TALK project work at UCAM
|
|
- Dustin Owen
- 5 years ago
- Views:
Transcription
1 TALK project work at UCAM Matt Stuttle August 2005 Web: mns25 Dialogs on Dialogs
2 Overview TALK project Goals Baseline system the Hidden Information State (this) system Proposed system architecture The Speech Understanding (SU) Agent Confidence scores HVS parser Current and future work Dialogs on Dialogs 1
3 Project Goals: TALK project: Tools for Ambient Linguistic Knowledge Implement Information State Update (ISU) approaches Develop in-car and in-home multimodal dialog systems Learning strategies for the ISU approach Integrate multimodality and multilinguality Partners include Edinburgh, Gothenburg, DFKI, Saarbrucken, Seville, Bosch, Linguamatics and BMW Dialogs on Dialogs 2
4 TALK project: UCAM Project Workpackages: WP1: Unifying Multimodality and Multilinguality New Speech Understanding components Developing notion of multimodal dialog act Closely coupling parser, recogniser and dialog manager WP4: Adaptivity and Learning Reinforcement learning approaches (Partially Observable) Markov Decision Process dialog managers User modelling approaches Dialogs on Dialogs 3
5 Baseline System: Current baseline system built with Edinburgh: Based on SACTI Tourist Information domain Built using: DIPPER dialog manager Open Agent Architecture ATK speech recogntion using n-gram language models Word spotting parser Currently features: Implicit and explicit confirmation Fragmentary clarifications Simple fixed dialog plan (slot filling) Overanswering Multimodal output Dialogs on Dialogs 4
6 Proposed HVS System Overview System Architecture Speech Understanding Speech In ATK Parser N best list of hypothesised user dialogue acts Dialogue Manager Turn Manager Buffer this Data Base Speech Out Festival NLG System dialogue acts Four agents: Speech Understanding Dialogue manager Turn Manager Speech Generation Dialogs on Dialogs 5
7 Proposed HVS System Overview Hidden Information State model Operates as a MDP over Belief State B = P (S d, S u ) where S u =user state and S d =dialog state Similar advantages to POMDP for modelling uncertainty but like an MDP can be optimised using on-line methods Belief state is discrete approximation to continuous state space Approximation is a forest of most likely states User state expands according to application specific rules User state captures domain ontology Actions A s are based on a linear function approximation of Q(B, A s ) Dialogs on Dialogs 6
8 Speech Understanding Agent Speech Understanding Agent Speech In ATK HVS Parser A u,1 A A u,2 u,3 N best list of hypothesised user dialogue acts ATK sends N best word lists from lattices A A... u,4 u,n Parser generates dialogue acts continuously Some of UCAM s proposed work focuses on developing the SU agent. Uses ATK and the Hidden Vector State (HVS) Parser. Outputs an n-best list of user dialog acts with scores. Operates asynchronously, forwards dialog acts to the Turn Manager agent. Dialogs on Dialogs 7
9 Speech Understanding (SU) Agent Motivation Asynchronous, so does not impose a turn-taking model - will allow barge-in. Will output the n-best dialog acts Use of HVS and ATK will allow statistical confidence measures to be implemented HVS model can be incrementally trained on-line with system data. Multimodal inputs can be investigated later (WP1 work) Dialogs on Dialogs 8
10 Confidence Scores Current implementation: ATK currently outputs confidence scores based on recognition scores relative to a background model Current scores do not contain much information about correctness of hypothesis Recent work has enabled use of n-best lists and lattice generation in ATK Need to generate very long n-best lists to get alternative parse hypotheses. Dialogs on Dialogs 9
11 Confidence Scores Proposed alternative: Generate word posteriors from lattice for each word position Will generate more hypotheses from parser Deletions/insertions handled by NULL label Can generate alternatives for each word in the best hypothesis Word posteriors have been shown to be more informative Can develop strategies based on fragmentary clarification more easily Currently working on generating information on-the-fly Calculating word posteriors requires forward and backward pass through the (complete) lattice Dialogs on Dialogs 10
12 ATK Outputs I need see the that s near nearer theatre here Lattice Is that i see that s nearer is that nearer i see that s near here is the theatre i need the theatre the nearer I 0.7 Is 0.3 theatre see 0.6 null need that s 0.5 the a 0.2 that nearer 0.7 null theatre 0.1 near 0.2 here N-Best Confidence Network Dialogs on Dialogs 11
13 The Hidden Vector State (HVS) model for Semantic Parsing Overview Trade-off between flat-concept and hierarchical models Flat-concept HMM model extended by expanding each state States encode stack of push-down automata Model is right branching encodes hierarchical context avoids tractability issues of a PCFG approach Dialogs on Dialogs 12
