALOGUE SYSTEMS: Reinforcement Learning Publications . In joint work with Shri Narayanan and Jeanne Fromer, we developed the first application of reinforcement learning to optimize dialogue strategy selection, by interacting with human users. The ELVIS system (EmaiL Voicemail Interactive System) was a spoken language interface that supports voice access to email and voicemail over the phone, and reinforcement learning for ELVIS was applied to initiative and information presentation dialogue strategies. JAIR Paper . These ideas were then further tested in a second system, the NJFun system, a spoken language interface that provides information about fun things to do in New Jersey. With Satinder Singh, Diane Litman, and Michael Kearns we conducted experiments with NJFun testing different initiative and confirmation dialogue strategies. Here are some sample NJFun dialogues .

PERFORMANCE MODELING AND EVALUATION OF SPOKEN DIALOGUE INTERFACES: Evaluation Publications .
I led evaluation efforts for DARPA Communicator , a multi-site, multi-million dollar DARPA program on mixed-initiative spoken dialogue systems. Our work on evaluation was based on work on PARADISE (PARAdigm for DIalogue System Evaluation) , a method for deriving an objective performance function for spoken dialogue systems. We investigated various aspects of fully automatic evaluation using fully automatic metrics extractable in real time so that the dialog system can adapt based on its assessment of its current performance. We have developed fully automatic evaluation modules for DARPA Communicator and for the How May I Help You system. We have applied similar techniques to identify and predict errors in spoken language understanding.

CENTERING THEORY IN DISCOURSE: Centering is an account of local coherence in discourse that attempts to predict which entities realized by an utterance are most salient, and how the salience of discourse entities changes as the discourse evolves. I started off my career at Hewlett Packard Labs in the HPNL group, where in collaboration with Susan Brennan and Carl Pollard, we developed the first computational implementation of centering theory as an application to the resolution of anaphora in natural language interfaces to databases. I have also applied centering to zero anaphors in Japanese and been interested in understanding the relationship between centering and given-new information in discourse (with Ellen Prince), between centering and human limits on attentional capacity, and centering and the global intentional structure of discourse. Centering Publications .

BOOKS
Marilyn A. Walker, Aravind K. Joshi, and Ellen F. Prince, editors. Centering Theory in Discourse . Oxford University Press, 1998.

THESIS
Marilyn Walker, Informational Redundancy and Resource Bounds in Dialogue . Ph.D. Computer and Information Science, University of Pennsylvania 1993.

EDITED COLLECTIONS
Guest Editor: Computer Speech and Language, Special Issue on Spoken Language Generation
Guest Editor: Computational Linguistics, Special Issue on Empirical Studies in Discourse

JOURNAL ARTICLES and BOOK CHAPTERS

Walker, M. and Anand, P and Abbott, R. and Tree, J.E.F. and Martell,C. and King, J. That's your evidence:? Classifying Stance in Online Political and Social Debate . Decision Support Sciences. 1-30. Elsevier. In Press. 2011

Francois Mairesse and Marilyn Walker. Controlling User Perceptions of Linguistic Style: Trainable Generation of Personality Traits. Computational Linguistics, 2011.

Michael Neff, Nicolaus Toothman}, Robeson Bowmani}, Jean E. Fox Tree and Marilyn A. Walker (2011). Don't Scratch: Self-adaptors Reflect Emotional Stability. Lecture Notes in Computer Science (LNCS) Springer Berlin/Heidelberg, vol. 6895. (paper and sample clips from the study are available at www.springerlink.com). 2011.

Francois Mairesse and Marilyn Walker. Towards Personality-Based User Adaptation: Psychologically Informed Stylistic Language Generation. . User Modeling and User-Adapted Interaction, 20:3, pages 227-278, 2010.

