Content Selection in Data-to-Text Systems: A Survey

Data-to-text systems are powerful in generating reports from data automatically and thus they simplify the presentation of complex data. Rather than presenting data using visualisation techniques, data-to-text systems use natural (human) language, which is the most common way for human-human communication. In addition, data-to-text systems can adapt their output content to users' preferences, background or interests and therefore they can be pleasant for users to interact with. Content selection is an important part of every data-to-text system, because it is the module that determines which from the available information should be conveyed to the user. This survey initially introduces the field of data-to-text generation, describes the general data-to-text system architecture and then it reviews the state-of-the-art content selection methods. Finally, it provides recommendations for choosing an approach and discusses opportunities for future research.

• Publication year

  2016

• Venue

  arXiv.org

• Publication date

  2016-10-26

• Fields of study

  Computer Science

• Identifiers
  arXiv 1610.08375
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Statistical Natural Language Generation from Tabular Non-textual Data

  2016influential reference
• Natural Language Generation enhances human decision-making with uncertain information

  2016influential reference
• How to talk to strangers: Generating medical reports for first-time users

  2016influential reference
• Personal storytelling: Using Natural Language Generation for children with complex communication needs, in the wild

  2016cited by this paper
• Data-driven approaches to content selection for data-to-text generation

  2015cited by this paper
• A Snapshot of NLG Evaluation Practices 2005 - 2014

  2015influential reference
• A Game-Based Setup for Data Collection and Task-Based Evaluation of Uncertain Information Presentation

  2015cited by this paper
• Multi-adaptive Natural Language Generation using Principal Component Regression

  2014influential reference
• Cluster-based Prediction of User Ratings for Stylistic Surface Realisation

  2014influential reference
• Generating Verbal Descriptions from Medical Sensor Data: A Corpus Study on User Preferences

  2014influential reference
• Comparing Multi-label Classification with Reinforcement Learning for Summarisation of Time-series Data

  2014influential reference
• Linguistic Descriptions for Automatic Generation of Textual Short-Term Weather Forecasts on Real Prediction Data

  2014cited by this paper
• Generating Annotated Graphs using the NLG Pipeline Architecture

  2014cited by this paper
• Comparative evaluation and shared tasks for NLG in interactive systems

  2014influential reference
• Learning to Summarize Time Series Data

  2014cited by this paper
• Latent User Models for Online River Information Tailoring

  2014influential reference
• Generating Student Feedback from Time-Series Data Using Reinforcement Learning

  2013influential reference
• A Statistical NLG Framework for Aggregated Planning and Realization

  2013cited by this paper
• MIME - NLG in Pre-Hospital Care

  2013cited by this paper
• Using Integer Linear Programming in Concept-to-Text Generation to Produce More Compact Texts

  2013cited by this paper
• Towards NLG for Physiological Data Monitoring with Body Area Networks

  2013influential reference
• Content Selection From Semantic Web Data

  2012cited by this paper
• Summarizing Information Graphics Textually

  2012cited by this paper
• Atlas.txt: exploring linguistic grounding techniques for communicating spatial information to blind users

  2012influential reference
• Unsupervised Concept-to-text Generation with Hypergraphs

  2012influential reference
• Combining Hierarchical Reinforcement Learning and Bayesian Networks for Natural Language Generation in Situated Dialogue

  2011cited by this paper
• Narrative monologue as a first step towards advanced mission debrief for AUV operator situational awareness

  2011cited by this paper
• Automatically generating stories from sensor data

  2011cited by this paper
• Generating Affective Natural Language for Parents of Neonatal Infants

  2011cited by this paper
• Acquiring Correct Knowledge for Natural Language Generation

  2011cited by this paper
• Learning user modelling strategies for adaptive referring expression generation in spoken dialogue systems

  2011cited by this paper
• BT-Nurse: computer generation of natural language shift summaries from complex heterogeneous medical data

  2011cited by this paper
• A Personalized System for Conversational Recommendations

  2011cited by this paper
• A Survey on Transfer Learning

  2010cited by this paper
• A Simple Domain-Independent Probabilistic Approach to Generation

  2010influential reference
• When a graph is poorer than 100 words: A comparison of computerised natural language generation, human generated descriptions and graphical displays in neonatal intensive care

  2010cited by this paper
• Using NLG and Sensors to Support Personal Narrative for Children with Complex Communication Needs

  2010cited by this paper
• Optimising Information Presentation for Spoken Dialogue Systems

  2010cited by this paper
• Extracting Parallel Fragments from Comparable Corpora for Data-to-text Generation

  2010cited by this paper
• Adaptive Referring Expression Generation in Spoken Dialogue Systems: Evaluation with Real Users

  2010cited by this paper
• Learning Semantic Correspondences with Less Supervision

  2009influential reference
• From data to text in the Neonatal Intensive Care Unit: Using NLG technology for decision support and information management

  2009influential reference
• Using Spatial Reference Frames to Generate Grounded Textual Summaries of Georeferenced Data

  2008influential reference
• Advanced Data Mining Techniques

  2008cited by this paper
• Learning to sportscast: a test of grounded language acquisition

  2008cited by this paper
• Automatic generation of weather forecast texts using comprehensive probabilistic generation-space models

  2008cited by this paper
• Adaptive, intelligent presentation of information for the museum visitor in PEACH

  2007cited by this paper
• Individual and Domain Adaptation in Sentence Planning for Dialogue

