State Machine & Dialog Systems

Notes:

A state machine is a device or system that can be in one of a finite number of stable states, and which can transition between these states based on its current state and the inputs it receives. State machines are used to model the behavior of systems that exhibit distinct states or modes of operation, and which change their behavior in response to external stimuli or events. In a state machine, each state represents a specific condition or mode of operation, and the transitions between states represent the rules for changing from one state to another. State machines are widely used in computer science, engineering, and other fields to design and implement systems that exhibit complex behavior.

Dialog systems are often used in conjunction with state machines in the context of virtual humans in order to enable natural language interactions with the virtual human. A virtual human is a computer-generated character that is designed to interact with users in a way that simulates human behavior. Virtual humans can be used in a variety of applications, including customer service, education, and entertainment.

In a dialog system, the state machine is used to model the behavior of the virtual human and to define the possible states and transitions that the virtual human can exhibit. For example, a virtual human might have a state for greeting users, a state for answering questions, and a state for providing information. The state machine would define the rules for transitioning between these states based on the inputs received from the user and the actions taken by the virtual human.

Dialog systems are used to enable the virtual human to understand and respond to user input in natural language. The dialog system processes the user’s input and determines the appropriate response based on the current state of the virtual human and the rules defined in the state machine. For example, if the user asks a question, the dialog system might transition the virtual human to the “answering questions” state and generate a response based on the content of the question.

By using a combination of dialog systems and state machines, virtual humans can provide a more natural and interactive experience for users, enabling them to communicate and interact with the virtual human.

Intent recognition is the process of identifying the purpose or goal behind an action or request made by a user or system. In natural language processing and artificial intelligence, intent recognition involves analyzing the words and context of a user’s input in order to determine their intended meaning or intended outcome. Intent recognition systems are used in a variety of applications, including language translation, dialogue systems, and virtual assistants.
Permugram is a term that is used to describe a graphical representation of a state machine. A permugram is a type of flowchart that shows the states and transitions of a state machine, as well as the conditions under which transitions occur. Permugrams are often used to design and document state machines, as they provide a clear visual representation of the behavior of the system.
State transition system is a mathematical model of a system that exhibits discrete states and transitions between these states. A state transition system consists of a set of states, a set of transitions between these states, and a set of rules that govern the conditions under which transitions occur. State transition systems are used to represent and analyze the behavior of systems that exhibit complex or dynamic behavior, and are widely used in computer science, engineering, and other fields.

Wikipedia:

Building a conversational agent overnight with dialogue self-play
P Shah, D Hakkani-Tür, G Tür, A Rastogi… – arXiv preprint arXiv …, 2018 – arxiv.org
… BS is modeled as a fi- nite state machine (Hopcroft et al … important when developing datasets to benchmark research aimed towards building human-level dialogue systems … Existing methods for developing chatbots with engineered finite state machines implicitly define a model …

Bootstrapping a neural conversational agent with dialogue self-play, crowdsourcing and on-line reinforcement learning
P Shah, D Hakkani-Tur, B Liu, G Tur – … of the 2018 Conference of the …, 2018 – aclweb.org
… Figure 2: Finite state machine for a task-independent system agent for database … developing datasets to benchmark research aimed towards building human-level dialogue systems … Existing methods for developing chatbots with engineered finite state machines implicitly define …

Spoken dialogue system for a human-like conversational robot ERICA
T Kawahara – Proc. IWSDS, keynote speech, 2018 – colips.org
… Fig. 3 Hybrid architecture of spoken dialog systems • State-transition flow A flow of dialogue is hand-crafted as a finite state machine (FSM). This approach has been widely adopted in a limited task domain with a definite task goal, such as filling forms and making transactions …

Gap after the next two vehicles: A Spatio-temporally Situated Dialog for a Cooperative Driving Assistant
M Heckmann, D Orth, D Kolossa – … Communication; 13th ITG …, 2018 – ieeexplore.ieee.org
… The Watch-Right State Machine consists of three different types of states: • Not Announced: The system reaches this state if no an- nouncement has yet … In this work we have presented a spatio-temporally situated dialog system, which makes references to quickly moving objects …

Deep Learning in Natural Language Processing
L Deng, Y Liu – 2018 – books.google.com
… Tur, Asli Celikyilmaz, Xiaodong He, Dilek Hakkani-Tür and Li Deng 3 Deep Learning in Spoken and Text-Based Dialog Systems … net Deep neural network Deep structured semantic model Dialog state tracking Entity linking Expectation maximization Finite state machine xv …

Simulation-Based Usability Evaluation of Spoken and Multimodal Dialogue Systems
S Hillmann, S Hillmann, Baumann – 2018 – Springer
… Stefan Hillmann Simulation-Based Usability Evaluation of Spoken and Multimodal Dialogue Systems Page 2. T-Labs Series in Telecommunication Services Series editors Sebastian Möller, Berlin, Germany Axel Küpper, Berlin, Germany Alexander Raake, Berlin, Germany …

Integrating a dialog component into a framework for spoken language understanding
S Weigelt, T Hey, M Landhäußer – … of the 6th International Workshop on …, 2018 – dl.acm.org
… Some model the decision process as finite state machines (call-flow based [7, 9]), some respond according to … and Language Understanding As shown in Figure 2, two building blocks of dialog systems (ie, speech … All dialog strategies are modeled as finite-state machine …

Multi-turn qa: A rnn contextual approach to intent classification for goal-oriented systems
M Mensio, G Rizzo, M Morisio – Companion of the The Web Conference …, 2018 – dl.acm.org
… To keep track of all the possible paths of a dialogue, usually a Finite State Machine [2] is used … 2017. Frames: A corpus for adding memory to goal-oriented dialogue systems. In Proceedings of the SIG- DIAL 2017 Conference …