Michael Neff, Yingying Wang, Rob Abbott and Marilyn A. Walker (2010). Evaluating the Effect of Gesture and Language on Personality Perception in Conversational Agents . Lecture Notes in Computer Science (LNCS) Springer Berlin/Heidelberg, ISSN 0302-9743, vol. 4738, pp. 203-217. (paper and sample clips from the study are available at www.springerlink.com)

N. Bee, C. Pollock, E. Andre and M. Walker. Bossy or Wimpy: Expressing Social Dominance by Combining Gaze and Linguistic Behaviors. Lecture Notes in Computer Science (LNCS) Springer Berlin/Heidelberg, ISSN 0302-9743, vol. 4738, pp. 203-217. 2010.

Michael Neff, Yingying Wang, Rob Abbott and Marilyn A. Walker (2010). Evaluating the Effect of Gesture and Language on Personality Perception in Conversational Agents . Lecture Notes in Computer Science (LNCS) Springer Berlin/Heidelberg, ISSN 0302-9743, vol. 4738, pp. 203-217. (paper and sample clips from the study are available at www.springerlink.com)

Marilyn Walker, Amanda Stent, Francois Mairesse, Rashmi Prasad. Individual and Domain Adaptation in Sentence Planning for Dialogue. Journal of Artificial Intelligence Research, 2007.

Francois Mairesse, Marilyn Walker, Matthias Mehl and Roger Moore (2007) Using Linguistic Cues for the Automatic Recognition of Personality in Conversation and Text Journal of Artificial Intelligence Research, Vol 30, pp 457-501.

Ryuichiro Higashinaka, Marilyn Walker and Rashmi Prasad An Unsupervised Method for Learning Generation Dictionaries for Spoken Dialogue Systems by Mining User Reviews. Journal of ACM Transactions on Speech and Language Processing, 2007.

Pam Jordan and Marilyn Walker. Learning Content Selection Rules for Generating Object Descriptions in Dialogue. In Journal of Artificial Intelligence Research, Vol 24, pp. 157-194, 2005.

Marilyn Walker. Can We Talk? Methods for Evaluation and Training of Spoken Dialogue System (written version of invited keynote, LREC 2004). In Language Resources and Evaluation, Vol 39(1), pp. 65-75, Springer Netherlands, 2005.

Steve Whittaker and Marilyn Walker. Evaluating Dialogue Strategies in Multimodal Dialogue Systems. In W. Minker, D. Bühler and L. Dybkjaer, editors, Spoken Multimodal Human-Computer Dialogue in Mobile Environments. Kluwer Academic Publishers, 2004.

Marilyn Walker, S. Whittaker, A. Stent, P. Maloor, J. Moore, M. Johnston, G. Vasireddy. Generation and Evaluation of User Tailored Responses in Multimodal Dialogue. In Cognitive Science, Vol 28., Issue 5, September-October 2004, Rumelhart Prize Special Issue Honoring Aravind K. Joshi, pp. 811-840, 2004.

Marilyn Walker, Owen Rambow and Monica Rogati. Training a Sentence Planner for Spoken Dialogue Using Boosting Computer Speech and Language Special Issue on Spoken Language Generation , July 2002.

Marilyn Walker and Owen Rambow. Spoken Language Generation Computer Speech and Language Special Issue on Spoken Language Generation , July 2002.

Marilyn Walker, Irene Langkilde-Geary, Helen Wright Hastie, Jerry Wright, and Allen Gorin. Automatically Training A Problematic Dialogue Predictor for the HMIHY Spoken Dialogue System Journal of Artificial Intelligence Research, 2002.

Satinder Singh, Diane Litman, Michael Kearns and Marilyn Walker. Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System. Journal of Artificial Intelligence Research(JAIR), 2002.

Marilyn Walker. An Application of Reinforcement Learning to Dialogue Strategy Selection in a Spoken Dialogue System for Email . Journal of Artificial Intelligence Research, JAIR, Vol 12., pp. 387-416, 2000.

Marilyn A. Walker, Candace. A. Kamm and Diane J. Litman. Towards Developing General Models of Usability with PARADISE . Natural Language Engineering, 2000.