  2007cited by this paper
• Multi-Label Classification: An Overview

  2007cited by this paper
• Summarizing Dive Computer Data: A Case Study in Integrating Textual and Graphical Presentations of Numerical Data

  2007cited by this paper
• Corpus-based generation of head and eyebrow motion for an embodied conversational agent

  2007cited by this paper
• An Architecture for Data-to-Text Systems

  2007cited by this paper
• Comparing Automatic and Human Evaluation of NLG Systems

  2006cited by this paper
• Information Presentation in Spoken Dialogue Systems

  2006cited by this paper
• Authoring and Generation of Individualized Patient Education Materials

  2006cited by this paper
• Data-Driven Generation of Emphatic Facial Displays

  2006cited by this paper
• Choosing the content of textual summaries of large time-series data sets

  2006cited by this paper
• Summarisation and Visualisation of e-Health Data Repositories

  2005cited by this paper
• Logic and Conversation

  2005cited by this paper
• A Comparison of Graphical and Textual Presentations of Time Series Data to Support Medical Decision Making in the Neonatal Intensive Care Unit

  2005cited by this paper
• Collective Content Selection for Concept-to-Text Generation

  2005cited by this paper
• Evaluation of an NLG System using Post-Edit Data: Lessons Learnt

  2005cited by this paper
• Lessons from Deploying NLG Technology for Marine Weather Forecast Text Generation

  2004cited by this paper
• Catching the Drift: Probabilistic Content Models, with Applications to Generation and Summarization

  2004cited by this paper
• ROUGE: A Package for Automatic Evaluation of Summaries

  2004cited by this paper
• Trainable Sentence Planning for Complex Information Presentations in Spoken Dialog Systems

  2004cited by this paper
• Statistical Acquisition of Content Selection Rules for Natural Language Generation

  2003influential reference
• Generating English summaries of time series data using the Gricean maxims

  2003influential reference
• Content Planner Construction via Evolutionary Algorithms and a Corpus-based Fitness Function

  2002cited by this paper
• Automatic evaluation of machine translation quality using n-gram co-occurrence statistics

  2002cited by this paper
• Should Corpora Texts Be Gold Standards for NLG?

  2002cited by this paper
• Training a sentence planner for spoken dialogue using boosting

  2002cited by this paper
• Bleu: a Method for Automatic Evaluation of Machine Translation

  2002cited by this paper
• ILEX: an architecture for a dynamic hypertext generation system

  2001cited by this paper
• Natural Language Processing and User Modeling: Synergies and Limitations

  2001cited by this paper
• A Two-Staged Model For Content Determination

  2001cited by this paper
• Types of Knowledge Required to Personalise Smoking Cessation Letters

  1999influential reference
• Experiments Using Stochastic Search for Text Planning

  1998cited by this paper
• TREND: A System for Generating Intelligent Descriptions of Time-Series Data

  1998influential reference
• Generation that Exploits Corpus-Based Statistical Knowledge

  1998cited by this paper
• Building Natural-Language Generation Systems

  1996influential reference
• Why looking isn't always seeing: readership skills and graphical programming

  1995cited by this paper
• Two-Level, Many-Paths Generation

  1995cited by this paper
• An introduction to machine translation

  1992cited by this paper
• Rhetorical Structure Theory: Toward a functional theory of text organization

  1988cited by this paper
• Design of a Knowledge-Based Report Generator

  1983cited by this paper

• A Novel Benchmark for Persian Table-to-Text Generation: A New Dataset and Baseline Experiments

  2025cites this paper
• Impact of Model Size on Fine-tuned LLM Performance in Data-to-Text Generation: A State-of-the-Art Investigation

  2024cites this paper
• Effectiveness of Data Augmentation and Pretraining for Improving Neural Headline Generation in Low-Resource Settings

  2022cites this paper
• Emotional Dialogue System in Open-domain Human-Machine Interactions

  2022cites this paper
• Most NLG is Low-Resource: here’s what we can do about it

  2022cites this paper
• Neural Data-to-Text Generation Based on Small Datasets: Comparing the Added Value of Two Semi-Supervised Learning Approaches on Top of a Large Language Model

  2022cites this paper
• Challenges and Opportunities in Low-Resource Natural Language Generation

  2022cites this paper
• Neural Data-to-Text Generation with LM-based Text Augmentation

  2021cites this paper
• A Baseline Document Planning Method for Automated Journalism

  2021cites this paper
• Enhancing Content Planning for Table-to-Text Generation with Data Understanding and Verification

  2020cites this paper
• Human-like Time Series Summaries via Trend Utility Estimation

  2020cites this paper
• DART: A Lightweight Quality-Suggestive Data-to-Text Annotation Tool

  2020cites this paper
• Table-to-Text Generation with Effective Hierarchical Encoder on Three Dimensions (Row, Column and Time)

  2019influential citation
• From Numerical Sensor Data to Semantic Representations: A Data-driven Approach for Generating Linguistic Descriptions

  2018cites this paper
• Automated learning of templates for data-to-text generation: comparing rule-based, statistical and neural methods

  2018cites this paper
• Everything you always wanted to know about a dataset: studies in data summarisation

  2018cites this paper
• Comparison of Intellectus Statistics and Statistical Package for the Social Sciences - Differences in User Performance Based on Presentation of Statistical Data

  2018cites this paper
• Data-to-Text Generation Improves Decision-Making Under Uncertainty

  2017cites this paper
• Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation

  2017cites this paper
• PASS: A Dutch data-to-text system for soccer, targeted towards specific audiences

  2017cites this paper