Integration of a Kaldi speech recognizer into a speech dialog system for automotive infotainment applications
T Ranzenberger, C Hacker, F Gallwitz… – … on Electronic Speech …, 2018 – essv2018.de
… 3 Integration of Kaldi into a dialog modeling tool The speech dialog system for our research is part of the HMI modeling tool EB GUIDE [6]. It is widely-used in the automotive industry, in particular to create infotainment systems. The dialog flow is modeled using a state machine …

Towards Chatbots in the museum
S Schaffer, O Gustke, J Oldemeier, N Reithinger – Proceedings of Mobile – ceur-ws.org
… versational systems domain-specific knowledge is mapped by dialog grammars and state machines [5]. Dialog grammars and state machines provide a … System promts will be generated for meta communication, ie system config- uration, as well as for specific information coming …

Learning Latent Beliefs and Performing Epistemic Reasoning for Efficient and Meaningful Dialog Management
A Chhabra, P Saini, A Sangroya… – arXiv preprint arXiv …, 2018 – arxiv.org
… Motivated by the above works, we propose to identify the beliefs, use these beliefs to trigger epistemic rules, and use the assertions of the rules to drive the conversation by tailoring the states in a finite-state machine dialog system …

NIPS Conversational Intelligence Challenge 2017 Winner System: Skill-based Conversational Agent with Supervised Dialog Manager
I Yusupov, Y Kuratov – Proceedings of the 27th International Conference …, 2018 – aclweb.org
… Abstract We present bot#1337: a dialog system developed for the 1st NIPS Conversational Intelligence Challenge 2017 (ConvAI) … The latter allows a developer to focus on the skill implementation rather than the finite state machine based dialog manager …

Tartan: A retrieval-based socialbot powered by a dynamic finite-state machine architecture
G Larionov, Z Kaden, HV Dureddy… – arXiv preprint arXiv …, 2018 – arxiv.org
… interest in human-machine spoken language interaction had focused on goal-oriented dialog systems … Magnus built multiple Finite State Machines to model dialog within a specific topic (eg … We took inspiration from Magnus and built a dynamic Finite State Machine to model …

Installation and Control of Building Automation Systems Using Human-Robot-Interaction
M Ohlenbusch, NFH Bartner, S Vöge… – … on Methods & …, 2018 – ieeexplore.ieee.org
… The implemented system, including the context-sensitive dia- log control features, have the elementary characteristics of a state machine … should adapt to a person instead of requiring adaptation by the user [6]. To ensure the user’s orientation in a complex dialog system, a help …

Multi-Modal Robot Apprenticeship: Imitation Learning Using Linearly Decayed DMP+ in a Human-Robot Dialogue System
Y Wu, R Wang, LF D’Haro, RE Banchs… – 2018 IEEE/RSJ …, 2018 – ieeexplore.ieee.org
… 1. System architecture of the multi-modal dialogue system … The implementation of our gluing task (see Section VB follows a multi-slot frame-based approach defined in a finite state-machine flow although the platform allows single-slot filling approach or a multi-goal approach [31 …

Towards a Types-As-Classifiers Approach to Dialogue Processing in Human-Robot Interaction
J Hough, L Jamone, D Schlangen, G Walck, R Haschke – 2018 – qmro.qmul.ac.uk
… A more challenging task, beyond the use of sin- gle sentence texts with images, is the creation of dialogue systems designed for real-world human … diagram shows how the robot tracks its own current task state and action state of its arm through a Hierarchical State Machine (HSM …

Modern Interfaces for Knowledge Representation and Processing Systems Based on Markup Technologies.
AA Saeed, D D?nciulescu – International Journal of …, 2018 – search.ebscohost.com
… SCXML as the representation of the state machine is seen as a benefit”. The mentioned authors found that “large portions of the SCXML standard are not necessary for it to be useful to our customers and us.” CCXML is designed to upgrade VXML dialog systems with advanced …

Automatic Extraction of Domain Specific Latent Beliefs in Customer Complaints to Help Tailor Chatbots
A Sangroya, C Anantaram, P Saini, M Rawat – Workshops at the Thirty …, 2018 – aaai.org
… Motivated by the above works, we propose to identify the beliefs, use these beliefs to trigger epistemic rules, and use the assertions of the rules to drive the conversation by tailoring the states in a finite-state machine dialog system …

Speech understanding for spoken dialogue systems: From corpus harvesting to grammar rule induction
E Iosif, I Klasinas, G Athanasopoulou… – Computer Speech & …, 2018 – Elsevier
… Volume 47, January 2018, Pages 272-297. Computer Speech & Language. Speech understanding for spoken dialogue systems: From corpus harvesting to grammar rule induction? … Highlights. • We investigate algorithms for inducing grammars for spoken dialogue systems. • …

Virtual Doctor: An Intelligent Human-Computer Dialogue System for Quick Response to People in Need
S Mallios – 2018 – corescholar.libraries.wright.edu
… 2018 Virtual Doctor: An Intelligent Human-Computer Dialogue System for Quick Response to People in Need … Repository Citation Mallios, Stavros, “Virtual Doctor: An Intelligent Human-Computer Dialogue System for Quick Response to People in Need” (2018) …

MeMo Platform for Automatic Usability Evaluation
S Hillmann – … of Spoken and Multimodal Dialogue Systems, 2018 – Springer
… For example, assuming a user wants to switch on a lamp by a spoken dialogue system, a possible actual utterance could be “Switch … The implementation of the state model is based upon a finite-state machine describing the relations between dialogues (ie representations of the …