14 Parse Tree generated by the Hidden Vector State Model TOLOC ON DUMMY CITY DATE SE sent_start I want to return to Dallas on Thursday sent_end DUMMY TOLOC CITY TOLOC ON DATE ON SE Parse tree of semantic concepts is right branching Tree is represented in vector state sequence below Dialogs on Dialogs 13
15 The Hidden Vector State (HVS) model for Semantic Parsing Motivation HVS is a statistical semantic parser Fits well into UCAM s plan for a statistical dialogue modelling approach Gives n-best acts together with probability/confidence scores HVS model is data-driven allows on-line/incremental adaptation/training requires only lightly supervised data HVS can be adapted to work on-the-fly will allow barge-in can use more complicated turn-manager Dialogs on Dialogs 14
16 Training and Parsing with the Hidden Vector State Model I want to return to Dallas on Thursday domain specific lexical classes 3 training parsing HVS-Model HVS-Parser abstract semantic annotation for each utterance TOLOC ON DUMMY CITY DATE SE sent_start I want to return to DUMMY TOLOC Dallas CITY TOLOC on ON Thursday DATE ON sent_end SE Dialogs on Dialogs 15
17 Current work Training HVS and word-spotting model on SACTI data for subset of tasks. Encapsulate HVS parser as an ATK component Make speech understanding (ATK+HVS) OAA agent Modify ATK to produce word-posterior networks with associated confidence scores Dialogs on Dialogs 16
18 Future plans (SU) Agent Combine ATK and HVS probabilities for a parser confidence score Adapt HVS approach to work with this data format Current parser results using HVS and word-spotting techniques are relatively poor SACTI data is not ideal: will perform a new data collection to bootstrap parser and language models Collection will feature abstract prompts of all features desired in final system May also do some collections with baseline system Plan to use a real town (Cambridge?) for new data collection with a much larger database extracted from Google maps/yell.com Dialogs on Dialogs 17
Task Completion Platform: A self-serve multi-domain goal oriented dialogue platform
Task Completion Platform: A self-serve multi-domain goal oriented dialogue platform P. A. Crook, A. Marin, V. Agarwal, K. Aggarwal, T. Anastasakos, R. Bikkula, D. Boies, A. Celikyilmaz, S. Chandramohan,
More informationStatistical Dialogue Modelling. Department of Engineering and Trinity Hall University of Cambridge
Statistical Dialogue Modelling Milica Gašić Department of Engineering and Trinity Hall University of Cambridge This dissertation is submitted for the degree of Doctor of Philosophy January 2011 2 Declaration
More informationHow to create dialog system
How to create dialog system Jan Balata Dept. of computer graphics and interaction Czech Technical University in Prague 1 / 55 Outline Intro Architecture Types of control Designing dialog system IBM Bluemix
More informationDFKI Approach to Dialogue Management. Norbert Reithinger, Elsa Pecourt, Markus Löckelt
DFKI Approach to Dialogue Management Norbert Reithinger, Elsa Pecourt, Markus Löckelt {bert,loeckelt,pecourt}@dfki.de What we develop at DFKI Research goal: Develop multimodal interactivity interfaces
More informationIntroduction to HTK Toolkit
Introduction to HTK Toolkit Berlin Chen 2003 Reference: - The HTK Book, Version 3.2 Outline An Overview of HTK HTK Processing Stages Data Preparation Tools Training Tools Testing Tools Analysis Tools Homework:
More informationCOLLAGEN: Applying Collaborative Discourse Theory to Human-Computer Interaction. Charles Rich Candace L. Sidner Neal Lesh
COLLAGEN: Applying Collaborative Discourse Theory to Human-Computer Interaction Charles Rich Candace L. Sidner Neal Lesh Mitsubishi Electric Research Laboratories Cambridge, Massachusetts 1 Road Map Philosophy
More informationContents. Resumen. List of Acronyms. List of Mathematical Symbols. List of Figures. List of Tables. I Introduction 1
Contents Agraïments Resum Resumen Abstract List of Acronyms List of Mathematical Symbols List of Figures List of Tables VII IX XI XIII XVIII XIX XXII XXIV I Introduction 1 1 Introduction 3 1.1 Motivation...
More informationConfidence Measures: how much we can trust our speech recognizers
Confidence Measures: how much we can trust our speech recognizers Prof. Hui Jiang Department of Computer Science York University, Toronto, Ontario, Canada Email: hj@cs.yorku.ca Outline Speech recognition
More informationTowards a basis for human-computer dialogue. Bengt Nordström Chalmers, Göteborg
Towards a basis for human-computer dialogue Bengt Nordström Chalmers, Göteborg Goal We want to model dialogue systems in which a human interacts with a computer to build an object. From Wikipedia: A dialog
More informationWHO WANTS TO BE A MILLIONAIRE?