Marilyn A. Walker. Toward a Model of the Interaction of Centering with Global Discourse Structure. . Verbum, 2000.

Marilyn Walker, Diane J. Litman, Candace A. Kamm and Alicia Abella. Evaluating Spoken Dialogue Agents with {PARADISE}: Two Case Studies . In Computer Speech and Language, 12-3, 1998.

Marilyn A. Walker. Centering, anaphora resolution, and discourse structure. In Marilyn A. Walker, Aravind K. Joshi, and Ellen F. Prince, editors, Centering in Discourse. Oxford University Press, 1998.

Marilyn A. Walker, Aravind K. Joshi, and Ellen F. Prince. Centering in naturally-occurring discourse: An overview. In Marilyn A. Walker, Aravind K. Joshi, and Ellen F. Prince, editors, Centering in Discourse. Oxford University Press, 1998.

Candace A. Kamm, Marilyn A. Walker, and Larry R. Rabiner, The role of speech processing in human-computer intelligent communication. Speech Communication, 1997.

Marilyn A. Walker and Johanna D. Moore. Empirical Studies in Discourse. Computational Linguistics, 20-2, 1997.

Marilyn A. Walker. The effect of resource limits and task complexity on collaborative planning in dialogue. Artificial Intelligence Journal, 85:1-2, 1996.

Marilyn A. Walker. Inferring Acceptance and Rejection in Dialogue by Default Rules of Inference. Language and Speech, 39-2, 1996.

Marilyn A. Walker. Limited attention and discourse structure. Computational Linguistics, 22-2, 1996.

Marilyn A. Walker and Ellen F. Prince. A bilateral approach to givenness: a Hearer-Status algorithm and a Centering algorithm. In Gundel, J. and Fretheim, T., eds. Reference accessibility. 1995.

Marilyn A. Walker. Testing collaborative strategies by computational simulation: Cognitive and task effects . Knowledge Based Systems, 1995.

Marilyn A. Walker, Masayo Iida, and Sharon Cote. Japanese Discourse and the Process of Centering. Computational Linguistics, 20-2, 1994.

REFEREED CONFERENCE PAPERS (excludes workshop papers)

Marilyn A. Walker, Ricky Grant, Grace Lin, Jennifer Sawyer, Noah Wardrip-Fruin and Michael Buell. Perceived or Not Perceived: Film Character Models for Expressive NLG. In Interactive Storytelling: Fourth Joint Conference on Interactive Digital Storytelling, ICIDS 2011. oral presentation.

Grace I. Lin and Marilyn A.Walker. (2011). All the World’s a Stage: Learning Character Models from Film. In Proceedings of the Conference on Artificial Intelligence and Digital Entertainment. AAAI Press. 2011. accepted as long paper.

Kris Liu and Natalia Blackwell and Jean E. Fox Tree and Marilyn A. Walker. A Hula Hoop almost Hit Me!:Running a Map Task in the Wild to Study Conversational Alignment. Poster presented at the 21st annual meeting of the Society for Text and Discourse. Poitiers, France, July 11-13.

Reed, A., Samuel B., Sullivan A., Grant, R., Grow A., Lazaro J., Mahal J., Sri Kurniawan, Marilyn A. Walker, Noah Wardrip-Fruin. A Step Towards the Future of Role-Playing Games: The SpyFeet Mobile RPG Project. In Proceedings of the Conference on Artificial Intelligence and Digital Entertainment. AAAI Press. 2011.

Aaron A. Reed, Ben Samuel, Anne Sullivan, Ricky Grant, April Grow, Justin Lazaro, Jennifer Mahal, Sri Kurniawan, Marilyn A. Walker, Noah Wardrip-Fruin. SpyFeet: An Exercise RPG. In Proceedings of the Sixth International Conference on the Foundations of Digital Games. ACM. 2011.