Composable Multimodal Dialogues Based on Communicative Acts
E Fernández-Rodicio, Á Castro-González… – … Conference on Social …, 2018 – Springer
… state-based dialogue manager for the Hygeiorobot robot focused on spoken dialogues, modelled as state machines, where the … and maintains three different representations for the current state of the dialogue: a state machine, a set … [7] proposed a dialogue system for controlling …

SMILEE: Symmetric Multi-modal Interactions with Language-gesture Enabled (AI) Embodiment
S Kim, D Salter, L DeLuccia, K Son, MR Amer… – Proceedings of the …, 2018 – aclweb.org
… Interaction Manager manages the state machines for dialogs/interactions … The symmetry game agent also utilizes a state machine to keep track of the game state based on the rules of … Evaluating description and reference strategies in a cooperative human-robot dialogue system …

Memory-augmented Dialogue Management for Task-oriented Dialogue Systems
Z Zhang, M Huang, Z Zhao, F Ji, H Chen… – arXiv preprint arXiv …, 2018 – arxiv.org
… Rule-based approaches date back to very early dialogue systems [34]. Several architectures are proposed to formulate the process of dialogue management. The flow diagram approach [19] used a finite-state machine to model state transition in dialogue, where the state …

A Natural Language Interface for Dissemination of Reproducible Biomedical Data Science
RJL John, JM Patel, AL Alexander, V Singh… – … Conference on Medical …, 2018 – Springer
… It is essentially a finite state machine (FSM) implemented in Python … CACM 9(1), 36–45 (1966)CrossRefGoogle Scholar. 10. Williams, J., Kamal, E., et al.: Fast and easy language understanding for dialog systems with Microsoft LUIS. In: SIGDIAL, pp …

Reactive chatbot programming
G Baudart, M Hirzel, L Mandel, A Shinnar… – Proceedings of the 5th …, 2018 – dl.acm.org
… The dialog is specified by a finite state machine that reacts to the intents and entities or context information set by the application … 3.2 Chatbot State Machines We now show how to use the control structures provided by ReactiveML to orchestrate the execution of chatbots …

Protecting chatbots from toxic content
G Baudart, J Dolby, E Duesterwald, M Hirzel… – Proceedings of the …, 2018 – dl.acm.org
… While there are high-level dialog programming models, eg, frames [Bobrow et al. 1977], most of them can use finite state machines as a low-level intermediate representation. Figure 3 gives an example finite state machine for a simple shopping chatbot …

Stack Automata-Based Framework for Behavior Modeling of Virtual Agents
SR Srivastava, A Joseph – … of First International Conference on Smart …, 2018 – Springer
… AH: A Natural Conversational Virtual Human with Multimodal Dialog System … ISBN-13: 978–8131720479 (2008)Google Scholar. 6. Wright, DR: Finite State Machines … https://www.nist. gov/dads/HTML/pushdownautm.html (2004). 8. Black, PE: Finite State Machine, Dictionary of …

How Was Your Weekend? A Generative Model of Phatic Conversation
HM Morrison, C Martens – The Thirty-First International Flairs Conference, 2018 – aaai.org
… Some of Bob’s statements have been omitted. the global conversation structure as a state machine in Fig- ure 2, which approximates these constraints as precedence ordering between conversational moves … Advances in natural multi- modal dialogue systems 30:23–54 …

Drink-O-Mender: An Adaptive Robotic Drink Adviser
H Ritschel, A Seiderer, K Janowski, I Aslan… – Proceedings of the 3rd …, 2018 – dl.acm.org
… with Visual SceneMaker [7], which allows modeling agent behavior as parallel, hierarchical finite state machines … in parallel to the dialog by means of a separate gaze state machine … politeness strategies for recommenda- tions [10] or an interactive dialog system with different …

Extracting Latent Beliefs and using Epistemic Reasoning to Tailor a Chatbot.
A Sangroya, C Anantaram, P Saini, M Rawat – IJCAI, 2018 – ijcai.org
… Deep learning based dialog systems [Miller et al., 2016] use mem- ory networks to learn the underlying dialog structure and carry out goal … We assume that we have a hand-crafted complaint- management finite-state-machine (FSM) to carry out the di- alog with the customer …

Speech technologies and the assessment of second language speaking: Approaches, challenges, and opportunities
D Litman, H Strik, GS Lim – Language Assessment Quarterly, 2018 – Taylor & Francis
… a dialogue manager typically uses the assessments from the speech recognition and natural language understanding components, in conjunction with an internal representation of system state, to decide what the dialogue system should do next. If a finite state machine is used …

Speech recognition in construction equipment: Creating a voice assistant for an autonomous wheel loader
N Kartalidis – 2018 – diva-portal.org
… 39 9. Appendix A: State machine diagram … Research has been conducted to evaluate and compare touch, gesture, and voice control in car infotainment systems [30] and research on how to reduce working memory load in spoken dialogue systems has taken place, mainly with …

A review on data fusion methods in multimodal human computer dialog
M YANG, J TAO – vr-ih.com
… While in multi-modal dialog system, we need combine multimodal channel information together to obtain users’ dialog intention or state … DM usually consider the speech information as the main interactive channel, and used, slot-filling, finite state machine (FSM), graph model …

Grounding Verbs for Tool-Dependent, Sensor-Based Robot Tasks
K Wölfel, D Henrich – 2018 27th IEEE International Symposium …, 2018 – ieeexplore.ieee.org
… In state machines, nodes in this graph store sub- tasks (primitive motions or further directed graphs) as well … and motion parameters are either predefined [17] or can be set by using a dialogue system [20 … Inside an MPN a set of MPs is connected in a finite state machine like style …

