people

Amanda J. Stent

Stent, Amanda J.
180 Park Ave - Building 103
Florham Park, NJ
http://www.amandastent.com
Subject matter expert in dialog systems, natural language generation, speech processing

My main research topic is natural language generation in interactive systems:  that is, designing algorithms that enable computer systems to produce more helpful, targeted and informative presentations in the context of an ongoing spoken, textual or multimodal interaction.  I work in all stages of the natural language generation pipeline, from content selection (deciding "what to say") through sentence planning and surface realization (deciding "how to say it"). 

I am also interested in adaptation in dialog systems.  For example, I have studied how discourse context can be used to improve natural language generation, how knowledge of the user's location can improve language modeling, and how user models can be used to improve information presentations.

Interactive systems come in many types, from speech-input speech-output dialog systems through to multimodal systems that support human-human communication.  I have also worked on assistive technology, focusing on speech-driven applications for people who are blind or have low vision, and on tools to help people maintain their privacy online.

I am vice president of the Special Interest Group on Discourse and Dialogue (SIGdial) and a rotating editor for the journal Dialogue and Discourse.  I also am the scheduler for the DiSpeLL talk series at AT&T Research -- if you are in the New York/New Jersey area, and would like to visit us to give a talk about dialog, speech, language or learning, please contact me.

Prior to coming to AT&T Research, I was a faculty member at Stony Brook University.  Together with a colleague from Stony Brook, I am co-author of the book "The Princess at the Keyboard:  Why Girls Should Become Computer Scientists".

Projects
Assistive Technology, At AT&T Labs - Research, we apply our speech, language and media technologies to give people with disabilities more independence, privacy and autonomy.

Connecting Your World, The need to be connected is greater than ever, and AT&T Researchers are creating new ways for people to connect with one another and with their environments, whether it's their home, office, or car.

Speech Mashup, The AT&T speech mashup is a web service that implements speech tasks for web applications, enabling users of smart phones and other devices to use and hear voice communications.

Patents

Systems And Methods For Creating And Using Geo-Centric Language Models, August 28, 2012
System And Method For Referring To Entities In A Discourse Domain, May 8, 2012

SPaRKy 2.0

SPaRKy 2.0
Download of the SPaRKy 2.0 sentence planner  index.html  (3k)

jsparkyv2.0.tar
  jsparkyv2.0.tar.gz  (1773k)


Publications

iWalk: A lightweight navigation system for low-vision users
Amanda Stent, Shiri Azenkot, Ben Stern
Proceedings of ASSETS,  2010.  [PDF]  [BIB]

EPG: Speech access to program guides for people with disabilities
Michael Johnston, Amanda Stent
Proceedings of ASSETS,  2010.  [PDF]  [BIB]

iTag: A personalized blog tagger
Michael Hart, Robert Johnson, Amanda Stent
Proceedings of RecSys,  2009.  [PDF]  [BIB]

Usable privacy controls for blogs
Michael Hart, Claude Castille, Robert Johnson, Amanda Stent
Proceedings of the Symposium on Social Intelligence and Networking at SocialCom,  2009.  [PDF]  [BIB]

TechWriter: An evolving system for writing assistance for advanced learners of English
Diane Napolitano, Amanda Stent
CALICO Journal,  v26,  #3,  pp 611-625,  2009.  [PDF]  [BIB]

Predicting concept types in user corrections in dialog
Svetlana Stoyanchev, Amanda Stent
Proceedings of the Workshop on Semantic Representation of Spoken Language at the Meeting of the European Chapter of the Association for Computational Linguistics (EACL),  2009.  [PDF]  [BIB]

Lexical and syntactic adaptation and their impact in deployed spoken dialog systems
Svetlana Stoyanchev, Amanda Stent
Proceedings of the Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL),  2009.  [PDF]  [BIB]

Incremental parsing models for dialog task structure
Srinivas Bangalore, Amanda Stent
Proceedings of the Meeting of the European Chapter of the Association for Computational Linguistics (EACL),  2009.  [PDF]  [BIB]

Geo-centric language models for local business voice search
Amanda Stent, Ilija Zeljkovic, Diamantino Caseiro, Jay Wilpon
Proceedings of the Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL),  2009.  [PDF]  [BIB]