IDIAP COMMUNICATION REPORT WHO WANTS TO BE A MILLIONAIRE? Huseyn Gasimov a Aleksei Triastcyn Hervé Bourlard Idiap-Com-03-2012 JULY 2012 a EPFL Centre du Parc, Rue Marconi 19, PO Box 592, CH - 1920 Martigny
More informationCMU Sphinx: the recognizer library
CMU Sphinx: the recognizer library Authors: Massimo Basile Mario Fabrizi Supervisor: Prof. Paola Velardi 01/02/2013 Contents 1 Introduction 2 2 Sphinx download and installation 4 2.1 Download..........................................
More informationTable of Contents 1 Introduction A Declarative Approach to Entity Resolution... 17
Table of Contents 1 Introduction...1 1.1 Common Problem...1 1.2 Data Integration and Data Management...3 1.2.1 Information Quality Overview...3 1.2.2 Customer Data Integration...4 1.2.3 Data Management...8
More information550 IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 9, NO. 3, APRIL /$ IEEE
550 IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 9, NO. 3, APRIL 2007 Information Seeking Spoken Dialogue Systems Part II: Multimodal Dialogue Alexandros Potamianos, Member, IEEE, Eric Fosler-Lussier, Senior
More informationtrindikit.py: An open-source Python library for developing ISU-based dialogue systems
trindikit.py: An open-source Python library for developing ISU-based dialogue systems Peter Ljunglöf Department of Philosophy, Linguistics and Theory of Science University of Gothenburg, Sweden peb@ling.gu.se
More informationCOMP90051 Statistical Machine Learning
COMP90051 Statistical Machine Learning Semester 2, 2016 Lecturer: Trevor Cohn 20. PGM Representation Next Lectures Representation of joint distributions Conditional/marginal independence * Directed vs
More informationAT&T: The Tag&Parse Approach to Semantic Parsing of Robot Spatial Commands
AT&T: The Tag&Parse Approach to Semantic Parsing of Robot Spatial Commands Svetlana Stoyanchev, Hyuckchul Jung, John Chen, Srinivas Bangalore AT&T Labs Research 1 AT&T Way Bedminster NJ 07921 {sveta,hjung,jchen,srini}@research.att.com
More informationSmartWeb Handheld Multimodal Interaction with Ontological Knowledge Bases and Semantic Web Services
IJCAI Workshop AI4HC, Hyderabad, 6/1/2007 SmartWeb Handheld Multimodal Interaction with Ontological Knowledge Bases and Semantic Web Services Daniel Sonntag, Ralf Engel, Gerd Herzog, Alexander Pfalzgraf,
More informationDesign of a Generation Component for a Spoken Dialogue System
Design of a Generation Component for a Spoken Dialogue System Graham Wilcock University of Helsinki 00014 Helsinki, Finland graham.wilcock@helsinki.fi Kristiina Jokinen University of Art and Design Helsinki
More informationInteraction Design and Implementation for Multimodal Mobile Semantic Web Interfaces
HCI International, Beijing, China, 27th July 2007 Interaction Design and Implementation for Multimodal Mobile Semantic Web Interfaces Daniel Sonntag German Research Center for Artificial Intelligence 66123
More informationForm. Settings, page 2 Element Data, page 7 Exit States, page 8 Audio Groups, page 9 Folder and Class Information, page 9 Events, page 10
The voice element is used to capture any input from the caller, based on application designer-specified grammars. The valid caller inputs can be specified either directly in the voice element settings
More informationSpoken language understanding II
NPFL099 - Statistical dialogue systems Spoken language understanding II Filip Jurčíček Institute of Formal and Applied Linguistics Charles University in Prague Czech Republic Home page: http://ufal.mff.cuni.cz/~jurcicek
More informationLightly Supervised Learning of Procedural Dialog Systems
Lightly Supervised Learning of Procedural Dialog Systems Svitlana Volkova in collaboration with Bill Dolan, Pallavi Choudhury, Luke Zettlemoyer, Chris Quirk Outline Motivation Data Query Logs Office.com
More informationUsing UIMA to Structure an Open Platform for Textual Entailment. Tae-Gil Noh, Sebastian Padó Dept. of Computational Linguistics Heidelberg University
Using UIMA to Structure an Open Platform for Textual Entailment Tae-Gil Noh, Sebastian Padó Dept. of Computational Linguistics Heidelberg University The paper is about About EXCITEMENT Open Platform a
More informationDialPort: Real-World Data for Academia Spoken Dialog Systems
DialPort: Real-World Data for Academia Spoken Dialog Systems Tiancheng Zhao, Yulun Du, Kyusong Lee and Maxine Eskenazi Department of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 {tianchez,
More informationKnowledge-Based Word Lattice Rescoring in a Dynamic Context. Todd Shore, Friedrich Faubel, Hartmut Helmke, Dietrich Klakow
Knowledge-Based Word Lattice Rescoring in a Dynamic Context Todd Shore, Friedrich Faubel, Hartmut Helmke, Dietrich Klakow Section I Motivation Motivation Problem: difficult to incorporate higher-level
More informationAn Introduction to Software Architecture
An Introduction to Software Architecture Software Engineering Design Lecture 11 Motivation for studying SW architecture As the size of SW systems increases, the algorithms and data structures of the computation
