Document Planning & Natural Language Generation 2017


Notes:

Automated planning is one of the oldest sub-areas of AI. Automated planning is related to automated reasoning.

Document planning may be referred to as content selection. Document planning consists of deciding what content should be integrated to the output and how it should be structured. Document planning may be described as a linear theoretical proof search.

Macro-planning consists of content selection followed by document structuring. Typical macro-planning systems take a high level representation of input data, select and structure the final information to convey.

  • AI planning
  • AI planning algorithm
  • Automated planning
  • Automated planning system
  • Content planning
  • Content selection
  • Document orchestration
  • Document planner
  • Document planners
  • Document planning
  • Document planning module
  • Document structuring
  • Macro planning
  • Narrative planning

Resources:

Wikipedia:

References:

See also:

Dialog Planner | Micro-planning & Natural Language Generation | OpenCCG (OpenNLP CCG Library) | PDDL (Planning Domain Definition Language) & Natural Language 2017Sentence Planner | SME (Structure Mapping Engine) 2017


Data-Driven News Generation for Automated Journalism
L Leppänen, M Munezero, M Granroth-Wilding… – … Language Generation, 2017 – aclweb.org
… discussed be- low, we here focus on the pipeline architecture com- mon in earlier NLG work (Reiter, 2007; Mahapatra et al., 2016), consisting of document planning, mi- cro planning, and surface realization stages. 3 Requirements for Journalistic Natural Language Generation …

Planning for Natural Language Generation in GF
G Lobanov, K Angelov – Workshop on Logic and Algorithms in …, 2017 – diva-portal.org
… In this paper we will focus on the document planning in natural language generation as it is now implemented in Grammatical Framework (GF)[16]. GF is a formalism where grammars for one or more natural languages can be coupled together via an abstract syntax …

Transformation of TOSCA to natural language texts
M Radic – 2017 – elib.uni-stuttgart.de
… [RDF00] Document Planning The Document Planning module generates an outline for the document to be generated … 20 Page 21. 2.2 Natural Language Generation Depending on the application, this task has to incorporate different factors …

Communication Mediated through Natural Language Generation in Big Data Environments: The Case of Nomao
JS Vayre, E Delpech, A Dufresne… – Journal of Computer and …, 2017 – file.scirp.org
… Nomao’s Natural Language Generation System (NLGs) As shown in Figure 1, Nomao’s NLGs has been designed in accordance with the typical stages of NLGs [3]. These stages are: macro-planning (content selection followed by document structuring); micro-planning (syntactic …

Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation
A Gatt, E Krahmer – Journal of Artificial Intelligence Research, 2018 – jair.org
… Netherlands Abstract This paper surveys the current state of the art in Natural Language Generation (nlg), defined as the task of generating text or speech from non-linguistic input … 66 Page 3. Natural Language Generation • weather …

Improving the Naturalness and Expressivity of Language Generation for Spanish
C Barros, D Gkatzia, E Lloret – … on Natural Language Generation, 2017 – aclweb.org
Proceedings of The 10th International Natural Language Generation conference, pages 41–50, Santiago de Compostela, Spain, September 4-7 2017 … a wide range of modules, commonly grouped into a pipeline of three broad stages: document planning, microplanning and sur …

A Study on Flexibility in Natural Language Generation Through a Statistical Approach to Story Generation
M Vicente, C Barros, E Lloret – … on Applications of Natural Language to …, 2017 – Springer
… Download fulltext PDF. 1 Context and Motivation. Macroplanning (ie, what to say) and surface realisation (ie, how to say it) are two key stages in the process of Natural Language Generation (NLG) … Recreation task. Baseline (no DP). Macro- planning. Originals. Baseline (no DP) …