Increasing the Role of Data Analytics in m-Learning Conversational Applications
D Griol, Z Callejas – Software Data Engineering for Network eLearning …, 2018 – Springer
… The simplest dialog management models are based on finite-state machines (each state represents a state of dialogue and the corresponding transitions indicate actions taken by the … dialog systems to provide help in pathologies related to language and voice (Vaquero et al …

Alexa Prize-State of the Art in Conversational AI
C Khatri, A Venkatesh, B Hedayatnia, A Ram… – AI …, 2018 – search.proquest.com
… Anaphora resolution is important for downstream tasks such as question answering and information extraction in multiturn dialogue systems … 2017),4 built finite-state machines (FSMs) (Wright 2005) for addressing spe- cific modules such as movies, sports, and others …

Agile Behaviour Design: A Design Approach for Structuring Game Characters and Interactions
SE Gaudl – arXiv preprint arXiv:1803.01631, 2018 – arxiv.org
… A system based on finite-state machines increases its complexity ex- ponentially, even in the average case (normal design), which renders … can be ordered (5) by clustering actions and senses under specific feature groups such as NPC movement, dialogue system, or combat …

Iris: A conversational agent for complex tasks
E Fast, B Chen, J Mendelsohn, J Bassen… – Proceedings of the …, 2018 – dl.acm.org
… A Programming Model for Conversation Iris draws upon many existing programming abstractions to support open-ended command combination. Previous dialog systems have used automata, or state machines [48], to model conversation …

Deep Learning in Natural
L Deng, Y Liu – Springer
… Tur, Asli Celikyilmaz, Xiaodong He, Dilek Hakkani-Tür and Li Deng 3 Deep Learning in Spoken and Text-Based Dialog Systems … DSSM Deep structured semantic model DST Dialog state tracking EL Entity linking EM Expectation maximization FSM Finite state machine xv …

Machine learning and systems for building the next generation of EDA tools
M Pandey – Proceedings of the 23rd Asia and South Pacific Design …, 2018 – dl.acm.org
… machines from Input-Output Traces have been presented in literature including [27,28]. Fig 4. Specification and Constraint Mining [27] B. Expert Helper for Automated Troubleshooting Advances in natural language processing have made possible automated dialogue systems …

Conversational ai: The science behind the alexa prize
A Ram, R Prasad, C Khatri, A Venkatesh… – arXiv preprint arXiv …, 2018 – arxiv.org
… Anaphora resolution is important for downstream tasks such as question answering and information extraction in multi-turn dialog systems … Few teams such as Magnus (Prabhumoye et al., 2017) even built Finite State Machines (FSMs) (Wright, 2005) for addressing specific …

Permugram Language Models
G Ernst – minet.uni-jena.de
… (6). The main problem with permugram modeling is to characterize a suitable subclass of nite- state machines which … Of course, only very restricted subsets of the permutation space PT can be expected to be modeled by a nite state machine of reasonable size …

Creating New Technologies for Companionable Agents to Support Isolated Older Adults
CL Sidner, T Bickmore, B Nooraie, C Rich… – ACM Transactions on …, 2018 – dl.acm.org
… The research team started out using the collaborative dialog system Disco … There are no restrictions in DiscoRT on the internal implementation of a schema, and the AlwaysOn schemas vary from state machines implemented in Java to programs written in the specialized …

Towards learning transferable conversational skills using multi-dimensional dialogue modelling
S Keizer, V Rieser – arXiv preprint arXiv:1804.00146, 2018 – arxiv.org
… Figure 1: Typical dialogue system architecture, contrasting a conventional statistical dialogue manager with a multi-di- mensional version … as user informed and system confirmed) of user goal item hy- potheses, which are updated according to a finite state machine similar to the …

Empowering Chatbots With Business Intelligence By Big Data Integration
S Reshmi, K Balakrishnan – International Journal of Advanced …, 2018 – researchgate.net
… Such an assistant may basically consist of a dialog system, an avatar, as well an expert system to process queries efficiently … Pattern matching, finite-state- machines and frame-based models are the main methodologies of conversional agent design [2]. Many research works …

ScripTale: generation of procedural narrative
L Ripoll Galan – 2018 – upcommons.upc.edu
… 40 5.2.2. States Editor 42 5.2.3. Relationships Editor 45 5.2.4. Dialogue System 46 5.2.5. Characters 47 5.2.6. Messages and actions 48 5.2.7. Emotions 49 5.3 … 53 5.4.2. States Editor 54 5.4.3. Relationships Editor 55 5.4.4. Dialogue System 56 5.4.4. Characters 56 3 Page 5 …

Engineering and user experience of chatbots in the context of damage recording for insurance companies
J Götzer – 2018 – elib.uni-stuttgart.de
… 75 6.3 State machine for controlling claim questionnaires … 61 RL reinforcement learning. 69 SDA specialized digital assistant. 32, 34, 37 SDS spoken dialog system. 33 SLU spoken language understanding. 33 STT speech-to-text. 38 TTM time to market. 68 …

Safety First: Conversational Agents for Health Care
T Bickmore, H Trinh, R Asadi, S Olafsson – Studies in Conversational UX …, 2018 – Springer
… The most important considerations when designing health counseling dialogue systems, and the most difficult to address, is their potential to cause harm … systems, from a safety perspective, are those that model dialogue as a transition network (finite state machine) coupled with …

A Systematic Approach to Implementing Chatbots in Organizations–RTU Leo Showcase
A Mislevics, J Grundspenkis, R Rollande – ceur-ws.org
… Flow-based conversation blocks are implemented in a form of a state machine. Each state is described by the message that is sent by the bot … Building Advanced Dialogue Managers for Goal-Oriented Dialogue Systems, arXiv:1806.00780 [cs], Jun. 2018 …

