Sentence Planner – Meta-Guide.com

Notes:

It is correct that the term “tactic planning” is sometimes used to refer to the process of generating the syntactic structure of individual utterances, which is also known as sentence planning. Tactic planning is a subcomponent of the overall natural language generation process and is responsible for selecting and organizing the specific words and phrases that will be used to form the final utterance.

Tactic planning is typically concerned with the detailed structure and content of the generated language, and is often contrasted with higher-level components of the natural language generation process, such as the discourse planner or the document planner, which are responsible for generating larger units of language, such as conversations or documents.

The term “tactic planning” is often used to emphasize the fact that the process of generating the syntactic structure of an utterance involves making a series of tactical decisions about the specific words and phrases to be used, and how they should be organized to achieve the desired meaning and structure of the final utterance.

The sentence planner is a component of a natural language generation system that is responsible for selecting the appropriate syntactic templates and aggregating them to produce the full syntactic structure of an utterance. In the process of generating an utterance, the sentence planner receives as input the content plan tree, which is a representation of the content and meaning of the utterance that has been generated by the content planner.

The sentence planner uses this input to select the appropriate syntactic templates for expressing the individual propositions contained in the content plan tree. These templates are often based on the grammatical roles that the propositions play in the meaning of the utterance, such as subject, object, verb, etc.

Once the appropriate syntactic templates have been selected, the sentence planner aggregates them to produce the full syntactic structure of the utterance. This process involves combining the templates in a way that is consistent with the grammatical rules of the language being used, and may also involve adding additional words or phrases to provide context or to express relationships between the propositions.

The resulting syntactic structure is then passed on to the surface realizer, which is responsible for generating the actual words and phrases that will be used to form the final utterance.

The sentence planner is sometimes referred to as the “micro planner” in the context of natural language generation systems. The term “micro planner” is often used to distinguish the sentence planner from other components of the system that operate at a higher level of abstraction, such as the discourse planner or the document planner.

The sentence planner, or micro planner, is responsible for generating the syntactic structure of individual utterances, whereas the discourse planner is responsible for generating a coherent and cohesive sequence of utterances, and the document planner is responsible for generating structured documents.

The term “micro planner” is used to emphasize the fact that the sentence planner operates at a more detailed level than these other components, and is responsible for generating the specific words and phrases that will be used to form the final utterance. It is an important component of a natural language generation system, as it plays a key role in determining the overall structure and coherence of the generated language.

The term “text planner” is sometimes used to refer to a component of a natural language generation system that is responsible for generating structured documents, such as reports or news articles. This component is also commonly referred to as the “document planner.”

The text planner, or document planner, is responsible for organizing the content and structure of the individual sentences and paragraphs in a way that is appropriate for the purpose of the document and that follows the conventions of the document genre. It plays a key role in determining the overall coherence and structure of the generated document, and is an important component of any natural language generation system that is designed to generate structured documents.

The term “text planner” is often used to emphasize the fact that this component is responsible for generating the overall structure and organization of the document, rather than the specific words and phrases that will be used to form the individual sentences and paragraphs. It is typically concerned with higher-level aspects of the document structure, such as the overall structure of the document, the organization of the content into sections and paragraphs, and the use of headings and other formatting elements to guide the reader’s attention.

Content plan tree is a representation of the content and meaning of an utterance that is used in a natural language generation system. It is typically a hierarchical tree structure that encodes the propositions that make up the meaning of the utterance, as well as the relationships between those propositions.
Content planner is a component of a natural language generation system that is responsible for generating the content plan tree for an utterance. It does this by selecting the appropriate propositions and relationships to express the meaning of the utterance, and then organizing them into the content plan tree structure.
Discourse planner is a component of a natural language generation system that is responsible for generating a coherent and cohesive sequence of utterances that make up a larger discourse, such as a conversation or a document. It does this by selecting and organizing the content and structure of the individual utterances in a way that is appropriate for the overall discourse context.
Document planner is a component of a natural language generation system that is responsible for generating a structured document, such as a report or a news article. It does this by organizing the content and structure of the individual sentences and paragraphs in a way that is appropriate for the purpose of the document and that follows the conventions of the document genre.
Micro-planner is another term for a sentence planner, which is a component of a natural language generation system that is responsible for generating the syntactic structure of individual utterances. The term “micro-planner” is often used to distinguish the sentence planner from other components of the system that operate at a higher level of abstraction, such as the discourse planner or the document planner.
Sentence planner system is a general term that refers to any type of system that is designed to generate the syntactic structure of individual utterances. These systems may use a variety of approaches, including rule-based systems, machine learning algorithms, or statistical models, and may be implemented using a variety of technologies, such as Java, XSLT, or other programming languages or technologies. Some sentence planner systems may use grammar rules to generate the syntactic structure of the generated language, while others may use more data-driven approaches that are based on large datasets of annotated language examples.
Stochastic sentence planner is a type of sentence planner that uses probabilistic or statistical techniques to generate the syntactic structure of an utterance. These techniques may involve sampling from a large dataset of annotated language examples to select the appropriate words and phrases for the final utterance, or using machine learning algorithms to learn patterns in the data and make predictions about the most appropriate words and phrases to use. Stochastic sentence planners are often used in natural language generation systems to generate more varied and natural-sounding language.
Surface realizer is a component of a natural language generation system that is responsible for generating the actual words and phrases that will be used to form the final utterance. It receives as input the syntactic structure of the utterance, which has been generated by the sentence planner, and uses this input to select the specific words and phrases that will be used to form the final utterance.
Syntactic templates are predefined structures or patterns that can be used to express the syntactic structure of an utterance. These templates may be based on the grammatical roles that the propositions contained in the utterance play in the overall meaning of the utterance, such as subject, object, verb, etc. Syntactic templates can be used by a sentence planner to generate the syntactic structure of an utterance, and may be combined with additional words or phrases to provide context or to express relationships between the propositions.
Text plan is a representation of the content and structure of a document that is used by a text planner, or document planner, to generate a structured document. It is typically a hierarchical tree structure that encodes the content and structure of the document, including the individual sentences and paragraphs, as well as the headings, subheadings, and other formatting elements that are used to guide the reader’s attention.
XSLT-based sentence planner is a type of sentence planner that is implemented using the Extensible Stylesheet Language Transformations (XSLT) technology. XSLT is a programming language that is used to transform XML documents into other formats, such as HTML, PDF, or text. An XSLT-based sentence planner may be used in a natural language generation system to generate the syntactic structure of individual utterances by transforming a representation of the meaning of the utterance into a specific syntactic structure using XSLT rules.

