Natural Language Generators & Dialog Systems


Notes:

In Natural Language Generation the overall generation task is traditionally divided into two separate phases.  In strategic generation it is decided “What to say”, ie which propositions are to be expressed in a still language-independent representation. Tactical generation then deals with the “How to say”, ie it is responsible to come up with the concrete wording.

See also:

Natural Language Generation


Toward Habitable Assistance from Spoken Dialogue Systems. SL Epstein, RJ Passonneau, T Ligorio, JB Gordon – IAAI, 2012 – aaai.org … Across a broad range of real-world applications, people in- creasingly use spoken dialogue systems (SDSs). … Once the dialogue manager decides what to say, a template-based natural language generator converts the semantic representation to an orthographic string, which is … Related articles All 7 versions

Optimising natural language generation decision making for situated dialogue N Dethlefs, H Cuayáhuitl, J Viethen – Proceedings of the SIGDIAL 2011 …, 2011 – dl.acm.org … Abstract Natural language generators are faced with a multitude of different decisions during their generation process. … Williams (2008) presents an approach of combining Partially- Observable Markov Decision Processes with con- ventional dialogue systems. … Cited by 17 Related articles All 12 versions

Reinforcement learning for parameter estimation in statistical spoken dialogue systems F Jur?í?ek, B Thomson, S Young – Computer Speech & Language, 2012 – Elsevier … Cover image Cover image. Reinforcement learning for parameter estimation in statistical spoken dialogue systems ?. … Abstract. Reinforcement techniques have been successfully used to maximise the expected cumulative reward of statistical dialogue systems. … Cited by 24 Related articles All 13 versions

Statistical methods for building robust spoken dialogue systems in an automobile P Tsiakoulis, M Gašic, M Henderson… – Proceedings of the …, 2012 – mi.eng.cam.ac.uk … The abstract system dialogue act a is converted to an appropriate utterance m by a natural language generator and then converted to speech x by a HMM-based speech synthesizer. The spoken dialogue system is implemented using the ATK platform (http://mi.eng.cam.ac.uk … Cited by 7 Related articles All 6 versions

Review of Dialogue Systems’ Methodologies G Kavitha, S Pande – Information Science and Applications ( …, 2013 – ieeexplore.ieee.org … The architecture of the corpus-based natural language dialogue system contains Natural Language Parser to analyze the input sentence … series of dialogues; Context Database contains dialogue acts like greetings, question, and so on; Natural Language Generator makes the … Related articles All 3 versions

Weakly and strongly constrained dialogues for language learning C Gardent, A Lorenzo… – the 14th annual …, 2013 – hal.archives-ouvertes.fr … dialogue system, the dialogue paths contained in the training corpus are used to decide on the next dialogue move. In a first step, learner’s moves are labelled with the meaning rep- resentation associated to them by the grammar un- derlying the natural language generator … Cited by 1 Related articles All 14 versions

First Steps in Chat-Based Negotiating Agents I Zuckerman, E Segal-Halevi, A Rosenfeld… – Next Frontier in Agent- …, 2015 – Springer … We constructed a natural language system based on a standard dialog system architecture [14], as described in Fig.5. We illustrate the system with a running example from our experimental domain, where the human is an employer and the agent is a job-candidate, and they …

A statistical spoken dialogue system using complex user goals and value directed compression PA Crook, Z Wang, X Liu, O Lemon – … of the Demonstrations at the 13th …, 2012 – dl.acm.org … The spoken dialogue system has knowl- edge about some set of objects where these ob- jects have attributes and these attributes … a Policy- Executor server that selects actions based on the compressed estimated state, and a template based Natural Language Generator server … Cited by 2 Related articles All 14 versions

Natural language generation in the context of the semantic web N Bouayad-Agha, G Casamayor, L Wanner – Semantic Web, 2014 – IOS Press Page 1. UNCORRECTED PROOF Semantic Web 00 (20xx) 1–21 1 DOI 10.3233/SW-130125 IOS Press 1 52 2 53 3 54 4 55 5 56 6 57 7 58 8 59 9 60 10 61 11 62 12 63 13 64 14 65 15 66 16 67 17 68 18 69 19 70 20 71 21 72 22 73 23 74 24 75 25 76 26 77 27 78 28 79 29 80 30 … Cited by 7 Related articles All 4 versions