More informationLearning Latent Linguistic Structure to Optimize End Tasks. David A. Smith with Jason Naradowsky and Xiaoye Tiger Wu
Learning Latent Linguistic Structure to Optimize End Tasks David A. Smith with Jason Naradowsky and Xiaoye Tiger Wu 12 October 2012 Learning Latent Linguistic Structure to Optimize End Tasks David A. Smith
More informationDialogue systems. Volha Petukhova Saarland University
Dialogue systems Volha Petukhova Saarland University 20/07/2016 Einführung in Diskurs and Pragmatik, Sommersemester 2016 Introduction Multimodal natural-language based dialogue as humanmachine interface
More informationLightly Supervised Learning of Procedural Dialog Systems. Svitlana Volkova Pallavi Choudhury, Chris Quirk, Bill Dolan, Luke Zettlemoyer
Lightly Supervised Learning of Procedural Dialog Systems Svitlana Volkova Pallavi Choudhury, Chris Quirk, Bill Dolan, Luke Zettlemoyer Motivation Procedural dialog systems aim to assist users with a range
More informationAn Interactive Framework for Document Retrieval and Presentation with Question-Answering Function in Restricted Domain
An Interactive Framework for Document Retrieval and Presentation with Question-Answering Function in Restricted Domain Teruhisa Misu and Tatsuya Kawahara School of Informatics, Kyoto University Kyoto 606-8501,
More informationAn Introduction to Software Architecture
An Introduction to Software Architecture Software Requirements and Design CITS 4401 Lecture 11 Motivation for studying SW architecture As the size of SW systems increase, the algorithms and data structures
More informationLab 2. Decision (Classification) Tree
Lab 2. Decision (Classification) Tree Represented as a set of hierarchically-arranged decision rules (i.e., tree-branch-leaf) Could be generated by knowledge engineering, neural network, or statistic methods.
More informationA CASE STUDY: Structure learning for Part-of-Speech Tagging. Danilo Croce WMR 2011/2012
A CAS STUDY: Structure learning for Part-of-Speech Tagging Danilo Croce WM 2011/2012 27 gennaio 2012 TASK definition One of the tasks of VALITA 2009 VALITA is an initiative devoted to the evaluation of
More informationLarge-Scale Syntactic Processing: Parsing the Web. JHU 2009 Summer Research Workshop
Large-Scale Syntactic Processing: JHU 2009 Summer Research Workshop Intro CCG parser Tasks 2 The Team Stephen Clark (Cambridge, UK) Ann Copestake (Cambridge, UK) James Curran (Sydney, Australia) Byung-Gyu
More informationJulius rev LEE Akinobu, and Julius Development Team 2007/12/19. 1 Introduction 2
Julius rev. 4.0 L Akinobu, and Julius Development Team 2007/12/19 Contents 1 Introduction 2 2 Framework of Julius-4 2 2.1 System architecture........................... 2 2.2 How it runs...............................
More informationWell-formed Default Unification in Non-deterministic Multiple Inheritance Hierarchies
Well-formed Default Unification in Non-deterministic Multiple Inheritance Hierarchies Christian Schulz, Jan Alexandersson and Tilman Becker DFKI, Saarbrücken 1 Introduction Default unification represents
More informationSum-Product Networks. STAT946 Deep Learning Guest Lecture by Pascal Poupart University of Waterloo October 15, 2015
Sum-Product Networks STAT946 Deep Learning Guest Lecture by Pascal Poupart University of Waterloo October 15, 2015 Introduction Outline What is a Sum-Product Network? Inference Applications In more depth
More informationJOINT INTENT DETECTION AND SLOT FILLING USING CONVOLUTIONAL NEURAL NETWORKS. Puyang Xu, Ruhi Sarikaya. Microsoft Corporation
JOINT INTENT DETECTION AND SLOT FILLING USING CONVOLUTIONAL NEURAL NETWORKS Puyang Xu, Ruhi Sarikaya Microsoft Corporation ABSTRACT We describe a joint model for intent detection and slot filling based
More informationDesign and Realization of the EXCITEMENT Open Platform for Textual Entailment. Günter Neumann, DFKI Sebastian Pado, Universität Stuttgart
Design and Realization of the EXCITEMENT Open Platform for Textual Entailment Günter Neumann, DFKI Sebastian Pado, Universität Stuttgart Textual Entailment Textual Entailment (TE) A Text (T) entails a
More informationHuman Interaction Container Paradigm
Human Interaction Container Paradigm HIT Lab. Sébastien PRAUD July 20th, 2004 THALES Research & Technology Motivations Human Machine Interfaces (HMI) were designed to render applications or systems tracktable
More informationSOFTWARE DESIGN AND DEVELOPMENT OF MUTIMODAL INTERACTION
SOFTWARE DESIGN AND DEVELOPMENT OF MUTIMODAL INTERACTION Marie-Luce Bourguet Queen Mary University of London Abstract: Key words: The multimodal dimension of a user interface raises numerous problems that
More informationCS 532c Probabilistic Graphical Models N-Best Hypotheses. December
CS 532c Probabilistic Graphical Models N-Best Hypotheses Zvonimir Rakamaric Chris Dabrowski December 18 2004 Contents 1 Introduction 3 2 Background Info 3 3 Brute Force Algorithm 4 3.1 Description.........................................