Marilyn A. Walker. Dynamic adaptation in dialog systems. In Proceedings of the 11th Annual Meeting of the Special Interest Group in Discourse and Dialogue, Association for Computational Linguistics. 2010.

Marilyn A.Walker. Endowing Virtual Characters with Expressive Conversational Skills. Intelligent Virtual Agents. Proceedings of the Intelligent Virtual Agents Conference.. 2009 Springer.

Khosmood, F. and Walker, M. Grapevine: a gossip generation system In Proceedings of the Fifth International Conference on the Foundations of Digital Games. p. 92--99. 2010. ACM.

Joseph Polifroni and Marilyn Walker (2008). Intensional Summaries as Cooperative Responses in Dialogue: Automation and Evaluation " In Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics (ACL), Columbus, June 2008.

François Mairesse and Marilyn Walker (2008). Trainable Generation of Big-Five Personality Styles through Data-driven Parameter Estimation." In Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics (ACL), Columbus, June 2008.

Gupta, S., Walker, M.A., Romano, D.M.(2008). POLLy: A Conversational System that uses a Shared, Representation to Generate Action and Social Language." IJCNLP 2008, The Third International Joint Conference on Natural Language Processing, Hyderabad, India, January 7-12, 2008.

Gupta, S., Walker, M.A., Romano, D.M.(2007). How Rude are You?: Evaluating Politeness and Affect in Interaction. Affective Computing & Intelligent Interaction (ACII-2007), 12th September 2007, Calouste Gulbenkian Foundation, Lisbon, Portugal. Lecture Notes in Computer Science (LNCS) Springer Berlin/Heidelberg, ISSN 0302-9743, vol. 4738, pp. 203-217.

François Mairesse and Marilyn Walker (2007). PERSONAGE: Personality Generation for Dialogue. In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics (ACL), Prague, June 2007.

Joseph Polifroni and Marilyn Walker. An Analysis of Automatic Content Selection Algorithms for Spoken Dialogue System Summaries. In IEEE/ACL, Aruba 2006.

Ryuichiro Higashinaka, Rashmi Prasad and Marilyn Walker. Learning to Generate Naturalistic Utterances Using Reviews in Spoken Dialogue Systems. In COLING-ACL, Australia 2006.

François Mairesse and Marilyn Walker. Words Mark the Nerds: Computational Models of Personality Recognition through Language. In Proceedings of the 28th Annual Conference of the Cognitive Science Society (CogSci 2006), Vancouver, July 2006.

François Mairesse and Marilyn Walker. Automatic Recognition of Personality in Conversation. In Proceedings of HLT-NAACL 2006, New York City, June 2006.

Emma Barker, Ryuichiro Higashinaka, François Mairesse, Robert Gaizauskas, Marilyn Walker and Jonathan Foster. Simulating Cub Reporter Dialogues: The collection of naturalistic human-human dialogues for information access to text archives. In Proceedings of the International Conference on Language Resources and Evaluation (LREC 2006), Genoa, May 2006.

Joseph Polifroni and Marilyn Walker. Learning Database Content for Spoken Dialogue System Design. In Proceedings of the International Conference on Language Resources and Evaluation (LREC 2006), Genoa, May 2006.

Ryuichiro Higashinaka, Rashmi Prasad and Marilyn Walker. Augmenting Variation of System Utterances using Corpora in Spoken Dialogue Systems. In IEEE Automatic Speech Recognition and Understanding (ASRU), Puerto Rico, 2005 .

Francois Mairesse and Marilyn Walker. Learning to Personalize Spoken Generation for Dialogue Systems. In Proceedings of Interspeech'2005 - Eurospeech: 9th European Conference on Speech Communication and Technology, pages 1881-1884, Lisbon, September 2005.

Amanda Stent, Rashmi Prasad and Marilyn Walker. Trainble Sentence Planning for Complex Information Presentation in Spoken Dialog Systems. In  42nd Annual Meeting of the Association for Computational Linguistics 2004, Barcelona, 2004.