A model for synthesizing a combined verbal and nonverbal behavior based on personality traits in human-robot interaction A Aly, A Tapus – Proceedings of the 8th ACM/IEEE international …, 2013 – dl.acm.org … human’s personality traits through a psycholinguistic analysis of the spoken language, then it uses PERSONAGE natural language generator that tries … field of user modeling (ie understanding user’s beliefs, goals and plans) in artificial intelligence dialog systems, and illustrated … Cited by 14 Related articles All 2 versions

Natural actor and belief critic: Reinforcement algorithm for learning parameters of dialogue systems modelled as POMDPs F Jur?í?ek, B Thomson, S Young – ACM Transactions on Speech and …, 2011 – dl.acm.org … Speech understanding usually consists of a speech recognizer and a semantic parser, and speech generation requires a natural language generator and a speech synthesizer. The main challenge in spoken dialogue systems is to robustly handle communication errors … Cited by 22 Related articles All 9 versions

Prosodic Entrainment in an Information-Driven Dialog System. A Fandrianto, M Eskenazi – INTERSPEECH, 2012 – cs.cmu.edu … 2. Approach The Let’s Go spoken dialog system currently deployed in the City of Pittsburgh gives bus timetable information to the gen- eral public. … This method requires changes in the DM, the natural language generator (NLG), and the synthesizer (TTS). … Cited by 6 Related articles All 4 versions

Natural language generation and semantic web technologies N Bouayad-Agha, G Casamayor… – Semantic Web …, 2012 – semantic-web-journal.org … In Janzen and Maas’s dialogue system [68], NLG starts from a layered OWL-DL knowledge repository that contains a complete model about question answer- ing and an instantiation of the domain model (in their case, in-store shopping dialogues). … Cited by 3 Related articles All 2 versions

An adaptive dialogue system for assessing post traumatic stress disorder A Papangelis, R Gatchel, V Metsis… – Proceedings of the 6th …, 2013 – dl.acm.org … 3. ADAPTIVE DIALOGUE SYSTEM (ADS) In this Section, we present our system, targeted for in- teracting with PTSD patients and making an … to generate the system’s output in natural-language, we used simpleNLG [5], which is a pub- licly available natural language generator. … Cited by 4 Related articles All 2 versions

Alex: A Statistical Dialogue Systems Framework F Jur?í?ek, O Dušek, O Plátek, L Žilka – Text, Speech and Dialogue, 2014 – Springer … our system is modular and consists of the traditional Spoken Dialogue System (SDS) components: an automatic speech recogniser (ASR) including a voice activity detector, spoken language understanding (SLU), dialogue manager (DM), natural language generator (NLG), and … Related articles All 3 versions

BEETLE II: Deep Natural Language Understanding and Automatic Feedback Generation for Intelligent Tutoring in Basic Electricity and Electronics M Dzikovska, N Steinhauser, E Farrow, J Moore… – International Journal of …, 2014 – Springer … Interestingly, while there are many computer-based tutoring systems that use simulation as a training tool (eg de Jong and van Joolingen 1998) and tutorial dialogue systems that ask students to provide justifications for problem solving steps (Aleven et al. 2002; Khuwaja et al. … Cited by 1 Related articles All 4 versions

Dialogue System Theory B Thomson – Statistical Methods for Spoken Dialogue Management, 2013 – Springer … A simplified form of semantic information is clearly an important input to the dialogue system. … The final stage of the dialogue cycle is to convey the system’s response to the user. This is done in two steps. First a natural language generator converts the system dialogue act to text. … Cited by 1 Related articles All 2 versions

From rule-based to data-driven lexical entrainment models in spoken dialog systems J Lopes, M Eskenazi, I Trancoso – Computer Speech & Language, 2015 – Elsevier … Lexical entrainment has been successfully tested in a text-based dialog system (Matessa, 2003), both in terms of performance and … parser (Ward and Issar, 1994), the Helios confidence annotator (Bohus and Rudnicky, 2002), the natural language generator Rosetta (Rudnicky et … Cited by 1 Related articles

User Adaptation in Automotive Environments M Sun, A Rudnicky, U Winter – … in Human Aspects of Road and …, 2012 – books.google.com … Keywords: spoken dialog system, speech recognizer, parser, dialog manager, natural language generator 1 INTRODUCTION Contemporary car drivers and their passengers (collectively, users) have at their disposal a large variety of services, including access to a car’s … Related articles