Resources:

jSPaRKy v 2.0

Wikipedia:

Tree-adjoining grammar: Lexicalized Tree-adjoining grammar .. TAG: LTAG

Does Personality Matter? Expressive Generation for Dialogue Interaction MA Walker, J Sawyer, G Lin, S Wing – Natural Interaction with Robots, …, 2014 – Springer … Below we will discuss in detail how our PERSONAGE Realizer Sentence Planner Text Planner Dialog Manager … SPOT was a trainable sentence planner (Sentence Planner Trainable) that provided 12 parameters to control how concepts were combined into sentences. … Related articles All 3 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 … The content planner is responsible for selecting and structuring (in a tree format) the information to be processed by the sentence planner in terms of the values of some parameters such as the verbosity, polarity, repetitions (ie, the content planner decides what to say). … Cited by 10 Related articles All 2 versions

Generation of landmark-based navigation instructions from open-source data M Dräger, A Koller – Proceedings of the 13th Conference of the …, 2012 – dl.acm.org … We handle this problem in the sentence planner, which may aggregate utterances to fit into the available time. … We mostly follow a standard NLG pipeline (Reiter and Dale, 2000), with a focus on the sentence planner and an extension to interac- tive real-time NLG. 760 Page 5. … Cited by 6 Related articles All 9 versions

A pattern-based model for generating text to express emotion F Keshtkar, D Inkpen – Affective Computing and Intelligent Interaction, 2011 – Springer … 2.5 Sentence Planner Sentence planning is one the main tasks of any NLG system. … Sentence content delimitation. If the user wants to generate more than one sentence, the sentence planner can allocate the information so that it is distributed into distinct sentences. … Cited by 1 Related articles All 6 versions

Individual and Domain Adaptation in Sentence Planning for Dialogue F Mairesse, R Prasad, A Stent, MA Walker – arXiv preprint arXiv: …, 2011 – arxiv.org … application domain, individual user, or user group. In this paper we present and evaluate a trainable sentence planner for providing restaurant information in the MATCH dialogue system. We show that trainable sentence planning … Related articles All 3 versions

Learning what to say and how to say it: Joint optimisation of spoken dialogue management and natural language generation O Lemon – Computer Speech & Language, 2011 – Elsevier … a text planner which performs content selection and discourse structuring,. (ii) a sentence planner which selects attributes for referring expressions, aggregates content into sentence-size units, and selects lexical items, and. (iii) … Cited by 50 Related articles All 8 versions

Experiences with planning for natural language generation A Koller, R Petrick – Computational Intelligence, 2011 – Wiley Online Library … Section 3.1 to generate REs. This problem is usually handled by the sentence planner if sentence planning and surface realization are separated; here it happens as part of the overall generation process. We consider a series … Cited by 38 Related articles All 12 versions

A Hybrid Approach to Multi-document Summarization of Opinions in Reviews G Di Fabbrizio, AJ Stent, R Gaizauskas – INLG 2014, 2014 – aclweb.org … Our sentence planner, JSPARKY–a freely-available toolkit (Stent and Molina, 2009)–can produce several candidate sentence plans and their corre- sponding surface realizations through SimpleNLG (Gatt and Reiter, 2009). … Cited by 1