An exploratory study on the benefits of using natural language for explaining fuzzy rule-based systems
JM Alonso, A Ramos-Soto, E Reiter… – Fuzzy Systems (FUZZ …, 2017 – ieeexplore.ieee.org
… Secondly, a partition tuning procedure gets better accuracy while keeping interpretability. B. Natural Language Generation from Data NLG is a well-known area inside the computational linguis- tics field … Document Planner …

On Natural Language Generation of Formal Argumentation
F Cerutti, A Toniolo, TJ Norman – arXiv preprint arXiv:1706.04033, 2017 – arxiv.org
… Language Generation (NLG) system requires [Reiter and Dale, 2006]: • A knowledge source to be used; 7 Page 8. Table 1: Modules and tasks of a NLG system, adapted from [Reiter and Dale, 2006, Figure 3.1]. Module Content task Structure task Document planning Content …

Recent Advances in Natural Language Generation: A Survey and Classification of the Empirical Literature
R Perera, P Nand – Computing and Informatics, 2017 – cai.sk
… We used International Natural Language Generation con- ference (INLG), European Workshop on Natural Language Generation (ENLG), Natural Language Engineering journal … Section 4 describes document planning, which is one of the significant and an initial step in NLG …

A Statistical Framework for Product Description Generation
J Wang, Y Hou, J Liu, Y Cao, CY Lin – Proceedings of the Eighth …, 2017 – aclweb.org
… Writing Knowledge Learning • Templated Knowledge • Structural Knowledge Document Planning Figure 2: The system framework … References Pablo A. Duboue and Kathleen R. McKeown. 2003. Statistical acquisition of content selection rules for natural language generation …

Integrated sentence generation using charts
A Koller, N Engonopoulos – … on Natural Language Generation, 2017 – aclweb.org
… 2000. Building Natural Language Generation Systems. Cambridge University Press, Cambridge, England. Maximilian Schwenger, ´Alvaro Torralba, Jörg Hoffmann, David M. Howcroft, and Vera Demberg. 2016. From OpenCCG to AI planning: Detecting infeasible edges …

A multilingual multi-domain data-to-text natural language generation approach
C Barros, E Lloret – Procesamiento del Lenguaje Natural, 2017 – journal.sepln.org
… The area of Natural Language Generation (NLG) aims to automatically develop tech- niques to produce human utterances, that can be materialised through text … In the document planning stage, the system must decide what information should be included in the text and how to …

A novel approach for automatic text analysis and generation for the cultural heritage domain
F Piccialli, F Marulli, A Chianese – Multimedia Tools and Applications, 2017 – Springer
… 2): 1. Text planning. 2. Document planning. 3. Surface realization. Open image in new window. Fig. 2 A general schema for natural language generation process. This architecture is then further decomposed into six basic activities (see Fig. 2) …

Separating Representation, Reasoning, and Implementation for Interaction Management: Lessons from Automated Planning
ME Foster, RPA Petrick – Dialogues with Social Robots, 2017 – Springer
… Dialogues with Social Robots pp 93-107 | Cite as. Separating Representation, Reasoning, and Implementation for Interaction Management: Lessons from Automated Planning … 3 The Separation of Representation and Reasoning in Automated Planning …

Merits of Hierarchical Story and Discourse Planning with Merged Languages
DR Winer, RM Young – 2017 – liquidnarrative.cs.utah.edu
… Story generators arose as the first AI planning algorithms were developed, such as TALE-SPIN (Mee- han 1977) in which woodland creatures follow plans to satisfy basic needs … State-of-the-art automated planning systems (Vallati et al …

Toward automatic generation of linguistic advice for saving energy at home
P Conde-Clemente, JM Alonso, G Trivino – Soft Computing, 2018 – Springer
… 2 The natural language generation pipeline proposed by Reiter and Dale (2000). Document planner It produces a document plan. The “content determination” sub-task decides what information should be communicated in the output text (What to say?) …