A novel approach for data fusion and dialog management in user-adapted multimodal dialog systems D Griol, J Garcia-Herrero… – … Fusion (FUSION), 2014 …, 2014 – ieeexplore.ieee.org … With this premise, a dialog system can be described in terms of the following modules. … The Natural Language Generator module (NLG) receives a formal representation of the system action and generates a user response that can include multi- modal information (video, data … Related articles

What if everyone could do it?: a framework for easier spoken dialog system design P Milhorat, S Schlögl, G Chollet, J Boudy – Proceedings of the 5th ACM …, 2013 – dl.acm.org … Since the goal of our framework is to support the development of dialog systems for specific ap- plication scenarios we decided to integrate Disco [21, 22], a representative of the later approach. … Figure 5. Natural Language Generator templates … Cited by 2 Related articles All 3 versions

Predicting user satisfaction in spoken dialog system evaluation with collaborative filtering Z Yang, GA Levow, H Meng – Selected Topics in Signal …, 2012 – ieeexplore.ieee.org … I. INTRODUCTION A spoken dialog system (SDS) is a computer system which supports human-computer conversations in a restricted domain. … response, the natural language generator is responsible for translating the representation of the response … Cited by 4 Related articles All 8 versions

A speech-based conversation system for accessing agriculture commodity prices in Indian languages GV Mantena, S Rajendran, B Rambabu… – Hands-free Speech …, 2011 – ieeexplore.ieee.org … Natural Language Generator … output of an ASR using confidence scoring techniques like normalized likelihood scores, counts from N- best hypothesis, language model scores, parsing related etc [2]. System can also use features from various levels of dialogue system like decod … Cited by 7 Related articles All 5 versions

Beyond audio and video retrieval: towards multimedia summarization D Ding, F Metze, S Rawat, PF Schulam… – Proceedings of the 2nd …, 2012 – dl.acm.org … Otherwise it equals zero. 4. NATURAL LANGUAGE GENERATOR We have implemented a template-based Natural Language Generation (NLG) system to generate written text about a given video. Figure 1 shows the general system architecture. … Cited by 19 Related articles

A Semi-Supervised Clustering Approach for Semantic Slot Labelling H Cuayáhuitl, N Dethlefs, H Hastie – 2014 – macs.hw.ac.uk … obtained in this way can serve as training data for various NLP components, such as semantic parsers and natural language generators within interactive … using the method described above; an (5) perform an extrinsic evaluation with an end-to-end spoken dialogue system [34]. … Cited by 1 Related articles All 2 versions

Entrainment in pedestrian direction giving: How many kinds of entrainment Z Hu, G Halberg, C Jimenez, M Walker – Proc. IWSDS, 2014 – uni-ulm.de … In this paper, we describe a natural language generator PERSONAGE- PRIMED, which can produce utterances entrained to a range of utterance features used in prior … Humans also entrain to dialog systems, in choice of vocabulary, speech rate and pause length [36, 12, 28]. … Cited by 3 Related articles

Comparison and combination of lightly supervised approaches for language portability of a spoken language understanding system B Jabaian, L Besacier, F Lefevre – Audio, Speech, and …, 2013 – ieeexplore.ieee.org … natives but with weak economic situation). However, portability of a spoken dialogue system (SDS) to a … This response is transferred to the user with the help of a natural language generator (NLG) and a text to speech synthesizer (TTS). A. SDS Portability … Cited by 8 Related articles All 5 versions

The Geranium System: Multimodal Conversational Agents for E-learning D Griol, JM Molina, AS de Miguel – Distributed Computing and Artificial …, 2014 – Springer … the system answer generator produces the HTML output for the GUI and the template to be used by the natural language generator to obtain … Expert Systems with Applications 38(5), 5486–5499 (2011) 3. Roda, C., Angehrn, A., Nabeth, T.: Dialog systems for Advanced Learning … Related articles All 3 versions

Negochat: A chat-based negotiation agent A Rosenfeld, I Zuckerman, E Segal-Halevi… – Proceedings of the …, 2014 – dl.acm.org … 5. NEGOCHAT’S NATURAL LANGUAGE Our natural language system has a standard dialog system ar- chitecture, described in Figure 1. We illustrate … The Natural Language Generator (NLG) translates the set of dialog acts, created by the DM, to a single natural language sen … Cited by 3 Related articles All 13 versions