PPLUM: A Framework for Large-Scale Personal Persuasion S Pan, M Zhou – Proceedings of the 3rd Workshop on Data-Driven User …, 2014 – dl.acm.org … architecture. The light NLG boxes in Fig- ure 1 shows a typical NLG architecture [4]. The content planner performs content selection and organization. The sentence planner decides the content and the wording in each sentence. Finally …

A Statistical NLG Framework for Aggregated Planning and Realization. R Kondadadi, B Howald, F Schilder – ACL (1), 2013 – videolectures.net … Word choice, phrase composition, pronoun use and resolution, etc. • Surface realization – Putting everything together into “natural” sounding texts Document Planner Sentence Planner Input Data & Communicative Goal Document plan Text specification Surface realizer Text … Cited by 4 Related articles All 5 versions

Generating different story tellings from semantic representations of narrative E Rishes, SM Lukin, DK Elson, MA Walker – Interactive Storytelling, 2013 – Springer … We integrated these tools in a standard nlg pipeline: – Content planner that introduces characters and events – Sentence planner that creates linguistic representations for those events – Surface realizer that produces text string out of linguistic structures … Cited by 9 Related articles All 5 versions

A case based reasoning model for multilingual language generation in dialogues V López Salazar, EM Eisman Cabeza… – Expert Systems with …, 2012 – Elsevier … The system is composed by several modules: a content planner which selects the content of the sentences and structures the discourse using rhetorical operators, a sentence planner which specifies how the sentences have to be arranged and a realization module which … Cited by 3 Related articles All 4 versions

SemScribe: Natural Language Generation for Medical Reports. S Varges, H Bieler, M Stede, LC Faulstich, K Irsig… – LREC, 2012 – ling.uni-potsdam.de … observations. Sentence planning is performed by recursively composing partially specified syntactic trees. The sentence planner works on all observations within a content element and produces one or more sentences for these. The … Related articles All 3 versions

[BOOK] SemScribe: automatic generation of medical reports LC Faulstich, K Irsig, M Atalla, S Varges, H Bieler… – 2011 – Springer … the SPUD [14] and PROTECTOR [8] systems. The sentence planner works on all observations within a content element, re- sulting in one or more sentences for each content element. The linguistic knowl- edge used for sentence … Related articles All 4 versions

One step further towards stochastic semantic sentence generation B Bohnet, S Mille, L Wanner – … Dependency Theory. Frontiers in …, 2013 – books.google.com … To choose the best candidate, they use n-gram models, as [6, 3 and 4]. Walker et al.[8] and Stent et al.[9] describe a trainable sentence planner for dialog systems. The system Page 122. … Training a Sentence Planner for Spoken Dialogue Using Boosting. … Cited by 2 Related articles All 3 versions

An ontology-based approach to natural language generation from coded data in electronic health records M Arguello, J Des, MJ Fernandez-Prieto… – … and Simulation (EMS …, 2011 – ieeexplore.ieee.org … This stage uses the Sentence Planner & Sentence Realiser service and the SPARQL Query Processor service (see figure 6). These two services provide the necessary functionality to transform the results of the sequential queries performed in the previous stage into sentences. … Cited by 2 Related articles All 6 versions

Modeling the semantic coordination of speech and gesture under cognitive and linguistic constraints K Bergmann, S Kahl, S Kopp – Intelligent Virtual Agents, 2013 – Springer … 3.2 Formulators and Generators The message generator has to pre-package the activated SPR information in a way that the speech formulator can produce an appropriate sentence. We employ an LTAG-based sentence planner for speech formulation. … Cited by 8 Related articles All 5 versions

Deep Natural Language Processing for Italian Sign Language Translation A Mazzei, L Lesmo, C Battaglino, M Vendrame… – AI* IA 2013: Advances in …, 2013 – Springer … The paper is organized as follows: in Section 2 we describe the parser and the on- tology based interpreter; in Section 3 we describe the LIS generator, composed by two sub-modules: a sentence planner based on expert systems and a realizer based on formal grammars; in … Related articles All 2 versions

Enhancing the Expression of Contrast in the SPaRKy Restaurant Corpus DM Howcroft, C Nakatsu, M White – ENLG 2013, 2013 – aclweb.org … They illustrated their ap- proach by developing SPaRKy (Sentence Planning with Rhetorical Knowledge), a sentence planner for generating restaurant recommendations and comparisons in the context of the MATCH (Mul- timodal Access To City Help) system (Walker et al … Related articles All 6 versions

On the feasibility of automatically describing n-dimensional objects PA Duboue – ENLG’13, 2013 – aclweb.org … research, I introduce the problem, describe a potential application and source of interesting n- dimensional objects and show preliminary work on a traditional NLG system built on off-the-shelf text planning and surface realization technology plus a customized sentence planner. … Cited by 1 Related articles All 10 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 Page 1. Int J Artif Intell Educ DOI 10.1007/s40593-014-0017-9 BEETLE II: Deep Natural Language Understanding and Automatic Feedback Generation for Intelligent Tutoring in Basic Electricity and Electronics Myroslava Dzikovska …