Crowdsourcing for Reminiscence Chatbot Design
N Svetlana, F Daniel, B Marcos, F Casati… – Conference on Human …, 2018 – re.public.polimi.it
… Crowd-Supported Chatbot Design Conversational Model Representation Conceptually, a simple model we can imagine for a chatbot is a state machine (S, A, ?, ?, F), where S denotes the … Roving mind: a balancing act between open–domain and engaging dialogue systems …

Enhancing Inquisitiveness of Chatbots Through NER Integration
S Reshmi, K Balakrishnan – 2018 International Conference on …, 2018 – ieeexplore.ieee.org
… The basic architecture of such assistants comprises of a dialog system, and an expert system that efficiently process user queries … The main methodologies of conversional agent design includes pattern matching, finite-state-machines and frame-based models [1] . Researchers …

Partitioning POMDPs for multiple input types, and their application to dialogue managers
S Luz – 2018 – tara.tcd.ie
… social and psychological aspects of how a human reacts to computers. Spoken dialogue systems have 4 Page 11 … The simplest type of dialogue manager uses a finite-state machine (sometimes called a finite state automaton, or FSA) as the underlying architecture …

Crowdsourcing for Reminiscence Chatbot Design
S Nikitina, F Daniel, M Baez, F Casati – arXiv preprint arXiv:1805.12346, 2018 – arxiv.org
… Crowd-Supported Chatbot Design Conversational Model Representation Conceptually, a simple model we can imagine for a chatbot is a state machine (S, A, ?, ?, F), where S denotes the states (a state includes … Guardian: A crowd- powered spoken dialog system for web apis …

MathBot: Transforming Online Resources for Learning Math into Conversational Interactions
J Grossman, Z Lin, H Sheng, JTZ Wei, JJ Williams… – footprints.stanford.edu
… Page 3. finite-state machine [6, 33, 35], where user responses update the conversation state according to a preset transition graph … In this rule-based system, the state of the con- versation is represented as a finite state machine (FSM) …

Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize
C Khatri, B Hedayatnia, A Venkatesh, J Nunn… – arXiv preprint arXiv …, 2018 – arxiv.org
… including the CoBot (conversational bot) toolkit, topic and dialog act detection models, conversation evaluators, and a sensitive content detection model so that the competing teams could focus on building knowledge-rich, coherent and engaging multi-turn dialog systems …

The Design of a Debugger Unit for a RISC Processor Core
N Velguenkar – 2018 – scholarworks.rit.edu
… 40 References 42 I Source Code I-1 Page 10. List of Figures 2.1 JTAG TAP Overview [2] . . . . 12 2.2 Test Access Port Controller State Machine[3] . . . . 14 4.1 System Overview … 26 4.6 Debug State Machine …

Attentive Speaking. From Listener Feedback to Interactive Adaptation
H Buschmeier – 2018 – pub.uni-bielefeld.de
… Timo Baumann, David Schlangen, Casey Kennington, and Spyros Kousidis from Bielefeld’s Dialogue Systems group for joint work on incremental and adaptive output gener- ation in dynamic situations. ? Zofia Malisz, Petra Wagner, and Joanna Skubisz for xiii Page 16 …

A Situated Dialogue System for Learning Structural Concepts in Blocks World
I Perera, J Allen, CM Teng, L Galescu – Proceedings of the 19th Annual …, 2018 – aclweb.org
… Foundalis, 2006) and reinforcement learning (Ramon et al., 2007), we are unaware of any prior work in the context of dialogue systems … Towards this end we focus on finite state machine language models given the nature of assertions our system understands, but we may have …

Sensornet: A scalable and low-power deep convolutional neural network for multimodal data classification
A Jafari, A Ganesan, CSK Thalisetty… – … on Circuits and …, 2018 – ieeexplore.ieee.org
… Fig. 14-A shows convolution block. As is shown, convolu- tion block contains one multiplier, one adder/subtractor, one cache for saving filters, input feature maps and output feature maps, a few registers, multiplexers and a state machine block …

Continuous density hidden markov model for hindi speech recognition
S Sinha, SS Agrawal, A Jain – GSTF Journal on Computing (JoC), 2018 – dl6.globalstf.org
… huge success and its implementation domain has also expanded from simplest system of digit recognition to spontaneous dialogue systems.Such growth is … in the time series that can be discretely or continuously distributed.It is visualized as a finite state machine which uses a …

Can a Chatbot Determine My Diet?: Addressing Challenges of Chatbot Application for Meal Recommendation
A Fadhil – arXiv preprint arXiv:1802.09100, 2018 – arxiv.org
… or IoT (Internet of Things) devices to handle tasks, or it could be rule-based and use finite state machine to accomplish … That said, having intent detection capabilities, dialogue system and strong NLP component can increasingly enhance the linguistic capabilities for the bot …

Mastering C++ Game Development: Create professional and realistic 3D games using C++ 17
M MacDonald – 2018 – books.google.com
… a scripting language 226 Why a scripting language 227 Introducing LUA 229 Implementing LUA 231 Building a dialog system 235 Constructing … Table of Contents Motion and pathfinding 255 What game AI is not 255 Making decisions 256 AI state machines 257 Decision trees …

Possible Scientific-Technical Solutions to the Problem of Giving Early Warning
S Petrenko – Big Data Technologies for Monitoring of Computer …, 2018 – Springer
… Dialog systems models and methods … The development of these solutions is done with Java programming language applying the JMS machine, which is used to transmit asynchronous messages between finite-state machines (FSM) … Sensor finite-state machine (sensor FSM) …