More informationAuthors Martin Eckert Ingmar Kliche Deutsche Telekom Laboratories.
Workshop on speaker biometrics and VoiceXML 3.0 March 5-6, 2009, Menlo Park, CA, US Proposal of an SIV architecture and requirements Authors Martin Eckert (martin.eckert@telekom.de), Ingmar Kliche (ingmar.kliche@telekom.de),
More informationSAPIENT Automation project
Dr Maria Liakata Leverhulme Trust Early Career fellow Department of Computer Science, Aberystwyth University Visitor at EBI, Cambridge mal@aber.ac.uk 25 May 2010, London Motivation SAPIENT Automation Project
More informationAssignment 4 CSE 517: Natural Language Processing
Assignment 4 CSE 517: Natural Language Processing University of Washington Winter 2016 Due: March 2, 2016, 1:30 pm 1 HMMs and PCFGs Here s the definition of a PCFG given in class on 2/17: A finite set
More informationInformation Seeking Spoken Dialogue Systems Part I: Semantics and Pragmatics
Information Seeking Spoken Dialogue Systems Part I: Semantics and Pragmatics Egbert Ammicht, Eric Fosler-Lussier, Senior Member, IEEE, Alexandros Potamianos, Member, IEEE Abstract In this paper, the semantic
More informationValue Iteration. Reinforcement Learning: Introduction to Machine Learning. Matt Gormley Lecture 23 Apr. 10, 2019
10-601 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University Reinforcement Learning: Value Iteration Matt Gormley Lecture 23 Apr. 10, 2019 1
More informationVoice Control becomes Natural
Voice Control becomes Natural ITU-T FOCUS GROUP CarCom -- SPEECH IN CARS Dr. Udo Haiber Torino, Italy, October 16, 2009 Overview Company What is Natural? Involved Components Focus Change Approach Conclusion
More informationToward a Standard Rule Language for Semantic Integration of the DoD Enterprise
1 W3C Workshop on Rule Languages for Interoperability Toward a Standard Rule Language for Semantic Integration of the DoD Enterprise A MITRE Sponsored Research Effort Suzette Stoutenburg 28 April 2005
More informationICT Dialogue Manager Tutorial: Session 5: Implementation in Soar (II)
ICT Dialogue Manager Tutorial: Session 5: Implementation in Soar (II) Outline Review Soar basics Dialogue Information State Dialogue Processing Cycles Code overview Content and Dialogue Act Representations
More informationThe Connected World and Speech Technologies: It s About Effortless
The Connected World and Speech Technologies: It s About Effortless Jay Wilpon Executive Director, Natural Language Processing and Multimodal Interactions Research IEEE Fellow, AT&T Fellow In the Beginning
More informationECE521: Week 11, Lecture March 2017: HMM learning/inference. With thanks to Russ Salakhutdinov
ECE521: Week 11, Lecture 20 27 March 2017: HMM learning/inference With thanks to Russ Salakhutdinov Examples of other perspectives Murphy 17.4 End of Russell & Norvig 15.2 (Artificial Intelligence: A Modern
More informationDECISION TREES & RANDOM FORESTS X CONVOLUTIONAL NEURAL NETWORKS
DECISION TREES & RANDOM FORESTS X CONVOLUTIONAL NEURAL NETWORKS Deep Neural Decision Forests Microsoft Research Cambridge UK, ICCV 2015 Decision Forests, Convolutional Networks and the Models in-between
More informationMotivating Ontology-Driven Information Extraction
Motivating Ontology-Driven Information Extraction Burcu Yildiz 1 and Silvia Miksch 1, 2 1 Institute for Software Engineering and Interactive Systems, Vienna University of Technology, Vienna, Austria {yildiz,silvia}@
More informationSupervised Learning with Neural Networks. We now look at how an agent might learn to solve a general problem by seeing examples.