Study on Education Resource Search Engine Based on Artificial Intelligence Technology N Yang, Y Wang – Journal of Jilin Institute of Architecture & Civil …, 2012 – en.cnki.com.cn … 1, ZHANG Dong Mo, GE Yong, and YAO Tian Fang (Department of Computer Science and Engineering, Shanghai Jiaotong University, Shanghai 200030);THE PRE-MAPPING SENTENCE PLANNER IN MULTILINGUAL NATURAL LANGUAGE GENERATION SYSTEM[J … Related articles All 2 versions

Question ranking and selection in tutorial dialogues L Becker, M Palmer, S van Vuuren… – Proceedings of the Seventh …, 2012 – dl.acm.org Page 1. The 7th Workshop on the Innovative Use of NLP for Building Educational Applications, pages 1–11, Montréal, Canada, June 3-8, 2012. cO2012 Association for Computational Linguistics Question Ranking and Selection in Tutorial Dialogues … Cited by 2 Related articles

Towards a Truly Statistical Natural Language Generator O Dušek – 2013 – ufal.ms.mff.cuni.cz … SimpleNLG: A realisation engine for practical applications. ENLG SPoT Walker, M. et al. 2001. SPoT: A trainable sentence planner. NAACL TectoMT Žabokrtský, Z. et al. 2008. TectoMT: highly modular MT system with tectogrammatics used as transfer layer. … Related articles All 3 versions

14th Annual Meeting of the Special Interest Group on Discourse and Dialogue F Metz – 2013 – sigdial.org … 21 Training an integrated sentence planner on user dialogue Brian McMahan and Matthew Stone . . . . . … 11:35 Training an integrated sentence planner on user dialogue Brian McMahan and Matthew Stone 11:55 Lunch … All 4 versions

Natural Language Generation O Dušek – 2013 – ufal.mff.cuni.cz … SimpleNLG: A realisation engine for practical applications. ENLG SPoT Walker, M. et al. 2001. SPoT: A trainable sentence planner. NAACL TectoMT Zabokrtský, Z. et al. 2008. TectoMT: highly modular MT system with tectogrammatics used as transfer layer. … Related articles All 2 versions

Natural Language Generation and Semantic Technologies K Staykova – Cybernetics and Information Technologies, 2014 – degruyter.com … The module produces a Document Plan containing a representation of the whole text and is often used as a specification of the discourse structure of the text. The second module is Sentence Planner (known also as Micro-planner or Tactic planning). …

Natural Language Generation as Incremental Planning Under Uncertainty: Adaptive Information Presentation for Statistical Dialogue Systems V Rieser, O Lemon, S Keizer – Audio, Speech, and Language …, 2014 – ieeexplore.ieee.org … understandable. The trained IP model is adaptive to variation from the current generation context (eg a user and a non-deterministic sentence planner), and it incrementally adapts the IP policy at the turn level. Reinforcement … Related articles

Graph matching algorithm based on edge map’s connection C CAO, J HE – Application Research of Computers, 2013 – en.cnki.com.cn … 5, ZHANG Dong Mo, GE Yong, and YAO Tian Fang (Department of Computer Science and Engineering, Shanghai Jiaotong University, Shanghai 200030);THE PRE-MAPPING SENTENCE PLANNER IN MULTILINGUAL NATURAL LANGUAGE GENERATION SYSTEM[J …

Natural Language Generation in the context of Multimodal Interaction in Portuguese JC Pereira, AJS Teixeira, JS Pinto – Electrónica e Telecomunicações, 2013 – revistas.ua.pt … As already presented, it has three main modules: a text planner, a sentence planner and a surface realiser; • Trainable NLG – modules that use trainable NLG are more complex than those described above. Here, different strategies are used. … Related articles

Systemic Functional Linguistics, Cognitive Linguistics and psycholinguistics: Opportunities for dialogue CS Butler – Functions of Language, 2013 – ingentaconnect.com … For language generation, the current model includes a general planner, an input, a discourse planner whose job is to structure the discourse as a whole, and a sentence planner dedicated to the task of specifying the internal structure of text sentences, which interact with a … Related articles All 2 versions

Computation and modeling of information structure M Stede – The Expression of Information Structure, 2012 – books.google.com … portions of the text. This arrange- ment, which applies globally across the entire text, needs to be determined in the text planning stage, so that the sentence planner, then, has the rel- evant information at its disposal. To this end …

A statistical prediction model of speakers’ intentions using multi-level features in a goal-oriented dialog system CN Seon, H Kim, J Seo – Pattern Recognition Letters, 2012 – Elsevier A dialog system is an intelligent program that helps users easily access information stored in a knowledge base by formulating requests in their natural languag. Cited by 3 Related articles All 3 versions

Controlling user perceptions of linguistic style: Trainable generation of personality traits F Mairesse, MA Walker – Computational Linguistics, 2011 – dl.acm.org … The resulting content plan tree is then processed by the sentence planner, which selects syntactic templates for expressing individual propositions, and aggregates them to produce the utterance’s 460 Page 7. Mairesse and Walker Trainable Generation of Personality Traits … Cited by 27 Related articles All 13 versions