Design and Evaluation of a Collaborative Virtual Environment (CoMove) for Autism Spectrum Disorder Intervention
L Zhang, Q Fu, A Swanson, A Weitlauf… – ACM Transactions on …, 2018 – dl.acm.org
… The controller component of CoMove was implemented using a Finite State Machine (FSM) with the objective to (i) manage multiple collaborative games to facilitate sequential interactions, information sharing, and simultaneous interactions and (ii) provide appropriate …

Flipper 2.0: A Pragmatic Dialogue Engine for Embodied Conversational Agents
J van Waterschoot, M Bruijnes, J Flokstra… – Proceedings of the 18th …, 2018 – dl.acm.org
… each pattern is a good approach for working with Flipper depending, among other things, on which stage of development the dialogue system is in … Turn-taking for example can be done by a state- machine which regulates turns based on current speech activity of the user and …

A Scalable Architecture to Design Multi-modal Interactions for Qualitative Robot Navigation
F Mastrogiovanni – AI* IA 2018–Advances in Artificial Intelligence …, 2018 – books.google.com
… voice), and eventu- ally performs a deictic gesture, the relative inputs are provided to the Command Logic component, implemented as a finite state machine … ACM (2014) 8. Lucignano, L., Cutugno, F., Rossi, S., Finzi, A.: A dialogue system for multimodal human-robot interaction …

Chatbot integration within Sitecore Experience Platform
G Albertengo, R Di Vittorio – webthesis.biblio.polito.it
… 27 2.1 DeepQA Architecture . . . . . 34 2.2 Finite-state machine for task-oriented chatbot . . . . . 39 2.3 Sequence to sequence model for answers generation . . 54 3.1 Azure Bot Service . . . . . 57 3.2 Bot Developer Portal …

Conversational memory network for emotion recognition in dyadic dialogue videos
D Hazarika, S Poria, A Zadeh, E Cambria… – Proceedings of the …, 2018 – aclweb.org
… properties. Yang et al., 2011, study patterns for emotion transitions and show the evidence of emotional inertia. Xiaolan et al., 2013, use finite state machines to model tran- sitions using stimuli and personality characteristics. Our …

A Scalable Architecture to Design Multi-modal Interactions for Qualitative Robot Navigation
L Buoncompagni, S Ghosh, M Moura… – … Conference of the …, 2018 – Springer
… and eventually performs a deictic gesture, the relative inputs are provided to the Command Logic component, implemented as a finite state machine … ACM (2014)Google Scholar. 8. Lucignano, L., Cutugno, F., Rossi, S., Finzi, A.: A dialogue system for multimodal human-robot …

Early prediction for physical human robot collaboration in the operating room
T Zhou, JP Wachs – Autonomous Robots, 2018 – Springer
… 2.3 Automatic turn-taking recognition Machine learning techniques have been applied to recognize turn-taking events automatically, mainly for spoken dialog systems … Fig. 4 Finite state machine to represent surgeon’s states. The black dot indicates initial state …

Learning Task-Oriented Dialog with Neural Network Methods
B Liu – 2018 – bingliu.me
… Tiancheng Zhao thanks for all the in-depth discussions on spoken dialog system both in research and in practice. Wonkyum Lee, Jungsuk Kim, Avneesh … 2.1 Task-Oriented Dialog Systems In this section we review the conventional architecture for task-oriented dialog systems …

Improving Search Through A3C Reinforcement Learning Based Conversational Agent
M Aggarwal, A Arora, S Sodhani… – International Conference …, 2018 – Springer
… Often task oriented dialogue systems are difficult to train due to absence of real conversations and subjectivity involved in measuring shortcomings and … The virtual user is modeled as a finite state machine by extracting conditional probabilities – P(User Action u| History h of User …

CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling
N Miao, H Zhou, L Mou, R Yan, L Li – arXiv preprint arXiv:1811.10996, 2018 – arxiv.org
… 2017, CBS) utilizes a finite-state machine to assist search- ing. Post and Vilar (2018) and Hasler et al … It has been previously explored in var- ious applications including question answering (Yin et al. 2016) and dialog systems (Mou et al. 2016) …

Social Behavior Learning with Realistic Reward Shaping
Y Gao, F Yang, M Frisk, D Hernandez, C Peters… – arXiv preprint arXiv …, 2018 – arxiv.org
… Both approaching and leaving behaviors are considered in [38], where a finite state machine is utilized in the transitions between different social behaviors. Jan et al … 1334–1373, 2016. [4] E. Ferreira and F. Lefevre, “Reinforcement-learning based dialogue system for human …

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
I Gurevych, Y Miyao – Proceedings of the 56th Annual Meeting of the …, 2018 – aclweb.org
Page 1. ACL 2018 The 56th Annual Meeting of the Association for Computational Linguistics Proceedings of the Conference, Vol. 1 (Long Papers) July 15 – 20, 2018 Melbourne, Australia Page 2. Diamond Sponsors: Platinum Sponsors: Gold Sponsors: ii Page 3. Silver Sponsors …

Efficient Extraction of Named Entities from New Domains Using Big Data Analytics
CJ Saju, S Ravimaran – Journal of Computational and …, 2018 – ingentaconnect.com
… time applications such as Language Modeling,29 website translations,33 Sentiment analysis,36 Digital Assistants,31 Speech Recognition,27 Dialog systems,34 Spelling … Let l be the set of FSM (Finite State Machine) states in which each state is associated with a label L (such …

An Eye Gaze Model for Controlling the Display of Social Status in Believable Virtual Humans
M Nixon, S DiPaola, U Bernardet – 2018 IEEE Conference on …, 2018 – ieeexplore.ieee.org
… [29] proposed a parametric gaze and head movement model that is linked with the emotional state machine developed at … By combining this with a chatbot-driven dialog system, we created a job interview simulator with two different variations on the character’s eye gaze …