A Target Driven Approach Supporting Data Diversified Generation in IoT Applications
F Amato, B Di Martino, F Marulli, A Mazzeo… – Conference on Complex …, 2017 – Springer
… What we need to coordinate these multiple interacting dimensions to support a successful natural language generation process … The second step is called Document Planning, in which selected facts from the ontology are “verbalized” in the form of Natural Language sentences …

Machine Intelligence Techniques for Next-Generation Context-Aware Wireless Networks
TE Bogale, X Wang, LB Le – arXiv preprint arXiv:1801.04223, 2018 – arxiv.org
… information to request intervening. In fact, recently it is demonstrated via experiment that the use of natural language generation techniques from imprecise data improves the human decision making accuracy. Such a linguistic …

WiseReporter: A Korean Report Generation System
Y Noh, SJ Choi, SB Park, SY Park – Proceedings of the IJCNLP 2017 …, 2017 – aclweb.org
… language generation following several studies on ontology verbalization (Androutsopou- los et al., 2013; Nadjet et al., 2014). The ar- chitecture is typically composed with three ma- jor modules (Mellish et al., 2006): (i) text plan- ning (also referred to as macro-planning), (ii) sen …

An automatic generation method of sports news based on knowledge rules
J Gong, W Ren, P Zhang – … Science (ICIS), 2017 IEEE/ACIS 16th …, 2017 – ieeexplore.ieee.org
… Natural Language Engineering, 2008,14(4):431–455. [3] Garoufi and A. Koller. Automated planning for situated natural language generation. In Proceedings of ACL-2010, 2010. 501 Page 4. [4] NaGerard Casamayor, Leo Wanner, and Chris Mellish …

Computer Vision and Natural Language Processing: Recent Approaches in Multimedia and Robotics
P Wiriyathammabhum, D Summers-Stay… – ACM Computing …, 2017 – dl.acm.org
Page 1. 71 Computer Vision and Natural Language Processing: Recent Approaches in Multimedia and Robotics PERATHAM WIRIYATHAMMABHUM, University of Maryland, College Park DOUGLAS SUMMERS-STAY, US …

SaferDrive: An NLG-based behaviour change support system for drivers
D Braun, E Reiter, A Siddharthan – Natural Language Engineering, 2018 – cambridge.org
… January 2018) Abstract Despite the long history of Natural Language Generation (NLG) research, the potential for influencing real world behaviour through automatically generated texts has not received much attention. In this …

Laying Down the Yellow Brick Road: Development of a Wizard-of-Oz Interface for Collecting Human-Robot Dialogue
C Bonial, M Marge, A Foots, F Gervits, CJ Hayes… – arXiv preprint arXiv …, 2017 – arxiv.org
… interface was our first step in automating the robot partner by providing a more advanced tool for the DM- Wizard’s natural language generation tasks … Since the path and final positioning derived by an automated planner might be dif- ferent from that taken by a human RN-Wizard …

RDF2PT: Generating Brazilian Portuguese Texts from RDF Data
D Moussallem, TC Ferreira, M Zampieri… – arXiv preprint arXiv …, 2018 – arxiv.org
… 1. Introduction Natural Language Generation (NLG) is the process of gen- erating coherent natural language text from non-linguistic data (Reiter and Dale, 2000) … 3.3. Document Planning This initial phase is divided into two sub-tasks …

Natural language processing in mental health applications using non-clinical texts
RA Calvo, DN Milne, MS Hussain… – Natural Language …, 2017 – cambridge.org
Page 1. Natural Language Engineering: page 1 of 37. c Cambridge University Press 2017. This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (http://creativecommons. org …

SaToS: Assessing and Summarising Terms of Services from German Webshops
D Braun, E Scepankova, P Holl, F Matthes – … Language Generation, 2017 – aclweb.org
Proceedings of The 10th International Natural Language Generation conference, pages 223–227, Santiago de Compostela, Spain, September 4-7 2017 … During Document Planning, so far, only the order of the messages is determined, starting with unlaw- ful messages, followed …