NegoChat-A: a chat-based negotiation agent with bounded rationality A Rosenfeld, I Zuckerman, E Segal-Halevi… – Autonomous Agents and …, 2015 – Springer … 123 Page 12. Auton Agent Multi-Agent Syst Fig. 1 Dialog system architecture. Example starts at the top-left corner … The Natural Language Generator (NLG) translates the set of dialog acts, created by the DM, to a single natural language sentence, that is sent to the human. …

Building the next generation of personal digital assistants P Milhorat, S Schlogl, G Chollet, J Boudy… – … for Signal and …, 2014 – ieeexplore.ieee.org … In order to approach the above discussed areas of improve- ment, a Spoken Dialog System (SDS) has been implemented. … Here the Natural Language Generator (NLG) is currently based on a fairly simple template selection process which randomly chooses text utterances … Cited by 1 Related articles All 2 versions

Towards a Truly Statistical Natural Language Generator O Dušek – 2013 – ufal.ms.mff.cuni.cz … FLAIRS Demberg, V. and Moore, J. 2006. Information presentation in spoken dialogue systems. EACL FUG Elhadad, M. and Robin, J. 1996. … ACL Ond?ej Dušek Towards a Truly Statistical Natural Language Generator Page 17. . . . . . … Related articles All 3 versions

Framework for Human Computer Interaction for Learning Dialogue Strategies using Controlled Natural Language in Information Systems M Ahmad – 2012 – dspaces.uok.edu.in … Lot of research has been done in building real spoken Dialogue Systems which can interact with humans using voice interactions and help in per- … of optimizing the dialogue management strategy selection in the Spoken Dialogue system prototype design. … Related articles All 6 versions

Developing multimodal conversational agents for an enhanced e-learning experience D Griol, JM Molina, AS de Miguel – ADCAIJ: Advances in Distributed …, 2014 – rca.usal.es … This way, different people can help in the development of the system without requiring an expert knowledge in dialogue systems. … the system answer generator produces the HTML output for the GUI and the template to be used by the natural language generator to obtain the … Related articles All 4 versions

POMDP concept policies and task structures for hybrid dialog management S Varges, G Riccardi, S Quarteroni… – Acoustics, Speech and …, 2011 – ieeexplore.ieee.org … rate.The ap- proach has been evaluated in several user studies in a tourist information domain involving 20 subjects and four different dialog systems. … top-ranked action am is selected by the system, ie it is exploiting the policy, and passed to the natural language generator (NLG … Cited by 5 Related articles All 4 versions

A Decision Theoretic Approach to Natural Language Generation N McKinley – 2014 – etd.ohiolink.edu … We believe that if this algorithm were developed further, it could be useful as the final step of a dialog system, or useful in generation situations where flexibility of the generation system is crucial. At present, it is already useful as the output stage of a simple dialog system. An … Related articles All 9 versions

Assessing user simulation for dialog systems using human judges and automatic evaluation measures H Ai, D Litman – Natural Language Engineering, 2011 – Cambridge Univ Press … 1 See problem statements in Appendix A and sample dialogs in Appendix B. 2 This size of experiment is comparable to most other dialog system experiments that involve human … (2005) when they collected human judges’ ratings on their natural language generator and by DUC … Related articles All 4 versions

Real-time conversational crowd assistants WS Lasecki – CHI’13 Extended Abstracts on Human Factors in …, 2013 – dl.acm.org … we can train multiple parts of an automated dialog system, including the parser (which converts from natural language to semantic frame), dialog manager (which determines what to do and how to respond to the user), and the natural language generator (which converts a set of … Cited by 1 Related articles All 2 versions

Incremental generation for real-time applications A Kilger, W Finkler – 2011 – scidok.sulb.uni-saarland.de … Obviously, there is need for a more formal de nition of the term `incremental generation.’ We begin by giving an application{independent de nition of incremental processing which we use for the speci cation of an incremental natural language generator. … Cited by 60 Related articles All 11 versions

Generating context-sensitive ECA responses to user barge-in interruptions N Crook, D Field, C Smith, S Harding, S Pulman… – Journal on Multimodal …, 2012 – Springer … Our system design there- fore needed to account for phenomena that task-based spo- ken language dialogue systems (SLDs) (eg, [2–4]) are … The ASM’s plan forms the input to the Natural Language Generator (NLG), which out- puts surface form to the ECA for performance to … Cited by 4 Related articles All 9 versions