Supervised Learning with Neural Networks We now look at how an agent might learn to solve a general problem by seeing examples. Aims: to present an outline of supervised learning as part of AI; to introduce
More informationNatural Language Processing
Natural Language Processing Machine Learning Potsdam, 26 April 2012 Saeedeh Momtazi Information Systems Group Introduction 2 Machine Learning Field of study that gives computers the ability to learn without
More informationStuck in Traffic (SiT) Attacks
Stuck in Traffic (SiT) Attacks Mina Guirguis Texas State University Joint work with George Atia Traffic 2 Intelligent Transportation Systems V2X communication enable drivers to make better decisions: Avoiding
More informationModularization of Multimodal Interaction Specifications
Modularization of Multimodal Interaction Specifications Matthias Denecke, Kohji Dohsaka, Mikio Nakano Communication Sciences Laboratories, NTT NTT Corporation Morinosato Wakamiya 3-1 Atsugi, Kanagawa 243-0198,
More informationMLSALT11: Large Vocabulary Speech Recognition
MLSALT11: Large Vocabulary Speech Recognition Riashat Islam Department of Engineering University of Cambridge Trumpington Street, Cambridge, CB2 1PZ, England ri258@cam.ac.uk I. INTRODUCTION The objective
More informationAudio Conferencing IP and TDM
Audio Conferencing IP and TDM May 5, 2004 Jerry Norton Chief Technical Officer Vapps, Inc. Wendell Bishop Chief Scientist NMS Communications NMS at a Glance Founded in 1983, publicly traded since 1994
More informationINDEX. Call Contact palette 93. Cisco Unity Express Script Editor Installation and Configuration Guide IN-149. Cisco Unity Express Release 2.
INDEX A aa_sample1.aef file 39 About option in Help menu 7 acceptable digits, specifying 108 Accept step 89 accessing call-specific information 97 adding connection output branch 76 adding new connection
More informationEVALITA 2009: Loquendo Spoken Dialog System
EVALITA 2009: Loquendo Spoken Dialog System Paolo Baggia Director of International Standards Speech Luminary at SpeechTEK 2009 Evalita Workshop December 12 th, 2009 Evalita Workshop 2009 Paolo Baggia 11
More informationLeveraging Knowledge Graphs for Web-Scale Unsupervised Semantic Parsing. Interspeech 2013
Leveraging Knowledge Graphs for Web-Scale Unsupervised Semantic Parsing LARRY HECK, DILEK HAKKANI-TÜR, GOKHAN TUR Focus of This Paper SLU and Entity Extraction (Slot Filling) Spoken Language Understanding
More informationIntroduction to Text Mining. Hongning Wang
Introduction to Text Mining Hongning Wang CS@UVa Who Am I? Hongning Wang Assistant professor in CS@UVa since August 2014 Research areas Information retrieval Data mining Machine learning CS@UVa CS6501:
More informationLecture Outlines. CSCI- 360 Section R Spring 2016 Wei- Min Shen
Lecture Outlines CSCI- 360 Section- 30304R Spring 2016 Wei- Min Shen Wk1 Ch1: Introduction * Welcome * Class structures/rules (syllabus, HM, projects, tests) * What is AI? * What are the related fields
More informationCombining Neural Networks and Log-linear Models to Improve Relation Extraction
Combining Neural Networks and Log-linear Models to Improve Relation Extraction Thien Huu Nguyen and Ralph Grishman Computer Science Department, New York University {thien,grishman}@cs.nyu.edu Outline Relation
More informationGrounded Compositional Semantics for Finding and Describing Images with Sentences
Grounded Compositional Semantics for Finding and Describing Images with Sentences R. Socher, A. Karpathy, V. Le,D. Manning, A Y. Ng - 2013 Ali Gharaee 1 Alireza Keshavarzi 2 1 Department of Computational
More informationTask-Oriented Planning for Manipulating Articulated Mechanisms under Model Uncertainty. Venkatraman Narayanan and Maxim Likhachev
Task-Oriented Planning for Manipulating Articulated Mechanisms under Model Uncertainty Venkatraman Narayanan and Maxim Likhachev Motivation Motivation A lot of household objects are ARTICULATED A lot of
More informationStochastic Segment Modeling for Offline Handwriting Recognition
2009 10th nternational Conference on Document Analysis and Recognition tochastic egment Modeling for Offline Handwriting Recognition Prem Natarajan, Krishna ubramanian, Anurag Bhardwaj, Rohit Prasad BBN
More informationSearch Engines. Information Retrieval in Practice