Tweet dreams are made of this: Appropriate incongruity in the dreamwork of language
T Veale, A Valitutti – Lingua, 2017 – Elsevier
… more. Reiter and Dale (2006) propose that the generation of complex natural-language artifacts requires two levels of planning: macro-planning (what is it I want to say?) and micro-planning (how do I go about saying it?). In …

Dialogue with Robots to Support Symbiotic Autonomy
A Vanzo, D Croce, E Bastianelli, G Gemignani… – Dialogues with Social …, 2017 – Springer
… Garoufi, K., Koller, A.: Automated planning for situated natural language generation. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pp. 1573–1582. ACL ’10, Association for Computational …

Building Cognitive Cities with Explainable Artificial Intelligent Systems
JM Alonso, C Mencar – 2018 – ceur-ws.org
… Keywords: Explainable Computational Intelligence, Interpretable Fuzzy Systems, Natural Language Generation, Cognitive Cities … to humans in NL (after document planning and careful computational lin- guistic realization which includes lexicalization, referring expression …

I Read the News Today, Oh Boy
T Veale, H Chen, G Li – International Conference on Distributed, Ambient …, 2017 – Springer
… Reiter and Dale (2006) argue that the generation of complex natural-language artifacts requires two levels of planning: macro-planning (what is it I want to say?) and micro … 45–50 (2010)Google Scholar. Reiter, E., Dale, R.: Building Natural Language Generation Systems …

A New Multilingual Authoring Tool of Semistructured Legal Documents
JLC Herrero, GC Pastor, AJ Trujillo… – TRANS. Revista de …, 2017 – revistas.uma.es
… Reiter and Dale (2000: 1). The former states the following: «The area of study called natural language generation (nlg) investigates … The process performed by a nlg system generally comprises three phases —document planning, microplanning and surface realisa- tion, which …

Natural language generation in the context of multimodal interaction in Portuguese: Data-to-text based in automatic translation
JC Pereira – 2017 – ria.ua.pt
… They are commonly known as classic Natural Language Generation systems (Reiter and Dale, 1997, Reiter and Dale, 2000), doing their job in three steps (Reiter and Dale, 2000, p.47–72)(Reiter, 2010, p.579–586): 1. Document Planning (makes a specification of text structure …

Modeling the clarification potential of instructions: Predicting clarification requests and other reactions
L Benotti, P Blackburn – Computer Speech & Language, 2017 – Elsevier
… template for a plan. That is, we use AI-planning to perform what is called micro-planning. Micro-planning has previously been used for natural language generation by Koller and Stone (2007), Garoufi (2014). Here, building on …

Novel Methods for Natural Language Generation in Spoken Dialogue Systems
O Dušek – 2017 – dspace.cuni.cz
… rare. 2.1 The Varied Landscape of NLG Systems In general, natural language generation is defined as the task of presenting … 1. Content planning (also referred to as content selection or document planning). The system selects relevant content from the input data and performs …

Language Generation from DB Query
K Kocijan, B Bekavac, K Šojat – … Automatic Natural Language Generation …, 2017 – aclweb.org
Page 1. 25 Proceedings of the Linguistic Resources for Automatic Natural Language Generation Workshop, pages 25– 32, Santiago de Compostela, Spain, September 4, 2017 … The proce- dures that are thereby applied can be divided into macro-planning and micro-planning …

Attribute grammars with set attributes and global constraints as a unifying framework for planning domain models
R Barták, A Maillard – Proceedings of the 19th International Symposium …, 2017 – dl.acm.org
Page 1. Attribute Grammars with Set Attributes and Global Constraints as a Unifying Framework for Planning Domain Models Roman Barták Charles University, Faculty of Mathematics and Physics Praha, Czech Republic bartak@ktiml.mff.cuni.cz …