Semantic Failover in Software-Defined Networking
SW Hsueh, TY Lin, WI Lei, CLP Ngai… – 2018 IEEE 23rd …, 2018 – ieeexplore.ieee.org
… controller failover. Existing solutions have been relying on state machine replication to achieve consistency. They require both the active controller and the standby controller to be of the same type or based on the same design. In …

Verbal Route Descriptions in Navigation of People with Visual Impairments
J Balata – 2018 – researchgate.net
Page 1. Czech Technical University in Prague Faculty of Electrical Engineering Department of Computer Graphics and Interaction Verbal Route Descriptions in Navigation of People with Visual Impairments Doctoral Thesis Ing. Jan Balata …

A User Simulator Architecture for Socially-Aware Conversational Agents
A Jain, F Pecune, Y Matsuyama… – Proceedings of the …, 2018 – articulab.hcii.cs.cmu.edu
… There also has been some work on user simulators to train socially-aware dialog systems … 4.6.2 Task Reasoner . We constructed the task reasoner based on the Finite State Machine (FSM) used to construct the rule-based version of SARA deployed in the conference …

Inferring Extended Probabilistic Finite-State Automaton Models from Software Executions
SS Emam, J Miller – ACM Transactions on Software Engineering and …, 2018 – dl.acm.org
… Their proposed method infers a model by observing program executions and concisely summarizing frequent interaction patterns as state machines … 4:5 Dallmeier et al. [33] suggest a technique to construct a state machine that would summarize object behavior …

An Integrated Architecture for Discourse: Generation, Interpretation, and Recipe Acquisition
N Green, JF Lehman – cs.cmu.edu
… This discourse architecture has been implemented as part of the NL-Soar dialogue system (Lehman, Van Dyke, Lonsdale, Green, & Smith, sub- mitted … Finite state machine (FSM) approaches have been proposed as a fast and e cient sup- plement to plan-based approaches to …

Field Trial Analysis of Socially Aware Robot Assistant
F Pecune, J Chen, Y Matsuyama… – Proceedings of the 17th …, 2018 – dl.acm.org
… NLU also extracted keywords using named entity recognition and a list of predefined keywords. The Task Reasoner was initially designed as a probabilistic finite state machine whose transitions are governed by a set of rules and learned probability distribution …

An on-line VAD based on Multi-Normalisation Scoring (MNS) of observation likelihoods
I Odriozola Sustaeta, H Rioja, I Concepción… – 2018 – addi.ehu.es
… In Mporas et al. (2010) the authors use Automatic Speech Recognition (ASR) technology with a VAD to develop a dialogue system in a motorcycle environment. Principi et al. (2015) describe an integrated system for processing voice emergency com …

An on-line VAD based on Multi-Normalisation Scoring (MNS) of observation likelihoods
I Odriozola, I Hernaez, E Navas – Expert Systems with Applications, 2018 – Elsevier
… It is profusely used in the development of all kinds of expert systems. In Mporas, Kocsis, Ganchev, and Fakotakis (2010) the authors use Automatic Speech Recognition (ASR) technology with a VAD to develop a dialogue system in a motorcycle environment …

Improving Test Execution Efficiency Through Clustering and Reordering of Independent Test Steps
B Walter, M Schilling, M Piechotta… – 2018 IEEE 11th …, 2018 – ieeexplore.ieee.org
… Each state can be either a point, line, area or n-dimensional volume in this space. The system can be seen as a finite state machine in the defined solution space. It contains a finite number of states and transitions between these states …

An Efficient Framework for Development of Task-Oriented Dialog Systems in a Smart Home Environment
Y Park, S Kang, J Seo – Sensors, 2018 – mdpi.com
… Quick Links. Open Access This article is: freely available; re-usable. Sensors 2018, 18(5), 1581; doi:10.3390/s18051581. Article. An Efficient Framework for Development of Task-Oriented Dialog Systems in a Smart Home … 3. Dialog Framework for Task-Oriented Dialog System …

Applying pragmatics principles for interaction with visual analytics
E Hoque, V Setlur, M Tory… – IEEE transactions on …, 2018 – ieeexplore.ieee.org
… Eviza supported pragmatics using a simple finite state machine (FSM) with the states defined by a weighted probabilistic distribution over the parse paths [35]. The resolution of phrasal segments occured using previous parse paths to maximize likelihood estimation …

Space-time algebra: a model for neocortical computation
JE Smith – Proceedings of the 45th Annual International …, 2018 – dl.acm.org
… It uses what is essential- ly WTA inhibition and consists of a single layer of excitato- ry neurons, with one neuron assigned to each class. Liquid State Machines [33][44] are based on the same principles as TNNs: temporal encoding and spiking neuron models …

Personality AI Development
J Wang, KV Nhan – 2018 – digitalcommons.wpi.edu
… AIs We used three algorithms: behavior tree, behavior tree with utility based decision maker, and finite state machine, and made four AIs each with personality of: aggressive, bullying, cowardly and tricky. All the AIs is put into an NPC monster called Nue in our game: Yokai …

A methodology for turn-taking capabilities enhancement in Spoken Dialogue Systems using Reinforcement Learning
H Khouzaimi, R Laroche, F Lefèvre – Computer Speech & Language, 2018 – Elsevier
… A state machine model is introduced in Raux and Eskenazi (2009) where the objective is to minimise speech gaps and overlaps between the system and the user … Skantze and Schlangen (2009) introduce an incremental dialogue system which asks the user to dictate a number …