Bringing context-aware access to the web through spoken interaction D Griol, J Carbo, JM Molina – Applied intelligence, 2013 – Springer … our dialog manager represents the dialogs as sequences of pairs (Ai, Ui), where Ai is the output of the dialog system (the system … Once the dialog manager has selected which is the next system action, the Natural Language Generator module (NLG) transforms this action into an … Cited by 6 Related articles All 6 versions

How Was Your Day? Evaluating a Conversational Companion D Benyon, B Gamback, P Hansen… – … IEEE Transactions on, 2013 – ieeexplore.ieee.org … next system turn, which is generated by the plan-based Affective Strategy Module (ASM) [10] and handed to Natural Language Generator (NLG). … Rather than singular, focused tasks, as seen in the majority of deployed dialogue systems, fully devel- oped companions can have a … Cited by 1 Related articles All 12 versions

An Architecture to Develop Multimodal Educative Applications with Chatbots D Griol, Z Callejas – Int J Adv Robotic Sy, 2013 – cdn.intechopen.com … Keywords Multimodal Dialogue Systems, Chatbots, Educative Technology 1. Introduction … These aspects can be addressed by means of dialogue systems by establishing a more engaging and human-like relationship between the students and the system. … Cited by 4 Related articles All 3 versions

Alex: Bootstrapping a Spoken Dialogue System for a New Domain by Real Users O Dušek, O Plátek, L Žilka… – 15th Annual Meeting of …, 2014 – anthology.aclweb.org … Our spoken dialogue system framework is freely available on GitHub2 and designed for easy adaptation to new … SDS components: automatic speech recognizer (ASR), spoken language under- standing (SLU), dialogue manager (DM), natural language generator (NLG), and a … Related articles All 6 versions

Data mining to support human-machine dialogue for autonomous agents SL Epstein, R Passonneau, T Ligorio… – Agents and Data Mining …, 2012 – Springer … 135 Fig. 1. A traditional pipeline architecture for spoken dialogue systems. Heavy arrows emphasize the pipeline … A decision to speak is forwarded to the natural language generator (NLG), which formulates text and then passes it to a text-to-speech (TTS) module. … Cited by 1 Related articles All 12 versions

Evaluation of the KomParse Conversational Non-Player Characters in a Commercial Virtual World. T Klüwer, F Xu, P Adolphs, H Uszkoreit – LREC, 2012 – lrec-conf.org … Moreover, frames are used to handle the task model of the dialogue system. … The query results are then turned into an abstract representation of the answer and spelt out by a natural-language generator (Adolphs et al., 2010). … Cited by 4 Related articles All 2 versions

Natural Language Generation from Graphs NT Dong, LB Holder – International Journal of Semantic Computing, 2014 – World Scientific Page 1. Natural Language Generation from Graphs Ngan T. Dong School of Electrical Engineering and Computer Science Washington State University Pullman, WA 99163, USA takura247@gmail.com Lawrence B. Holder School …

Dialogue POMDP components (part I): learning states and observations HR Chinaei, B Chaib-Draa – International Journal of Speech Technology, 2014 – Springer … 1 Introduction Spoken dialogue systems (SDSs) are systems which help the human user to accomplish a task using the spoken language. … The output includes natural language generator (NLG) and text-to-speech (TTS) components. … Cited by 1 Related articles All 4 versions

Development of a spoken dialogue system for accessing agricultural information in Telugu GV Mantena, S Rajendran, SV Gangashetty… – Proceedings of ICON- …, 2011 – ravi.iiit.ac.in … Index Terms: spoken dialogue system, speech recognition, multiple decoders, contextual infor- mation 1 Introduction … Speech Recognition Speech Synthesis Natural Language Understanding Natural Language Generator Manager Dialog Text Text Speech … Cited by 5 Related articles All 4 versions

Managing uncertainty within the KTD framework M Geist, O Pietquin – Proceedings of, 2011 – ejournal.narotama.ac.id … A spoken dialog system (SDS) generally aims at providing information to a user through natural language-based interactions. … speech recognizer and semantic parser), a dialogue manager and a speech generation component (natural language generator and speech synthesis … Cited by 15 Related articles All 22 versions