Search Engines Information Retrieval in Practice All slides Addison Wesley, 2008 Beyond Bag of Words Bag of Words a document is considered to be an unordered collection of words with no relationships Extending
More informationTransition-Based Dependency Parsing with MaltParser
Transition-Based Dependency Parsing with MaltParser Joakim Nivre Uppsala University and Växjö University Transition-Based Dependency Parsing 1(13) Introduction Outline Goals of the workshop Transition-based
More informationbarge In option 127 bigdecimal variables 16 biginteger variables 16 boolean variables 15 business hours step 100
A aa_sample1.aef file 25 aa script 1 acceptable digits, specifying 137 accept step 67 annotate step 99 attach to fax step 95 auto attendant sample script 1 B barge In option 127 bigdecimal variables 16
More informationRecurrent Neural Networks. Nand Kishore, Audrey Huang, Rohan Batra
Recurrent Neural Networks Nand Kishore, Audrey Huang, Rohan Batra Roadmap Issues Motivation 1 Application 1: Sequence Level Training 2 Basic Structure 3 4 Variations 5 Application 3: Image Classification
More informationIntroduction to CRFs. Isabelle Tellier
Introduction to CRFs Isabelle Tellier 02-08-2013 Plan 1. What is annotation for? 2. Linear and tree-shaped CRFs 3. State of the Art 4. Conclusion 1. What is annotation for? What is annotation? inputs can
More informationCompiler Design Aug 1996
Aug 1996 Part A 1 a) What are the different phases of a compiler? Explain briefly with the help of a neat diagram. b) For the following Pascal keywords write the state diagram and also write program segments
More informationTopological Mapping. Discrete Bayes Filter
Topological Mapping Discrete Bayes Filter Vision Based Localization Given a image(s) acquired by moving camera determine the robot s location and pose? Towards localization without odometry What can be
More informationLing/CSE 472: Introduction to Computational Linguistics. 5/4/17 Parsing
Ling/CSE 472: Introduction to Computational Linguistics 5/4/17 Parsing Reminders Revised project plan due tomorrow Assignment 4 is available Overview Syntax v. parsing Earley CKY (briefly) Chart parsing
More informationFrom Legacy Lexicon to Archivable Resource
From Legacy Lexicon to Archivable Resource Mike Maxwell Linguistic Data Consortium 3600 Market St, Suite 810 Philadelphia, PA 19104 USA maxwell@ldc.upenn.edu Abstract A common format for lexicons produced
More informationCollective Intelligence in Action
Collective Intelligence in Action SATNAM ALAG II MANNING Greenwich (74 w. long.) contents foreword xv preface xvii acknowledgments xix about this book xxi PART 1 GATHERING DATA FOR INTELLIGENCE 1 "1 Understanding
More informationHomework 3: Dialog. Part 1. Part 2. Results are due 17 th November 3:30pm
Homework 3: Dialog Part 1 Call TellMe and get two sets of driving directions Call CMU s Let s Go Call Amtrak Part 2 Build your own pizza ordering systems Register with Tell Me Studio Use VoiceXML to build
More informationA Comparison of Sequence-Trained Deep Neural Networks and Recurrent Neural Networks Optical Modeling For Handwriting Recognition
A Comparison of Sequence-Trained Deep Neural Networks and Recurrent Neural Networks Optical Modeling For Handwriting Recognition Théodore Bluche, Hermann Ney, Christopher Kermorvant SLSP 14, Grenoble October
More informationQuestion Answering Biographic Information and Social Networks Powered by the Semantic Web
Question Answering Biographic Information and Social Networks Powered by the Semantic Web Peter Adolphs, Xiwen Cheng, Tina Klüwer, Hans Uszkoreit & Feiyu Xu German Research Center for Artifical Intelligence
More informationOntology-based Service Discovery Front-end Interface for GloServ
Ontology-based Service Discovery Front-end Interface for GloServ Knarig Arabshian, Christian Dickmann and Henning Schulzrinne Department of Computer Science Columbia University, New York NY 10027, USA
More informationA MULTILINGUAL DIALOGUE SYSTEM FOR ACCESSING THE WEB
A MULTILINGUAL DIALOGUE SYSTEM FOR ACCESSING THE WEB Marta Gatius, Meritxell González and Elisabet Comelles Technical University of Catalonia, Software Department, Campus Nord UPC, Jordi Girona, 1-3 08034
More informationInteractive Handwritten Text Recognition and Indexing of Historical Documents: the transcriptorum Project
Interactive Handwritten Text Recognition and ing of Historical Documents: the transcriptorum Project Alejandro H. Toselli ahector@prhlt.upv.es Pattern Recognition and Human Language Technology Reseach