Deep Learning in Conversational Language Understanding
G Tur, A Celikyilmaz, X He, D Hakkani-Tür… – Deep Learning in Natural …, 2018 – Springer
… management (RM) tasks. At this early stage, natural language understanding (NLU) techniques like finite state machines (FSMs) and augmented transition networks (ATNs) were applied for SLU (Woods 1983). The study of …

Induction of Emotional States in Educational Video Games through a Fuzzy Control System
CA Lara, H Mitre-Hernandez, J Flores… – IEEE Transactions on …, 2018 – ieeexplore.ieee.org
… Liu et al. [30] analyze physiological signals to infer the the player’s probable anxiety and the game difficulty level is automatically adjusted in real time by using a finite state machine. Different Affective Intelligent Tutor Systems (AITS) have been reported in the literature …

Automated dyadic data recorder (ADDR) framework and analysis of facial cues in deceptive communication
T Sen, MK Hasan, Z Teicher, ME Hoque – Proceedings of the ACM on …, 2018 – dl.acm.org
… audio from a game where users had to guess correct image by exchanging information between them using their dialogue system … The ADDR Framework comprises a videoconferencing online media server and a rudimentary video game state machine engine, which together …

Recurrent Neural Networks
CC Aggarwal – Neural Networks and Deep Learning, 2018 – Springer
“Democracy is the recurrent suspicion that more than half the people are right more than half the time.”— The New Yorker, July 3, 1944.

Towards a framework for computational persuasion with applications in behaviour change
A Hunter – Argument & Computation, 2018 – content.iospress.com
… Moves in a dialogue For considering the possible dialogues that might be generated by a pair of agents, a probabilistic finite state machine can represent the possible moves that each agent can make in each state of the dialogue assuming a set of arguments that each agent is …

Learning socio-communicative behaviors of a humanoid robot by demonstration
DC Nguyen – 2018 – hal.archives-ouvertes.fr
… 128 Page 11. viii Contents A Sensorimotor Calibration for Pointing 131 A.1 Comments . . . . . 132 B Finite State Machine of the RL/RI scenario 135 B.1 FSM . . . . . 135 …

Belieavable decision making in large scale open world games for ambient characters
T Plch – 2018 – dspace.cuni.cz
Page 1. ] Charles University in Prague Faculty of Mathematics and Physics DOCTORAL THESIS [ Tomáš PLCH Believable Decision Making in Large Scale Open World Games for Ambient Characters Department of Software and Computer Science Education …

CSIndexbr: Exploring the Brazilian Scientific Production in Computer Science
MT Valente, K Paixão, D Hafner, D Tran, A Irpan… – arXiv preprint arXiv …, 2018 – arxiv.org

A Statistical Approach To Speech Synthesis And Image Recognition Based On Hidden Markov Models
K Sawada – nitech.repo.nii.ac.jp
… In consequence, new services such as spo- ken dialogue system and biometrics authentication system have been developed … An hidden Markov model (HMM) is a finite state machine which generates a sequence of discrete time observations [26–28] …

The Performance Optimization of LTE Multimedia Broadcast Multicast Services Based on RObust Header Compression
C Jiang – 2018 – search.proquest.com
Page 1. The Performance Optimization of LTE Multimedia Broadcast Multicast Services Based on RObust Header Compression By CHEN JIANG BS (Huazhong University of Science and Technology) 2008 MS (Wichita State University) 2013 Dissertation …

Response Generation For An Open-Ended Conversational Agent
N Dziri – 2018 – era.library.ualberta.ca
… Over the past decade, dialogue systems have become omnipresent in our daily lives, assisting … models has shown promising results in solving problems such as scalability and language-independence that conventional dialogue system fail to cope with …

Automatic Image Captioning with Style
AP Mathews – 2018 – openresearch-repository.anu.edu.au
Page 1. Automatic Image Captioning with Style Alexander Mathews A thesis submitted for the degree of Doctor of Philosophy The Australian National University November 2018 Page 2. c Alexander Mathews 2018 Page 3. Except …

Deep Reinforcement Learning Hands-On: Apply modern RL methods, with deep Q-networks, value iteration, policy gradients, TRPO, AlphaGo Zero and more
M Lapan – 2018 – books.google.com
… Systems. He is a staff member on a Git-course, Practical_RL and Practical_DL, taught on-campus in HSE and YSDA. Oleg’s previous work experience includes working in Dialog Systems Group, Yandex, as Data Scientist. He …

Neural Networks for Narrative Continuation
M Roemmele – 2018 – roemmele.github.io
… of what became known as template-based generation. One historical example of the template-based approach was the dialogue system ELIZA (Weizenbaum, 1966). As one of the first ‘chatbots’, ELIZA was a program that acted as a psychother …

Learning to Interpret and Apply Multimodal Descriptions
T Han – 2018 – pub.uni-bielefeld.de
… Moreover, I show that abstract deictic gestures not only lead to better understanding of spatial descriptions, but also result in earlier correct decisions of the system, which can be used to trigger immediate reactions in dialogue systems …

Proof Search in Multi-Agent Dialogues for Modal Logic
M Sticht – 2018 – books.google.com
Page 1. Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg 32 Proof Search in Multi-Agent Dialogues for Modal Logic Martin Sticht Page 2. 32 Schriften aus der …

Zero-Effort Technologies: Considerations, Challenges, and Use in Health, Wellness, and Rehabilitation
J Boger, V Young, J Hoey, T Jiancaro… – Synthesis Lectures on …, 2018 – morganclaypool.com
Page 1. Zero-Effort Technologies Considerations, Challenges, and Use in Health, Wellness, and Rehabilitation, Second Edition Jennifer Boger Victoria Young Jesse Hoey Tizneem Jiancaro Alex Mihailidis BO GE R • E T AL ZE R OE FFOR T T ECH NOL O GIE S …