Evaluating automatic extraction of rules for sentence plan construction
Amanda Stent, Martin Molina
Proceedings of SIGdial,  2009.  [PDF]  [BIB]

Determining the position of adverbial phrases in English
Huayan Zhong, Amanda Stent
Proceedings of the Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL),  2009.  [PDF]  [BIB]

Concept form adaptation in human-computer dialog
Svetlana Stoyanchev, Amanda Stent
Proceedings of SIGdial,  2009.  [PDF]  [BIB]

An analysis of user behavior following speech recognition errors in the Communicator corpus
Svetlana Stoyanchev, Amanda Stent
Proceedings of Corpus Linguistics,  2009.  [BIB]

Where do the words come from? Learning models for word choice and ordering from spoken dialog corpora
Amanda Stent, Srinivas Bangalore, Giuseppe Di Fabbrizio
Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP),  2008.  [PDF]  [BIB]

Trainable speaker-based referring expression generation
Giuseppe Di Fabbrizio, Amanda Stent, Srinivas Bangalore
Proceedings of the Conference on Natural Language Learning (CONLL),  2008.  [PDF]  [BIB]

Towards one world web with HearSay3
Yevgen Borodin, Jeffrey Bigham, I. V. Ramakrishnan, Amanda Stent
Proceedings of the International Cross-Disciplinary Conference on Web Accessibility (W4A),  2008.  [PDF]  [BIB]

Statistical shared plan-based dialog management
Amanda Stent, Srinivas Bangalore
Proceedings of the International Conference on Spoken Language Processing (ICSLP),  2008.  [PDF]  [BIB]

Referring expression generation using speaker-based attribute selection and trainable realization (ATT-REG)
Giuseppe Di Fabbrizio, Amanda Stent, Srinivas Bangalore
Proceedings of the International Natural Language Generation Conference (INLG),  2008.  [PDF]  [BIB]

Learning the structure of task-driven human-human dialog
Srinivas Bangalore, Giuseppe Di Fabbrizio, Amanda Stent
IEEE Transactions of Audio, Speech, and Language Processing special issue on New Approaches to Statistical Speech and Text Processing,  v16,  #7,  pp 1249-1259,  2008.  [PDF]  [BIB]

Adapting speaking after evidence of misrecognition: Local and global hyperarticulation
Amanda Stent, Marie Huffman, Susan Brennan
Speech Communication,  v50,  #3,  pp 163-178,  2008.  [PDF]  [BIB]

The HearSay non-visual web browser
Yevgen Borodin, Jalal Mahmud, I. V. Ramakrishnan, Amanda Stent
Proceedings of the International Cross-Disciplinary Conference on Web Accessibility (W4A),  2007.  [PDF]  [BIB]

TechWriter: An individualized approach to writing assistance and improvement
Diane Napolitano, Amanda Stent
Proceedings of the CALICO Workshop on Automatic Analysis of Learner Language,  2007.  [BIB]

RavenCalendar: A multimodal dialog system for managing a personal calendar
Svetlana Stenchikova, Basia Mucha, Sarah Hoffman, Amanda Stent
Proceedings of NAACL/HLT,  2007.  [PDF]  [BIB]

More content -- less control: Access control in the Web 2.0
Robert Johnson, Michael Hart, Amanda Stent
Proceedings of the Workshop on Web 2.0 Security and Privacy at the IEEE Symposium on Security and Privacy,  2007.  [PDF]  [BIB]

Measuring adaptation between dialogs
Svetlana Stenchikova, Amanda Stent
Proceedings of SIGdial,  2007.  [PDF]  [BIB]

Individual and domain adaptation in sentence planning for dialogue
Marilyn Walker, Amanda Stent, Francois Mairesse, Rashmi Prasad
Journal of Artificial Intelligence Research,  v30,  pp 413-456,  2007.  [PDF]  [BIB]

A general approach for partitioning web page content based on geometric and style information
Hui Guo, Jalal Mahmud, Yevgen Borodin, Amanda Stent, I. V. Ramakrishnan
Proceedings of the International Conference on Document Analysis and Recognition (ICDAR),  2007.  [PDF]  [BIB]