Explanations engine for energy management systems in buildings
AA Alyafi, JP Guillbaud, P Reignier… – … Data Acquisition and …, 2017 – ieeexplore.ieee.org
… statement Natural Language Generation (NLG) is an NLP sub- field concerned with the generation of texts from non- linguistic data [10]. Typical systems take a high-level representation of input data, select and structure the final information to convey (macro-planning), makes a …

Natural Transmission of Information Extraction Results to End-Users-A Proof-of-Concept Using Data-to-Text
JC Pereira, AJS Teixeira, M Rodrigues… – … Series in Informatics, 2017 – drops.dagstuhl.de
… this problem, of efficient and natural transmission, with a data-to-text system, a derivation of formal Natural Language Generation (NLG) systems … The BT-45 follows the data-to-text architecture suggested by [10], hence the presence of a Document Planning, Micro-Realization …

An Approach for Explaining Reasoning on the Diet Domain
L Anselma, A Mazzei – CEUR WORKSHOP PROCEEDINGS, 2017 – iris.unito.it
… In this paper we address some issues related to numerical reasoning and persuasive natural language generation in the diet do- main … for NL generation, especially in applicative contexts, is a pipeline composed by three distinct modules: the document planning, the sentence …

Dialogues with Social Robots
K Jokinen, G Wilcock – Springer, 2017 – Springer
… and Mikio Nakano Separating Representation, Reasoning, and Implementation for Interaction Management: Lessons from Automated Planning … Devillers and Guillaume Dubuisson Duplessis Extrinsic Versus Intrinsic Evaluation of Natural Language Generation for Spoken …

Institute of Communications Engineering Staff
M Bossert, R Fischer, W Minker, UC Fiebig… – Proceedings of the …, 2017 – uni-ulm.de
… Style in Dialogue Management Proceedings of the INLG 2016 Workshop on Computational Creativity in Natural Language Generation, Association for … Behnke, P. Bercher, S. Biundo and W. Minker The Interplay of User-Centered Dialog Systems and AI Planning Proceedings of …

Simulated Penetration Testing and Mitigation Analysis
M Backes, J Hoffmann, R Künnemann… – arXiv preprint arXiv …, 2017 – arxiv.org
… To this end, AI planning methods have been proposed [4], [33] and in fact used commercially, at a company called Core Security, since at least 2010 [11] … Automated Planning is one of the oldest sub-areas of AI (see [13] for a comprehensive introduction) …

Placing mined clues on causality at the heart of narrative planning
PL Vaudry, G Lapalme – 2018 – rali.iro.umontreal.ca
… However, they play only a secondary role in their document planners and their identi- fication relies mostly on domain knowledge … This can help obtain a more appropriate connecting associative thread in document planning …

New types of computational perceptions: Linguistic descriptions in deforestation analysis
P Conde-Clemente, JM Alonso, ÉO Nunes… – Expert Systems With …, 2017 – Elsevier
… main research lines in the specialized literature for text generation from data (Data-to-Text, in short): (1) Natural Language Generation (NLG); and … the whole NLG system, they divided the text generation process in a pipeline with three core tasks: (1) Document Planner, (2) Micro …

Dialogue System for Advising Ethiopian Public Universities Students
DT Habte – 2017 – etd.aau.edu.et
… KB Knowledge Base KE Keyword Extraction LU Lexical Unit MySQL My Structured Query Language NLG Natural Language Generation NLP Natural Language Processing NLU Natural Language Understanding ON Outcome Negative Page 11. vi POS Part of Speech …

Symbol Grounding via Chaining of Morphisms
R Lian, B Goertzel, L Vepstas, D Hanson… – arXiv preprint arXiv …, 2017 – arxiv.org
… Significant aspects of natural language generation can be viewed in terms of tracing these morphisms in the opposite direction; though other aspects, such as pragmatics oriented micro and macro planning, need to be dealt with using broader sorts of inference …

Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples
P Vougiouklis, H Elsahar, LA Kaffee, C Gravier… – arXiv preprint arXiv …, 2017 – arxiv.org
… In the context of the Semantic Web, Natural Language Generation (NLG) is concerned with the im- plementation of textual interfaces that … i) docu- ment planning or content selection, (ii) microplanning and (iii) surface realisation [13, 4]. During document planning the information …

Producing Referring Expressions in Identification Tasks and Route Directions: What’s the Difference?
A Baltaretu, E Krahmer, A Maes – Discourse Processes, 2017 – Taylor & Francis
Page 1. Producing Referring Expressions in Identification Tasks and Route Directions: What’s the Difference? Adriana Baltaretu, Emiel Krahmer, and Alfons Maes Tilburg Center for Cognition and Communication, Tilburg University, Tilburg, Netherlands …

Constructing Sentences from Text Fragments: Aggregation in Text-to-text Generation
V Chenal – 2017 – digitool.library.mcgill.ca
… 2003). • Macroplanning or document planning, consists of deciding what content should be integrated to the output and how it should be structured. 5 Page 12. CHAPTER 2. NATURAL LANGUAGE GENERATION 6 • Microplanning …

Proceedings of the Workshop on Logic and Algorithms in Computational Linguistics 2017 (LACompLing2017)
R Loukanova, K Liefke – Workshop on Logic and Algorithms in …, 2017 – diva-portal.org
… for Natural Language Generation in GF Abstract: In this paper, we present a minimalistic approach to docu- ment planning in natural language generation which is … It turns out that document planning is easy to describe as a type theoretical proof search under a linear context …

Automatically Classifying User Engagement for Dynamic Multi-party Human–Robot Interaction
ME Foster, A Gaschler, M Giuliani – International Journal of Social …, 2017 – Springer
A robot agent designed to engage in real-world human–robot joint action must be able to understand the social states of the human users it interacts with in order to behave appropriately. In particula.

Narrative generation by associative network extraction from real-life temporal data
PL Vaudry – 2017 – papyrus.bib.umontreal.ca
… lexical choices adequate. Keywords: Natural language generation, data-to-text, document planning, narrative, temporal data, causal relation, association rule, sequence, event, domain knowledge. v Page 6. CONTENTS RÉSUMÉ . . . . . ii …

A statistical, grammar-based approach to microplanning
C Gardent, L Perez-Beltrachini – Computational Linguistics, 2017 – MIT Press
… The content to be expressed must be selected (content selection) and structured (document planning) … To illustrate the workings of our approach, we consider a Natural Language Generation (NLG) setting where content selection and linearization are given, namely, the …

Design of Hybrid Cells to Facilitate Safe and Efficient Human-Robot Collaboration During Assembly Operations
K Kaipa, C Morato, SK Gupta – Journal of …, 2018 – … .asmedigitalcollection.asme.org
… This requires generating feasible assembly sequences and instructions for robots and human operators, respectively. Automated planning poses the following two challenges. First, generating precedence constraints for complex assemblies is challenging …

Utilizing bots in delivering content from Kentico Cloud and Kentico EMS
A Eikonsalo – 2017 – tampub.uta.fi
… By this definition, a dialog system does not include any advanced components such as natural language understanding, natural language generation (NLG), or ma- chine learning (ML) … document planning, microplanning and surface realization. He continues that …

Assistive and Adaptive Dialog Management
F Nielsen, W Minker – Companion Technology, 2017 – Springer
… Hence, it is translated by the explanation manager using template-based natural language generation into human-readable text. This new generated content is then transmitted to the information model in the knowledge base …

Generating variations in a virtual storyteller
SM Lukin – 2017 – search.proquest.com
… NLG story gap [Callaway and Lester, 2002, Lnneker, 2005]; an architectural disconnect between narrative representation, generation, and natural language generation … Content planning, or document planning, is the module in the NLG pipeline responsible for the selection and …

(Visited 35 times, 1 visits today)