Rich semantic representation based approach for text generation I Fathy, D Fadl, M Aref – Informatics and Systems (INFOS), 2012 …, 2012 – ieeexplore.ieee.org … [11] Mostafa Aref, Ibrahim Fathy, Dalia Sayed “Natural language Generation Sentence Planner” International Conference on intelligent computing and information systems ICICIS, Faculty of computer and information science Ain shams University, Cairo, Egypt, 2011. … Cited by 1 Related articles

Adaptive Natural Language Generation V Rieser, O Lemon – Reinforcement Learning for Adaptive Dialogue …, 2011 – Springer … the wizards’ choices in Page 6. 194 9 Adaptive Natural Language Generation real time. This generator is based on data from the stochastic sentence planner SPaRKy (Stent et al, 2004b). We replicated the variation observed … All 2 versions

Adaptive information presentation for spoken dialogue systems: Evaluation with human subjects V Rieser, S Keizer, X Liu, O Lemon – … of the 13th European Workshop on …, 2011 – dl.acm.org … The IP module has to decide which action to take next, how many attributes to mention, and when to stop generating. We use a sentence generator based on the stochastic sentence planner SPaRKy (Stent et al., 2004) for surface generation. … Cited by 11 Related articles All 8 versions

Creating a Cognitive Agent in a Virtual World: Planning, Navigation, and Natural Language Generation W Hewlett – 2013 – escholarship.org Page 1. … Related articles All 4 versions

DEXTOR: Reduced Effort Authoring for Template-Based Natural Language Generation. KS Narayan, CL Isbell Jr, DL Roberts – AIIDE, 2011 – aaai.org … Theune, MA 2003. Natural language generation for dialogue: system survey. Technical Report 2003-22. Walker, MA; Rambow, OC; and Rogati, M. 2002. Training a sentence planner for spoken dialogue using boosting. Computer Speech and Language. 175 Cited by 3 Related articles All 5 versions

Joint Video and Text Parsing for Understanding Events and Answering Queries K Tu, M Meng, MW Lee, TE Choe, SC Zhu – MultiMedia, IEEE, 2014 – ieeexplore.ieee.org Page 1. Video understanding is an im- portant aspect of multimedia content analysis that aims to automatically recognize objects, scenes, and events in the video. This step is a crucial component in systems attempting to improve … Related articles All 3 versions

Adapting Graph Summaries to the Users’ Reading Levels P Moraes, K McCoy, S Carberry – INLG 2014, 2014 – anthology.aclweb.org Page 72. Proceedings of the 8th International Natural Language Generation Conference, pages 64–73, Philadelphia, Pennsylvania, 19-21 June 2014. c 2014 Association for Computational Linguistics Adapting Graph Summaries … Cited by 2

An architecture for fluid real-time conversational agents: integrating incremental output generation and input processing S Kopp, H van Welbergen, R Yaghoubzadeh… – Journal on Multimodal …, 2013 – Springer … We have incremen- talized the SPUD sentence planner [42] so that—given an appropriately structured specification of a communicative intention—it generates natural language sentences in chunks of the size of intonation units; see [3] for details. 123 Page 8. … Cited by 3 Related articles All 5 versions

Towards a surface realization-oriented corpus annotation L Wanner, S Mille, B Bohnet – Proceedings of the Seventh International …, 2012 – dl.acm.org Page 1. INLG 2012 Proceedings of the 7th International Natural Language Generation Conference, pages 22–30, Utica, May 2012. cO2012 Association for Computational Linguistics Towards a Surface Realization-Oriented Corpus Annotation … Cited by 4 Related articles All 7 versions

Murder in the Arboretum: Comparing Character Models to Personality Models. MA Walker, GI Lin, J Sawyer, R Grant, M Buell… – Intelligent Narrative …, 2011 – aaai.org Page 1. Murder in the Arboretum: Comparing Character Models to Personality Models Marilyn A. Walker, Grace I. Lin, Jennifer Sawyer, Ricky Grant, Michael Buell, Noah Wardrip-Fruin Natural Language and Dialogue Systems Lab, Computer Science Dept. … Cited by 1 Related articles All 9 versions

Morpheme and semantic based approach for Tamil question answering system TV Geetha – 2013 – shodhganga.inflibnet.ac.in … LLL-2000, Lisbon, Portugal, 2000. 91. Marilyn Walker, Owen Rambow and Monica Rogati, “SPoT: A Trainable Sentence Planner”, URL http://www.aclweb.org/anthology/ N/N01/N01-1003.pdf, 2001. 92. Mayfield, J., Paul, MN … Related articles All 4 versions