Unheralded pronouns and theories of pronoun resolution
Richard Gerrig, Sid Horton, Amanda Stent
Proceedings of the 16th Annual Meeting of the Society for Text and Discourse,  2006.  [BIB]

Towards learning to converse: Structuring task-oriented human-human dialogs
Srinivas Bangalore, Giuseppe Di Fabbrizio, Amanda Stent
Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP),  2006.  [PDF]  [BIB]

Taxonomy Based Data Extraction from Multi-item Web Pages
Hui Guo, Amanda Stent
Proceedings of Workshop on Web Content Mining with Human Language Technologies at the International Semantic Web Conference (ISWC),  2006.  [PDF]  [BIB]

Modeling the dative alternation with automatically extracted features
Huayan Zhong, Amanda Stent, Mary Swift
Proceedings of the Workshop on Statistical and Empirical Approaches for Spoken Dialog Systems at AAAI,  2006.  [PDF]  [BIB]

Learning the structure of task-driven human-human dialogs
Srinivas Bangalore, Giuseppe Di Fabbrizio, Amanda Stent
Proceedings of COLING/ACL,  2006.  [PDF]  [BIB]

Dialog systems for surveys: The Rate-a-Course system
Amanda Stent, Svetlana Stenchikova, Matthew Marge
Proceedings of the IEEE/ACL 2006 Workshop on Spoken Language Technology (SLT),  2006.  [PDF]  [BIB]

Dialog generation for voice browsing
Zan Sun, Amanda Stent, I. V. Ramakrishnan
Proceedings of the International Cross-Disciplinary Workshop on Web Accessibility (W4A),  2006.  [PDF]  [BIB]

Two diverse systems built using generic components for spoken dialogue (recent progress on TRIPS)
James Allen, George Ferguson, Amanda Stent, Scott Stoness, Mary Swift, Lucian Galescu, Nate Chambers, Ellen Campana, Gregory Aist
Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL),  2005.  [PDF]  [BIB]

Trainable adaptable multimedia presentation generation
Hui Guo, Amanda Stent
Proceedings of the International Conference on Multimodal Interfaces (ICMI),  2005.  [PDF]  [BIB]

Evaluating evaluation methods for generation in the presence of variation
Amanda Stent, Matthew Marge, Mohit Singhai
Proceedings of CICLing,  2005.  [PDF]  [BIB]

Building surface realizers automatically from corpora using general-purpose tools
Huayan Zhong, Amanda Stent
Proceedings of the Workshop on Using Corpora for Natural Language Generation (UCNLG),  2005.  [PDF]  [BIB]

Automatic evaluation of referring expression generation using corpora
Surabhi Gupta, Amanda Stent
Proceedings of the Workshop on Using Corpora for Natural Language Generation (UCNLG),  2005.  [PDF]  [BIB]

A new data-driven approach for multimedia presentation planning
Amanda Stent, Hui Guo
Proceedings of EuroIMSA,  2005.  [PDF]  [BIB]

Trainable sentence planning for complex information presentations in spoken dialog systems
Amanda Stent, Rashmi Prasad, Marilyn Walker
Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL),  2004.  [PDF]  [BIB]

HearSay: Enabling Audio Browsing on Hypertext Content
I. V. Ramakrishnan, Amanda Stent, Guizhen Yang
Proceedings of the World Wide Web Conference (WWW),  2004.  [PDF]  [BIB]

Generation and evaluation of user tailored responses in multimodal dialogue
Marilyn Walker, Steve Whittaker, Amanda Stent, Preetam Maloor, Johanna Moore, Michael Johnston, Gunaranjan Vasireddy
Cognitive Science,  v28,  #5,  pp 811-840,  2004.  [PDF]  [BIB]

A trainable generator for recommendations in multimodal dialogue
Marilyn Walker, Rashmi Prasad, Amanda Stent
Proceedings of Eurospeech,  2003.  [PDF]  [BIB]

User-tailored generation for spoken dialogue: An experiment
Amanda Stent, Marilyn Walker, Steve Whittaker, Preetam Maloor
Proceedings of the International Conference on Spoken Language Processing (ICSLP),  2002.  [PDF]  [BIB]