Marilyn Walker, Rashmi Prasad and Amanda Stent. A Trainable Generator for Recommendations in Multimodal Dialog. In EUROSPEECH: European Conference on Speech Processing pages 1697-1701, Geneva, 2003.

Stephen Whittaker, Marilyn Walker and Preetam Maloor. Should I Tell All? An Experiment On Conciseness in Spoken Dialogue. In EUROSPEECH: European Conference on Speech Processing pages 1685-1689, Geneva, 2003.

Marilyn Walker, Alex Rudnicky, John Aberdeen , Elizabeth Bratt, John Garofolo, Helen Hastie, Audrey Le, Bryan Pellom, Alex Potamianos, Rebecca Passonneau, Rashmi Prasad, Salim Roukos, Gregory Sanders, Stephanie Seneff and David Stallard. DARPA Communicator Evaluation: Progress from 2000 to 2001. In ICSLP 2002.

Marilyn Walker, Alex Rudnicky, Rashmi Prasad, John Aberdeen , Elizabeth Bratt, John Garofolo, Helen Hastie, Audrey Le , Bryan Pellom, Alex Potamianos, Rebecca Passonneau, Salim Roukos, Gregory Sanders, Stephanie Seneff, David Stallard. DARPA Communicator: Cross-System Results for the 2001 Evaluation . In ICSLP 2002.

J. Chen, S. Bangalore, O. Rambow and M. Walker,  ``Towards Automatic Generation of Natural Language Generation Systems'',  International Conference on Computational Linguistics (COLING 2002), Taipei, Taiwan, 2002.

Amanda Stent, Marilyn Walker, Steve Whittaker and Preetam Maloor. User-Tailored Generation for Spoken Dialogue: An Experiment In ICSLP, 2002.

Whittaker, S., Walker, M., and Moore, J.. Fish or Fowl: A Wizard of Oz Evaluation of Dialogue Strategies in the Restaurant Domain . Language Resources and Evaluation Conference. 2002.

M Walker, S. Whittaker, A. Stent, P. Maloor, J. Moore, M. Johnston, G. Vasireddy. Speech plans: generating evaluative responses in spoken dialogue. International Natural Language Generation Conference.

Johnston, M., Ehlen, P., Bangalore, S., Walker., M., Stent, A., Maloor, P., and Whittaker, S. (2002). MATCH: An Architecture for Multimodal Dialogue Systems. In Meeting of the Association for Computational Linguistics , 2002.

Helen Wright Hastie, Rashmi Prasad and Marilyn A. Walker, What's the Trouble: Automatically Identifying Problematic Dialogs in DARPA Communicator Dialog Systems In Meeting of the Association of Computational Linguistics , 2002.

Helen Wright Hastie, Marilyn A. Walker and Rashmi Prasad, Automatic Evaluation: Using a DATE Dialogue Act Tagger for User Satisfaction and Task Completion Prediction In Language Resources and Evaluation Conference , 2002.

Marilyn A. Walker, Rebecca Passonneau and Julie E. Boland Quantitative and Qualitative Evaluation of Darpa Communicator Spoken Dialogue Systems In Meeting of the Association of Computational Linguistics , 2001.

Monica Rogati, Marilyn A. Walker and Owen Rambow. Training a Sentence Planner for Spoken Dialog: The Impact of Syntactic and Planning Features In EUROSPEECH: European Conference on Speech Processing , 2001. , 2001.

M. Walker, J. Aberdeen, J. Boland, E. Bratt, J. Garofolo, L. Hirschman, A. Le, S. Lee, S. Narayanan, K. Papineni, B. Pellom, J. Polifroni, A. Potamianos, P. Prabhu, A. Rudnicky, G. Sanders, S. Seneff, D. Stallard, S. Whittaker. DARPA Communicator Dialog Travel Planning Systems: The June 2000 Data Collection In EUROSPEECH: European Conference on Speech Processing , 2001.