Beyond audio and video retrieval: topic-oriented multimedia summarization F Metze, D Ding, E Younessian… – International Journal of …, 2013 – Springer … UNQ(ti ) is 1 if ti is included in the unique word list of detected event. Otherwise it equals zero. 4 Natural language generator We have implemented a template-based NLG system to gen- erate written text about a given video. Figure 1 shows the general system architecture. … Cited by 3 Related articles All 2 versions

A case base planning approach for dialogue generation in digital movie design S Hajarnis, C Leber, H Ai, M Riedl, A Ram – Case-Based Reasoning …, 2011 – Springer … Finally, we use a simple natural language generator to deliver the full dialogue in natural language (4.4). Page 6. … 457 4.1 Dialogue Act Representation Dialogue acts are generally used to model and automatically detect discourse structure in dialogue systems. … Cited by 5 Related articles All 9 versions

Computational generation of referring expressions: A survey E Krahmer, K Van Deemter – Computational Linguistics, 2012 – MIT Press … 2008) needs to generate spatial descriptions for areas with low or high pollen levels (“the central belt and further North”), and a robot dialogue system that assembles construction toys together with a human user (Giuliani et al. … Cited by 77 Related articles All 14 versions

[BOOK] Statistical methods for spoken dialogue management B Thomson – 2013 – books.google.com … In Proceedings of SLT, 2010. B. Thomson, J. Schatzmann, K. Weilhammer, H. Ye, and S. Young. Training a real—world POMDP-based dialog system. … B. Thomson, J. Schatzmann, and S. Young. Bayesian update of dialogue state for robust dialogue systems. … Cited by 34 Related articles All 7 versions

Fusing Eye-gaze and Speech Recognition for Tracking in an Automatic Reading Tutor: A Step in the Right Direction? MH Rasmussen, ZH Tan – SLaTE, 2013 – forskningsbasen.deff.dk … I will then illustrate our use of such findings to build better educational dialogue systems. … After each move (ie each attempt to combine two treelets, or to reorder a branch), the system’s natural-language generator computes all possible grammatically well- formed sentences … Related articles All 5 versions

Parallel computing and practical constraints when applying the standard POMDP belief update formalism to spoken dialogue management PA Crook, B Roblin, HW Loidl, O Lemon – … in Spoken Dialogue Systems …, 2011 – Springer … RL-C. Delgado and T. Kobayashi (eds.), Proceedings of the Paralinguistic Information and its Integration in Spoken Dialogue Systems Workshop … The Natural Language Generator (NLG) then maps the DM’s action into natural language text which is then realised as spoken … Cited by 1 Related articles All 7 versions

Rhetorical robots: making robots more effective speakers using linguistic cues of expertise S Andrist, E Spannan, B Mutlu – Proceedings of the 8th ACM/IEEE …, 2013 – dl.acm.org Page 1. Rhetorical Robots: Making Robots More Effective Speakers Using Linguistic Cues of Expertise Sean Andrist, Erin Spannan, Bilge Mutlu Department of Computer Sciences, University of Wisconsin–Madison 1210 West … Cited by 6 Related articles All 5 versions

Evaluating the Perception of Personality and Naturalness in Computer Generated Utterances C McCormick – 2012 – scss.tcd.ie … Any one dialogue system, or conversational agent, is made up of various compo- nents, such as an automatic speech recognition unit, a natural language understanding unit, a natural language generator and possibly even a text-to-speech engine [9]. Ram- … Related articles All 3 versions

[BOOK] Natural language processing E Kumar – 2011 – books.google.com … xviii Contents 8.14 Multimodal Anaphora Resolution 174 8.14.1 The Centring Algorithm 175 9. NATURAL LANGUAGE GENERATION 178 9.1 Salient Issues in Natural Language Generation 179 9.2 Components of Natural Language Generator 181 9.3 Language Generation … Cited by 10 Related articles

Using the journalistic metaphor to design user interfaces that explain sensor data M Molina, E Parodi, A Stent – Human-Computer Interaction–INTERACT …, 2011 – Springer … Presentation Generation Content Planner Discourse Planner Data Analyzer Analysis Goals Graphic Generator Natural Language Generator User … on Natural Language Generation (2000) 7. Demberg, V., Moore, J.: Information presentation in spoken dialogue systems. … Cited by 2 Related articles All 7 versions