Joint Video and Text Parsing for Understanding Events and Answering Queries K Tu, M Meng, MW Lee, TE Choe, SC Zhu – arXiv preprint arXiv: …, 2013 – arxiv.org Page 1. 1 Joint Video and Text Parsing for Understanding Events and Answering Queries Kewei Tu, Meng Meng, Mun Wai Lee, Tae Eun Choe, Song-Chun Zhu Abstract—We propose a framework for parsing video and text jointly … Cited by 1 Related articles All 6 versions

Abstractive summarization of voice communications V Pallotta, R Delmonte, A Bristot – Human Language Technology. …, 2011 – Springer … The existing annotations of the AMI corpus data are used to create a content representation that is subsequently fed to a sentence planner. The semantic representation produced is then rendered into a surface form with surface generator. … Cited by 2 Related articles All 6 versions

Joint models for concept-to-text generation I Konstas – 2014 – era.lib.ed.ac.uk Page 1. This thesis has been submitted in fulfilment of the requirements for a postgraduate degree (eg PhD, MPhil, DClinPsychol) at the University of Edinburgh. Please note the following terms and conditions of use: • This work … Related articles

A brief motivational interviewing intervention with prisoners: when you lead a horse to water, can it drink for itself? B Anstiss, DLL Polaschek, M Wilson – Psychology, Crime & Law, 2011 – Taylor & Francis … For the MI participants, the MI intervention followed the Time 1 assessment by no more than four weeks, and the Time 2 CNI-RTC score was derived from a sentence planner’s reassessment completed after the intervention. … Cited by 28 Related articles All 5 versions

Deep stochastic sentence generation: resources and strategies S Mille – 2014 – tdx.cat Page 1. Deep stochastic sentence generation Resources and strategies Simon Mille TESI DOCTORAL UPF / 2014 Director de la tesi Prof. Leo Wanner Department of Information and Communication Technologies Page 2. By …

Statistical language generation from semantic structures B Bohnet, S Mille, L Wanner – Proc. of International Conference …, 2011 – researchgate.net Page 1. Statistical Language Generation from Semantic Structures Bernd Bohnet1, Simon Mille2, Leo Wanner2,3 1 Institut für maschinelle Sprachverarbeitung (IMS) Universität Stuttgart, {first-name.last-name}@ims.uni-stuttgart … Cited by 6 Related articles All 5 versions

Co-speech Gesture Generation for Embodied Agents and its Effects on User Evaluation K Bergmann – Coverbal Synchrony in Human-Machine …, 2013 – books.google.com … 4.2 Modeling results The previously described generation model has been embedded in a larger production architecture realized using a multi-agent system toolkit, a natural language sentence planner (SPUD; Stone et al., 2003), the Hugin toolkit for Bayesian inference … Related articles All 2 versions

Perceived or not perceived: Film character models for expressive nlg MA Walker, R Grant, J Sawyer, GI Lin… – Interactive …, 2011 – Springer Page 1. Perceived or Not Perceived: Film Character Models for Expressive NLG Marilyn A. Walker, Ricky Grant, Jennifer Sawyer, Grace I. Lin, Noah Wardrip-Fruin, and Michael Buell Natural Language and Dialogue Systems … Cited by 9 Related articles All 14 versions

Improving MT coherence through text-level processing of input texts: the COMTIS project. http://webcast. in2p3. fr/videos-the_comtis_project B Cartoni, A Gesmundo, J Henderson, C Grisot… – 2011 – lodel.irevues.inist.fr … characteristic that must be explicitly managed when generating discourse. Therefore, any sentence planner system must somehow make decisions on cohesion markers (Hovy, 1988). Methods for correctly selecting tense as well as … Cited by 2 Related articles All 2 versions

Generating Elliptic Coordination C Gardent, S Narayan – Proceedings of the 14th …, 2013 – hal.archives-ouvertes.fr Page 1. Proceedings of the 14th European Workshop on Natural Language Generation, pages 40–50, Sofia, Bulgaria, August 8-9 2013. cO2013 Association for Computational Linguistics Generating Elliptic Coordination Claire … Related articles All 10 versions

Stochastic Language Generation in Dialogue using Factored Language Models F Mairesse, S Young – 2014 – MIT Press … senting the utterance, then the surface realization phase converts it into the final text. As developing a sentence planner capable of overgeneration typically requires sub- stantial amount of handcrafting (Walker, Rambow, and Rogati 2002; Stent, Prasad, and … Related articles

A Global Model for Concept-to-Text Generation. I Konstas, M Lapata – J. Artif. Intell. Res.(JAIR), 2013 – jair.org … selecting the appropriate content from the input and determining the structure of the target text), sentence planning (determining the structure and lexi- cal content of individual sentences), and surface realization (rendering the specification chosen by the sentence planner into a … Cited by 1 Related articles All 3 versions

Summarizing Information Graphics Textually S Demir, S Carberry, KF McCoy – Computational Linguistics, 2012 – MIT Press Cited by 2 Related articles All 6 versions

Natural Language Generation in the context of the Semantic Web N Bouayad-Agha, G Casamayor, L Wanner – Semantic Web, 2013 – IOS Press … text plan. The sentence planner is in charge of mapping the text plan to the linguistic structure of a sentence plan, grouping information into sentences and performing aggregation, and lexicalization along the way. Finally, the … Cited by 7 Related articles All 3 versions