Multimodal language processing for mobile information access
Michael Johnston, Srinivas Bangalore, Amanda Stent, Gunaranjan Vasireddy, Patrick Ehlen
Proceedings of the International Conference on Spoken Language Processing (ICSLP),  2002.  [PDF]  [BIB]

MATCH: An architecture for multimodal dialogue systems
Michael Johnston, Srinivas Bangalore, Gunaranjan Vasireddy, Amanda Stent, Patrick Ehlen, Marilyn Walker, Steve Whittaker, Preetam Maloor
Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL),  2002.  [PDF]  [BIB]

Generating evaluative responses in spoken dialogue
Marilyn Walker, Steve Whittaker, Amanda Stent, Preetam Maloor
Proceedings of the International Natural Language Generation Conference (INLG),  2002.  [PDF]  [BIB]

A conversation acts model for generating spoken dialogue contributions
Amanda Stent
Computer Speech and Language special issue on Spoken Language Generation,  v16,  #3-4,  pp 313-352,  2002.  [PDF]  [BIB]

Using event segmentation to improve indexing of consumer photographs
Amanda Stent, Alexander Loui
Proceedings of SIGIR,  2001.  [PDF]  [BIB]

Towards conversational human-computer interaction
James Allen, Donna Byron, Myroslava Dzikovska, George Ferguson, Lucian Galescu, Amanda Stent
AI Magazine,  v22,  #4,  pp 27-37,  2001.  [PDF]  [BIB]

Dialogue Systems as Conversational Partners: Applying conversation acts theory to natural language generation for task-oriented mixed-initiative spoken dialogue
Amanda Stent
University of Rochester,  2001.  [PDF]  [BIB]

An Architecture for More Realistic Conversational Systems
James Allen, George Ferguson, Amanda Stent
Proceedings of the Intelligent User Interfaces Conference (IUI),  2001.  [PDF]  [BIB]

The Monroe Corpus
Amanda Stent
University of Rochester,  #TR728 and TN99-2,  2000.  [PDF]  [BIB]

TRIPS-911 system demonstration
James Allen, Donna Byron, David Costello, Myroslava Dzikovska, George Ferguson, Lucian Galescu, Amanda Stent
Proceedings of the ANLP/NAACL 2000 Workshop on Conversational Systems,  2000.  [PDF]  [BIB]

Rhetorical structure in dialog
Amanda Stent
Proceedings of the International Natural Language Generation Conference (INLG),  2000.  [PDF]  [BIB]

Annotating Argumentation Acts in Spoken Dialog
Amanda Stent, James Allen
University of Rochester,  #TR740 and TN00-1,  2000.  [PDF]  [BIB]

An Architecture for a Generic Dialogue Shell
James Allen, Donna Byron, Myroslava Dzikovska, George Ferguson, Lucian Galescu, Amanda Stent
Natural Language Engineering special issue on Best Practices in Spoken Language Dialogue Systems Engineering,  v6,  #3,  2000.  [PDF]  [BIB]

The CommandTalk spoken dialogue system
Amanda Stent, John Dowding, Jean-Mark Gawron, Elizabeth Owen Bratt, Robert Moore
Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL),  1999.  [PDF]  [BIB]

Content planning and generation in continuous-speech spoken dialog systems
Amanda Stent
Proceedings of the KI'99 workshop, "May I Speak Freely?",  1999.  [PDF]  [BIB]

Content Planning for Multi-modal, Mixed-initiative, Task-oriented Dialog
Amanda Stent
1998.  [PDF]  [BIB]

Aspects of Natural Language Generation
Amanda Stent
University of Rochester,  #TR701,  1998.  [PDF]  [BIB]

null
  bibtex.bib  (0k)

A preliminary model of centering in dialog
Donna Byron, Amanda Stent
Proceedings of COLING-ACL,  1998.  [PDF]  [BIB]

A Preliminary Model of Centering in Dialog
Donna Byron, Amanda Stent
University of Rochester,  #TR687,  1998.  [PDF]  [BIB]

TRAINS-96 System Evaluation
Amanda Stent, James Allen
University of Rochester,  #TN97-1,  1997.  [PDF]  [BIB]