[BOOK] DIGUI: A Flexible Dialogue System for Guiding the User Interaction to Access Web Services MG Bermúdez, MG Vila – 2011 – cs.upc.edu Page 1. DIGUI: A Flexible Dialogue System for Guiding the User Interaction to Access Web Services PhD Thesis by … Chapter 2 Brief introduction to the state of the art in dialogue systems This chapter gives an introduction to dialogue systems. It focuses mainly on the topics that … Related articles All 7 versions

[BOOK] 7. Österreichische Artificial-Intelligence-Tagung/Seventh Austrian Conference on Artificial Intelligence: Wien, Austria, 24.–27. September 1991 Proceedings H Kaindl – 2013 – books.google.com … As the title of this paper indicates, it is an important goal of this research not simply to merge the verbalization results of a natural language generator and the … 4 (XTRA, CUBRICON, AL- Fresco) consists of multimodal dialog systems with an analysis and generation component. …

Automatic design of multimodal presentations W Wahlster – 2011 – scidok.sulb.uni-saarland.de … It is an important goal of this research not simply to merge the verbalization results of a natural language generator and the visualization … 78] W. Wahlster, A. Jameson and W. Hoeppner, Glancing, Referring and Explaining in the Dialogue System HAM-RPM, American Journal of … Cited by 2 Related articles All 9 versions

Online adaptation of dialogue systems F Jurc?cek, M Gašic, S Young, R Laroche, G Putois… – 2011 – classic-project.org … and speech generation requires a natural language generator and a speech synthesiser. In recent years, Partially Observable Markov Decision Processes (POMDPs) have been proposed as a principled way of modelling the uncertainty in spoken dialogue systems (Young et al … Related articles All 3 versions

Learning user modelling strategies for adaptive referring expression generation in spoken dialogue systems SC Janarthanam – 2011 – era.lib.ed.ac.uk … Spoken Dialogue Systems Srinivasan Chandrasekaran Janarthanam T H E U NIVER S I T Y … Page 2. Abstract We address the problem of dynamic user modelling for referring expression gen- eration in spoken dialogue systems, ie how a spoken dialogue system should choose … Cited by 1 Related articles All 3 versions

Conversational agents in a virtual world P Adolphs, A Benz, NB Castelló, X Cheng… – KI 2011: Advances in …, 2011 – Springer … Due to the mixed-initiative approach used in the agent, the dialogue system is also responsible for the control of the system initiative on … The query results are then turned into an abstract representation of the answer and spelt out by a natural-language generator [1]. Our module … Cited by 2 Related articles All 5 versions

Recovering From Errors in Conversational Dialogue Systems M Henderson – 2011 – era.lib.ed.ac.uk … using an OWL ontology, a user personalization server, and a Natural Language Generator. The robot could also interpret user gestures, and create natural gestures itself. As a base to create the Tourguide Dialogue System, the INDIGO system was stripped down … Related articles All 2 versions

Adaptive dialogue strategy selection through imprecise probabilistic query answering I O’Neill, A Yue, W Liu, P Hanna – Symbolic and Quantitative Approaches …, 2011 – Springer … A fully implemented spoken dialogue system requires a delicately balanced interaction between a number of main components. These typically include a speech recogniser, a semantic parser, a dialogue manager, a natural language generator, a speech synthesiser and an … Cited by 1 Related articles All 4 versions

Design and evaluation of acceleration strategies for speeding up the development of dialog applications LF D’Haro, R De Córdoba, R San-Segundo… – Speech …, 2011 – Elsevier … platform is made up of seven modules that carry out the different processes in a dialog system. The current modules are Automatic Speech Recognition (ASR), Audio server, text-to-speech (TTS), Natural Language Understanding (NLU), Natural Language Generator (NLG), the … Related articles All 15 versions

Embedded wizardry RJ Passonneau, SL Epstein, T Ligorio… – Proceedings of the …, 2011 – dl.acm.org … In two of the experi- ments, human wizards are embedded in the spoken dialogue system while run-time SLU features are collected. … A dialogue act se- lected by the wizard was passed to a template-based natural language generator, and then to a Text-to- Speech component. … Cited by 2 Related articles All 12 versions

Design and Development of an Automated Voice Agent: Theory and Practice Brought Together P Stavropoulou, D Spiliotopoulos… – … Agents and Natural …, 2011 – books.google.com … and Practice Brought Together Pepi Stavropoulou University of Athens, Greece Dimitris Spiliotopoulos University of Athens, Greece Georgios Kouroupetroglou University of Athens, Greece ABSTRACT Sophisticated, commercially deployed spoken dialogue systems capable … Cited by 1 Related articles All 3 versions