M. Rahim, G. Di Fabbrizio, C. Kamm, M. Walker, A. Pokrovsky, P. Ruscitti, E. Levin, S. Lee, A. Syrdal, K. Schlosser. VOICE-IF: A MIXED-INITIATIVE SPOKEN DIALOGUE SYSTEM FOR AT&T CONFERENCE SERVICES In EUROSPEECH: European Conference on Speech Processing , 2001.

Marilyn A. Walker and Rebecca Passonneau. DATE: A Dialogue Act Tagging Scheme for Evaluation of Spoken Dialogue Systems. In Human Language Technology Conference , San Diego, March, 2001.

Marilyn A. Walker, Owen Rambow and Monica Rogati. SPoT: A Trainable Sentence Planner In North American Meeting of the Association of Computational Linguistics , 2001.

Owen Rambow, Monica Rogati and Marilyn A. Walker. Evaluating a Trainable Sentence Planner for a Spoken Dialogue Travel System In Meeting of the Association of Computational Linguistics , 2001.

Rambow, Owen; Bangalore, Srinivas; and Walker, Marilyn, 2001. Natural Language Generation in Dialog Systems. In Proceedings of the First International Conference on Human Language Technology Research (HLT2001), San Diego, USA.[pdf]

Dutton, D., Chu, S., Hubbell, J., Walker, M., Narayanan, S. (April 2001) Just (All) the Facts, Ma'am, CHI 2001, Seattle,WA.

Dutton, D., Chu, S., Hubbell, J., Walker, M., Narayanan, S. (March 2001). Amount of Information Presented in a Complex List: Effects on User Performance, Human Language Technology Conference, HLT 2001, San Diego, CA.

Pamela Jordan and Marilyn Walker. Learning Attribute Selections for Non-Pronominal Expressions In the Proceedings of ACL 2000, Hong Kong, October 2000.

Levin, E., Narayanan, S., Pieraccini, R., Biatov, K., Bocchieri, E., DiFabbrizio, G., Eckert, W., Lee, S., Pokrovsky, A., Rahim, M., Ruscitti, P. and Walker, M. 2000 The AT&T DARPA Communicator Mixed-Initiative Spoken Dialog System. In Proceedings of the International Conference on Spoken Language Processing . 2000.

Marilyn A. Walker, Jerry Wright, Irene Langkilde. Using Natural Language Processing and Discourse Features to Identify Understanding Errors in a Spoken Dialogue System. In Proceedings of the Seventeenth International Conference on Machine Learning , 2000.

Marilyn A. Walker, Irene Langkilde , Jerry Wright, Allen Gorin and Diane Litman. Learning to Predict Problematic Situations in a Spoken Dialogue System: Experiments with How May I Help You? In North American Meeting of the Association of Computational Linguistics , 2000.

Diane J. Litman, Michael S. Kearns, Satinder Singh, and Marilyn A. Walker. Automatic Optimization of Dialogue Management. In Proceedings of COLING 2000.

Satinder Singh, Michael S. Kearns, Diane J. Litman, and Marilyn A. Walker. Empirical Evaluation of a Reinforcement Learning Spoken Dialogue System. In Proceedings of AAAI 2000.

Kary Myers, Michael S. Kearns, Satinder Singh, Marilyn A. Walker. A Boosting Approach to Topic Spotting on SubDialogues. In Proceedings of the Seventeenth International Conference on Machine Learning , 2000.

Marilyn A. Walker, Lynette Hirschman and John Aberdeen. Evaluation For Darpa Communicator Spoken Dialogue Systems In Language Resources and Evaluation Conference, LREC , 2000.

Marilyn A. Walker, Candace Kamm and Julie Boland. Developing And Testing General Models Of Spoken Dialogue System Perfor mance In Language Resources and Evaluation Conference, LREC , 2000.