More informationMaximum Likelihood Beamforming for Robust Automatic Speech Recognition
Maximum Likelihood Beamforming for Robust Automatic Speech Recognition Barbara Rauch barbara@lsv.uni-saarland.de IGK Colloquium, Saarbrücken, 16 February 2006 Agenda Background: Standard ASR Robust ASR
More informationUsing Document Summarization Techniques for Speech Data Subset Selection
Using Document Summarization Techniques for Speech Data Subset Selection Kai Wei, Yuzong Liu, Katrin Kirchhoff, Jeff Bilmes Department of Electrical Engineering University of Washington Seattle, WA 98195,
More information2. Basic Task of Pattern Classification
2. Basic Task of Pattern Classification Definition of the Task Informal Definition: Telling things apart 3 Definition: http://www.webopedia.com/term/p/pattern_recognition.html pattern recognition Last
More informationMultilingual Vocal Access to Databases: the Central Role of Ontology Management in VocaBase
Multilingual Vocal Access to Databases: the Central Role of Ontology Management in VocaBase Christophe Dupriez DB Scape Chaussée de Bruxelles, 63 - Waterloo (Belgium) dupriez@dbscape.com - http://www.dbscape.com
More informationBuild, Deploy & Operate Intelligent Chatbots with Amazon Lex
Build, Deploy & Operate Intelligent Chatbots with Amazon Lex Ian Massingham AWS Technical Evangelist @IanMmmm aws.amazon.com/lex 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
More informationFully Delexicalized Contexts for Syntax-Based Word Embeddings
Fully Delexicalized Contexts for Syntax-Based Word Embeddings Jenna Kanerva¹, Sampo Pyysalo² and Filip Ginter¹ ¹Dept of IT - University of Turku, Finland ²Lang. Tech. Lab - University of Cambridge turkunlp.github.io
More informationLandmark-based Location Belief Tracking in a Spoken Dialog System
Landmark-based Location Belief Tracking in a Spoken Dialog System Yi Ma The Ohio State University Columbus, OH 43210 may@cse.ohio-state.edu Antoine Raux, Deepak Ramachandran, Rakesh Gupta Honda Research
More informationPRACTICAL SPEECH USER INTERFACE DESIGN
; ; : : : : ; : ; PRACTICAL SPEECH USER INTERFACE DESIGN й fail James R. Lewis. CRC Press Taylor &. Francis Group Boca Raton London New York CRC Press is an imprint of the Taylor & Francis Group, an informa
More informationReflection in the Chomsky Hierarchy
Reflection in the Chomsky Hierarchy Henk Barendregt Venanzio Capretta Dexter Kozen 1 Introduction We investigate which classes of formal languages in the Chomsky hierarchy are reflexive, that is, contain
More informationA Survey Of Different Text Mining Techniques Varsha C. Pande 1 and Dr. A.S. Khandelwal 2
A Survey Of Different Text Mining Techniques Varsha C. Pande 1 and Dr. A.S. Khandelwal 2 1 Department of Electronics & Comp. Sc, RTMNU, Nagpur, India 2 Department of Computer Science, Hislop College, Nagpur,
More informationafewadminnotes CSC324 Formal Language Theory Dealing with Ambiguity: Precedence Example Office Hours: (in BA 4237) Monday 3 4pm Wednesdays 1 2pm
afewadminnotes CSC324 Formal Language Theory Afsaneh Fazly 1 Office Hours: (in BA 4237) Monday 3 4pm Wednesdays 1 2pm January 16, 2013 There will be a lecture Friday January 18, 2013 @2pm. 1 Thanks to
More informationComponent Model for Multimodal Web Applications
Component Model for Multimodal Web Applications How to combine object oriented concepts with markup for event driven applications 1/22 Dave Raggett, W3C/Canon MWeb Workshop, Sophia Antipolis, July 2004
More informationSoftware Engineering Principles
1 / 19 Software Engineering Principles Miaoqing Huang University of Arkansas Spring 2010 2 / 19 Outline 1 2 3 Compiler Construction 3 / 19 Outline 1 2 3 Compiler Construction Principles, Methodologies,
More informationNatural Language Processing. SoSe Question Answering
Natural Language Processing SoSe 2017 Question Answering Dr. Mariana Neves July 5th, 2017 Motivation Find small segments of text which answer users questions (http://start.csail.mit.edu/) 2 3 Motivation
More informationShrey Patel B.E. Computer Engineering, Gujarat Technological University, Ahmedabad, Gujarat, India
International Journal of Scientific Research in Computer Science, Engineering and Information Technology 2018 IJSRCSEIT Volume 3 Issue 3 ISSN : 2456-3307 Some Issues in Application of NLP to Intelligent
More information