Automatic generation of multiple choice questions using dependency-based semantic relations N Afzal, R Mitkov – Soft Computing, 2013 – Springer Page 1. Soft Comput DOI 10.1007/s00500-013-1141-4 METHODOLOGIES AND APPLICATION Automatic generation of multiple choice questions using dependency-based semantic relations Naveed Afzal · Ruslan Mitkov © Springer-Verlag Berlin Heidelberg 2013 … Cited by 1 Related articles

Generating natural language descriptions from OWL ontologies: the NaturalOWL system I Androutsopoulos, G Lampouras, D Galanis – arXiv preprint arXiv: …, 2014 – arxiv.org Page 1. Journal of Artificial Intelligence Research 48 (2013) 671-715 Submitted 04/13; published 11/13 Generating Natural Language Descriptions from OWL Ontologies: the NaturalOWL System Ion Androutsopoulos ion@aueb.gr … Cited by 6 Related articles All 6 versions

Domain-Independent Abstract Generation for Focused Meeting Summarization. L Wang, C Cardie – ACL (1), 2013 – aclweb.org Page 1. Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, pages 1395–1405, Sofia, Bulgaria, August 4-9 2013. c 2013 Association for Computational Linguistics Domain-Independent Abstract … Cited by 2 Related articles All 6 versions

OpenCCG Realizer Manual M White – Documentation of the OpenCCG Realizer, 2012 – svn.kwarc.info … JDOM API. For example, if the logical form is created by a Java XSLT-based sentence planner in the same process, the XSLT output can be captured in a JDOM document, and then simply passed by reference to the realizer. The … Cited by 3 Related articles

G-Asks: An intelligent automatic question generation system for academic writing support M Liu, RA Calvo, V Rus – Dialogue & Discourse, 2012 – elanguage.net Page 1. Dialogue and Discourse 3(2) (2012) 101–124 doi: 0.5087/dad.2012.205 ©2012 Ming Liu, Rafael A. Calvo and Vasile Rus. Submitted 2/11; Accepted 1/12; Published online 3/12 G-Asks: An Intelligent Automatic Question Generation System for Academic Writing Support … Cited by 6 Related articles All 3 versions

Learning to tell tales: automatic story generation from Corpora ND McIntyre – 2011 – era.lib.ed.ac.uk … 165 Page 14. Page 15. List of Tables 3.1 Example of grammar rules used by the sentence planner. Nodes pre- fixed with a $ are those that require satisfaction by the system. Vari- ables are prefixed with an @. Rules contain a set of attributes which … Cited by 3 Related articles All 2 versions

Generation of German narrative probability exercises R Boer Rookhuiszen – 2011 – essay.utwente.nl … In this process, the contents and structure of the text is determined, based on the goal of the text. This will result in a text plan that is used in the ‘Sentence Planner’. … Text Planner is called ‘Document Planner’ • Sentence Planner is called ‘Micro Planner’ … Related articles All 3 versions

Translationese and punctuation: An empirical study of translated and non-translated international newspaper articles (English and Spanish) M Rodríguez-Castro – Translation and Interpreting Studies, 2011 – ingentaconnect.com Page 1. Translation and Interpreting Studies 6:1 (2011), 40–61. doi 10.1075/tis.6.1.03rod issn 1932–2798 / e-issn 1876–2700 © John Benjamins Publishing Company Translationese and punctuation An empirical study of translated and non- … Related articles All 2 versions

Statistical Approaches to Adaptive Natural Language Generation O Lemon, S Janarthanam, V Rieser – Data-Driven Methods for Adaptive …, 2012 – Springer … The IP module has to decide which action to take next, how many attributes to mention and when to stop generating. A sentence generator based on the stochastic sentence planner SPaRKy [50] was employed for surface generation. … Related articles All 4 versions

A detailed account of the First Question Generation Shared Task Evaluation challenge V Rus, B Wyse, P Piwek, M Lintean… – Dialogue & …, 2012 – oro.open.ac.uk Page 1. Open Research Online The Open University’s repository of research publications and other research outputs A detailed account of the First Question Generation Shared Task Evaluation challenge Journal Article How to cite: … Related articles All 8 versions

The generation of qualitative descriptions of multivariate time series using fuzzy logic J Moreno-Garcia, L Rodriguez-Benitez, J Giralt… – Applied Soft …, 2014 – Elsevier An approach to generating qualitative descriptions of multivariate time series using the ‘Temporal Fuzzy Model’ as an intermediate representation is present.