Marilyn A. Walker, Julie Boland and Candace Kamm. The Utility of Elapsed Time as a Usability Metric for Spoken Dialogue Systems In ASRU99 , 1999.

Irene Langkilde, Marilyn A. Walker, Jerry Wright, Allen Gorin and Diane Litman. Automatic Prediction of Problematic Human-Computer Dialogues in How May I Help You? In ASRU99 , 1999.

Satinder Singh, Michael S. Kearns, Diane J. Litman, and Marilyn A. Walker. Reinforcement Learning for Spoken Dialogue Systems. In Proceedings of NIPS*99.

Diane Litman, Marilyn A. Walker and Michael Kearns. Automatic Detection of Poor Speech Recognition at the Dialogue Level" In Proceedings of the 37th Annual Meeting of the Association of Computational Linguistics , ACL99, 1999.

Candace Kamm, Marilyn A. Walker, and Diane Litman. "Evaluating Spoken Language Systems" In Proceedings of American Voice Input/Output Society, , AVIOS, 1999. Recipient of a Best Paper Award

Candace Kamm, Diane Litman, Marilyn A. Walker". From Novice to Expert: The Effect of Tutorials on User Expertise with Spoken Dialogue Systems" In Proceedings of the International Conference on Spoken Language Processing , ICSLP98, 1998.

Diane Litman, Shimei Pan and Marilyn Walker. Evaluating Response Strategies in a Web-Based Spoken Dialogue Agent. In Proceedings of ACL/COLING 98 , 1998.

Marilyn Walker, Jeanne Fromer, Shrikanth Narayanan. Learning Optimal Dialogue Strategies: A Case Study of a Spoken Dialogue Agent for Email. In Proceedings of ACL/COLING 98 , 1998.

Marilyn Walker, Jeanne Fromer, Giuseppe Di Fabbrizio, Craig Mestel and Don Hindle. What Can I Say? . In Proceedings of the Conference on Human Factors in Computing Systems , CHI98, 1997.

Marilyn Walker, Don Hindle, Jeanne Fromer, Giuseppe Di Fabbrizio and Craig Mestel. Evaluating Competing Agent Strategies for a Voice Email Agent . In Proceedings of the 5th European Conference on Speech Technology and Communication , EUROSPEECH 97, 1997.

Marilyn A. Walker, Janet E. Cahn and Stephen J. Whittaker. Improvising Linguistic Style: Social and Affective Bases for Agent Personality . In Proceedings of the Conference on Autonomous Agents, AGENTS97, 1997. This work was also written up in the Dallas Morning News and the Newark Star Ledger.

Marilyn Walker, Diane Litman, Candace Kamm and Alicia Abella. PARADISE: A Framework for Evaluating Spoken Dialogue Agents . PDF In Proceedings of the 35th Annual Meeting of the Association of Computational Linguistics , ACL 97, 1997.

Kamm, C. and Walker, M. A., Design and evaluation of spoken dialog systems. Proc. 1997 IEEE Workshop on Speech Recognition and Understanding, 1997.

Marilyn A. Walker and Pamela Jordan. Design-world: A testbed of communicative action and resource limits. Special Issue of the SIGART Bulletin on AI Education, 1995.

Pamela Jordan and Marilyn A. Walker. Deciding to Remind During Collaborative Problem Solving: Empirical Evidence for Agent Strategies . In Proceedings ofthe Conference of the American Association Artificial Intelligence, AAAI96, 1996.

Marilyn A. Walker. Experimentally evaluating communicative strategies: The effect of the task . In Proceedings of the Conference of the American Association Artificial Intelligence, AAAI94, 1994.

Marilyn A. Walker. Discourse and Deliberation: Testing a collaborative strategy . In 15th International Conference on Computational Linguistics: COLING 94, 1994.

Marilyn A. Walker and Owen Rambow. The Role of Cognitive Modeling in Communicative Intentions. In The 7th International Conference on Natural Language Generation, 1994.