Statistical dialogue modelling M Gašic – 2011 – mi.eng.cam.ac.uk … The Dialogue Systems Group has provided a highly motivat- ing and pleasant environment in which to carry out research. … More importantly, this enables building real-world dialogue systems with large domains. This thesis also examines the potential for improving the action … Cited by 9 Related articles All 3 versions

[BOOK] Web Engineered Applications for Evolving Organizations: Emerging Knowledge G Alkhatib – 2011 – Citeseer … The Dialogue Manager (DM), the core of the dialogue system and probably the most complicated component. It handles the conversation flow, evaluating the input and creating the output. … The Natural Language Generator (NLG) that formulates the actual system prompts … Related articles All 6 versions

Effective handling of dialogue state in the hidden information state POMDP-based dialogue manager M Gaši?, S Young – ACM Transactions on Speech and Language …, 2011 – dl.acm.org … The speech generation component normally consists of a natural language generator and a speech synthesiser. It maps the system’s response first into text and then into speech. The overall structure of a statistical spoken dialogue system is shown in Figure 1. The core of the … Cited by 27 Related articles All 8 versions

Learning Dialogue POMDP Model Components from Expert Dialogues HR Chinaei – 2013 – theses.ulaval.ca … Page 3. Abstract Spoken dialogue systems should realize the user intentions and maintain a natural and efficient dialogue with users. … 33 3.3 The architecture of a spoken dialogue system, adapted from Williams [2006]. . . . … Related articles All 2 versions

Let’s talk! speaking virtual counselor offers you a brief intervention U Yasavur, C Lisetti, N Rishe – Journal on Multimodal User Interfaces, 2014 – Springer … The goal of our dialog system is to deliver alcohol screening and brief interventions based on this guide. … The Best Action is passed to the Natural Language Generator component, which gives the final form of the system response and passes the text to the Text-to-Speech (TTS … Cited by 1 Related articles

Statistical Dialog Management for Health Interventions U Yasavur – 2014 – digitalcommons.fiu.edu … Research endeavors on spoken dialogue systems in the 1990s and 2000s have led to the deployment of commercial spoken dialogue systems (SDS) in microdomains … based on the brief intervention counseling style via spoken dialogue systems. … Related articles All 3 versions

Towards an Interactive Human-Robot Relationship: Developing a Customized Robot’s Behavior to Human’s Profile ALY Amir – 2014 – pastel.archives-ouvertes.fr Page 1. Towards an Interactive Human-Robot Relationship: Developing a Customized Robot’s Behavior to Human’s Profile Amir ALY To cite this version: Amir ALY. Towards an Interactive Human-Robot Relationship: Developing …

Computational Linguistics Gerald Penn DG Hays – Philosophy of Linguistics, 2012 – books.google.com … lexical collocations and syntactic analysis than one would expect of the higher-level planning component of a natural language generator. … Dialogue systems research attempts to recognize plans and intentions in speech transcripts and to respond to them constructively and … Related articles All 3 versions

[BOOK] Multilingual text generation from structured formal representations D Dannélls – 2013 – gupea.ub.gu.se Page 1. Dana Dannélls Multilingual text generation from structured formal representations Page 2. Data linguistica <http://www.svenska.gu.se/publikationer/data-linguistica/> Editor: Lars Borin Språkbanken Department of Swedish University of Gothenburg 23 • 2012 Page 3. … Related articles All 3 versions

Dynamic User Modelling For Speech Interfaces Using Implicit Personalisation SR Denholm – 2014 – macs.hw.ac.uk … comments which point to a preference of the user and update their model. The project looks at technologies such as User Modelling, spoken dialogue systems and data collection … V 2.3 Spoken dialogue systems ….. 13 … Related articles

Learning to tell tales: automatic story generation from Corpora ND McIntyre – 2011 – era.lib.ed.ac.uk Page 1. Learning to Tell Tales: Automatic Story Generation from Corpora Neil McIntyre T H E U NIVER S I T Y O F E DI NBU R G H Doctor of Philosophy Institute for Communicating and Collaborative Systems School of Informatics University of Edinburgh 2011 Page 2. Page 3. iii … Cited by 2 Related articles All 4 versions