Natural Language Descriptions for Video Streams MUG Khan – 2012 – etheses.whiterose.ac.uk Page 1. Access to Electronic Thesis Author: Muhammad Usman Ghani Khan Thesis title: Natural Language Descriptions for Video Streams Qualification: PhD This electronic thesis is protected by the Copyright, Designs and Patents Act 1988. … Related articles All 7 versions

Automatic Acquisition of Corpus for Multimedia Applications N Hajlaoui – Communications of the IBIMA, 2011 – ibimapublishing.com … France, 15-17. Walker, MA, Rambow, O. & Rogati, M. (2001). “SPoT: A Trainable Sentence Planner,” In Proceedings of the 2nd Annual Meeting of the North American Chapter of the Associataion for Computational Linguistics. Related articles All 4 versions

Automatic argumentative analysis for interaction mining V Pallotta, R Delmonte – Argument & Computation, 2011 – Taylor & Francis Cited by 5 Related articles All 4 versions

Natural language generation and semantic web technologies N Bouayad-Agha, G Casamayor… – Semantic Web …, 2012 – semantic-web-journal.org … into a coherent whole. The sentence planner is in charge of mapping the text plan to the linguistic struc- ture, grouping information into sentences and perform- ing aggregation, and lexicalization along the way. Fi- nally, the … Cited by 3 Related articles All 2 versions

Lessons Learned From a Rational Reconstruction of Minstrel. BR Tearse, PA Mawhorter, M Mateas, N Wardrip-Fruin – AAAI, 2012 – aaai.org … Laurence Scott. Austin, TX.:University of Texas Press. Ritchie, G. 1984. A Rational Reconstruction of the Proteus Sentence Planner. In Proceedings of the 10th international conference on Computational linguistics. Ritchie, G. 2001. Assessing Creativity. … Cited by 4 Related articles All 2 versions

A computational approach to the analysis and generation of emotion in text F Keshtkar – 2011 – ruor.uottawa.ca … 112 6.2.3 Pattern Extraction . . . . . 113 6.2.4 Pattern Analysis . . . . . 116 6.2.5 Sentence Planner . . . . . 119 6.2.6 Template-based Approach . . . . . 121 6.2.7 Surface Realization . . . . . … Cited by 3 Related articles All 4 versions

Introduction to special issue on machine learning for adaptivity in spoken dialogue systems O Lemon, O Pietquin – ACM Transactions on Speech and Language …, 2011 – dl.acm.org … W3C. http://www.w3.org/TR/voicexml30/. WALKER, M., RAMBOW, O., AND ROGATI, M. 2001. SPOT: A trainable sentence planner. In Proceedings of the North American Meeting of the Association for Computational Linguistics. WILLIAMS, J. AND YOUNG, S. 2007. … Cited by 3 Related articles All 3 versions

Access to multimodal articles for individuals with sight impairments S Carberry, S Elzer Schwartz, K Mccoy… – ACM Transactions on …, 2012 – dl.acm.org Page 1. 21 Access to Multimodal Articles for Individuals with Sight Impairments SANDRA CARBERRY, University of Delaware STEPHANIE ELZER SCHWARTZ, Millersville University KATHLEEN MCCOY, University of Delaware … Cited by 3 Related articles All 3 versions

A Chatbot Dialogue Manager-Chatbots and Dialogue Systems: A Hybrid Approach A Woudenberg – 2014 – dspace.learningnetworks.org Page 1. A Chatbot Dialogue Manager Chatbots and Dialogue Systems: A Hybrid Approach AF van Woudenberg, 850272823 June 17, 2014 Page 2. Page 3. A Chatbot Dialogue Manager Chatbots and Dialogue Systems: A Hybrid Approach …

Using Rhetorical Figures and Shallow Attributes as a Metric of Intent in Text CW Strommer – 2011 – uwspace.uwaterloo.ca … corporated into natural language generation through works such as that of Hervas and Gervas [71] and ongoing work based on ideas first proposed for the HealthDoc Sentence Planner [146]. 2.1.2 Natural Language Generation Systems Classic Model … Related articles All 3 versions

Evaluating the Perception of Personality and Naturalness in Computer Generated Utterances C McCormick – 2012 – scss.tcd.ie Page 1. Evaluating the Perception of Personality and Naturalness in Computer Generated Utterances by Christopher McCormick, B.Sc.(Hons) Dissertation Presented to the University of Dublin, Trinity College in fulfillment of the requirements for the Degree of … Related articles All 3 versions

Design and Implementation of a Conceptual Modeling Assistant (CMA) D Aguilera Moncusí – 2011 – upcommons.upc.edu Page 1. Master in Computing Llenguatges i Sistemes Inform`atics Master’s Thesis – September 2010 – DESIGN AND IMPLEMENTATION OF A CONCEPTUAL MODELING ASSISTANT (CMA) Student: Advisors: David Aguilera Moncusi … Related articles

Assessing user simulation for dialog systems using human judges and automatic evaluation measures H Ai, D Litman – Natural Language Engineering, 2011 – Cambridge Univ Press Page 1. Natural Language Engineering 17 (4): 511–540. c Cambridge University Press 2011 doi:10.1017/S1351324910000318 511 Assessing user simulation for dialog systems using human judges and automatic evaluation measures … Related articles All 4 versions