Marilyn A. Walker. Rejection by Implicature . In Proceedings of the 20th Meeting of the Berkeley Linguistics Society, 1994.

Marilyn A. Walker. 1993. When given information is accented: Repetition, paraphrase and inference in dialogue . In Proceedings of Linguistics Society of America Annual Meeting

Ellen F. Prince and Marilyn A. Walker. 1993. A bilateral approach to givenness: a hearer-status algorithm and a centering algorithm. In 4th International Pragmatics Conference.

Marilyn A. Walker. Redundant affirmation, deliberation and discourse . In Penn Review of Linguistics, volume 17, 1993.

Marilyn A. Walker. 1992. Redundancy in collaborative dialogue . In Fourteenth International Conference on Computational Linguistics,COLING, Nantes.

Marilyn A. Walker, Andrew L. Nelson, and Phil Stenton. 1992. A Case Study of Natural Language Customisation: The practical effects of world knowledge . In Fourteenth International Conference on Computational Linguistics, COLING, Nantes.

Marilyn A. Walker, Masayo Iida, and Sharon Cote. 1990. Centering in Japanese Discourse . In COLING90: Proc. 13th International Conference on Computational Linguistics, Helsinki.

Marilyn A. Walker and Steve Whittaker. 1990. Mixed Initiative in Dialogue: An investigation into discourse segmentation . In Proc. 28th Annual Meeting of the ACL.

Marilyn A. Walker. 1989. Evaluating Discourse Processing Algorithms . In Proc. 27th Annual Meeting of the Association of Computational Linguistics.

Marilyn A. Walker. 1989. Natural Language in a Desk-Top Environment . In Proceedings of HCI89, 3rd International Conference on Human-Computer Interaction, Boston, Mass, pages 502-509.

Susan E. Brennan, Marilyn  Walker Friedman and Carl J. Pollard. 1987. A Centering Approach to Pronouns . In Proc. 25th Annual Meeting of the ACL.

SELECTED WORKSHOP PAPERS

Marilyn A. Walker, Ricky Grant, Grace Lin, Jennifer Sawyer, Noah Wardrip-Fruin and Michael Buell. Murder in the Arboretum: Comparing Character Models to Personality Models. In 4th International Workshop on Intelligent Narrative Technologies. AAAI Press.

Rob Abbott and Marilyn A. Walker and Pranav Anand and Jean E. Fox Tree and Robeson Bowmani and Joseph King. (2011). How can you say such things?!?: Recognizing Disagreement in Informal Political Argument. ACL HLT Workshop on Language in Social Media. Association for Computational Linguistics.

Anand, P. and Walker, M. and Abbott, R. and Fox Tree, J.E. and Bowmani, R. and Minor, M. Cats Rule and Dogs Drool!: Classifying Stance in Online Debate. Best Paper Award . ACL HLT Workshop on Sentiment and Subjectivity.

Gupta, S., Walker, M.A., Romano, D.M.(2008). Using a Shared Representation to Generate Action and Social Language for a Virtual Dialogue Environment. AAAI 2008, Spring Symposium on Emotion, Personality and Social Behavior, Stanford University in March 26-28, 2008.

Gupta, S., Walker, M.A., Romano, D.M.(2007). Generating Politeness in Task Based Interaction: An Evaluation of the Effect of Linguistic Form and Culture. ENLG'07, 11th European Workshop on Natural Language Generation,Schloss Dagstuhl, Germany, 17-20 June 2007. (accepted for publication)

Marilyn Walker. Information and Deliberation in Discourse . In Workshop on Intentionality and Structure in Discourse , 1995.

Steve Whittaker and Marilyn Walker. 1991. Towards a theory of multimodal interaction . Proceedings of the AAAI Symposium on Multimodal Interaction.

Marilyn Walker and Steve Whittaker. 1989. When Natural Language is better than Menus: A field study . Technical Report HPL-BRC-TR-89-020, HP Laboratories, Bristol, England.

PATENTS AWARDED and FILED