Fuzzy-Based Language Grounding of Geographical References: From Writers to Readers

We describe an applied methodology to build fuzzy models of geographical expressions, which are meant to be used for natural language generation purposes. Our approach encompasses a language grounding task within the development of an actual data to- text system for the generation of textual descriptions of live weather data. For this, we gathered data from meteorologists through a survey and built consistent fuzzy models that aggregate the interpersonal variations found among the experts. A subset of the models was utilized in an illustrative use case, where we generated linguistic descriptions of weather maps for specific geographical expressions. These were used in a task-based evaluation to determine how well potential readers are able to identify the geographical expressions grounded on the models.

[1]  Ehud Reiter,et al.  SumTime-Mousam: Configurable marine weather forecast generator , 2003 .

[2]  Peter Fisher,et al.  Sorites paradox and vague geographies , 2000, Fuzzy Sets Syst..

[3]  Yuval Shahar,et al.  An automated knowledge-based textual summarization system for longitudinal, multivariate clinical data , 2016, J. Biomed. Informatics.

[4]  Ehud Reiter,et al.  Selecting the Content of Textual Descriptions of Geographically Located Events in Spatio-Temporal Weather Data , 2007, SGAI Conf..

[5]  Vincent B. Robinson,et al.  A Perspective on the Fundamentals of Fuzzy Sets and their Use in Geographic Information Systems , 2003, Trans. GIS.

[6]  Ehud Reiter,et al.  Generating Approximate Geographic Descriptions , 2009, ENLG.

[7]  A. Ramos-Soto,et al.  On the role of linguistic descriptions of data in the building of natural language generation systems , 2016, Fuzzy Sets Syst..

[8]  Senén Barro,et al.  Linguistic Descriptions for Automatic Generation of Textual Short-Term Weather Forecasts on Real Prediction Data , 2015, IEEE Trans. Fuzzy Syst..

[9]  Slawomir Zadrozny,et al.  Computing With Words Is an Implementable Paradigm: Fuzzy Queries, Linguistic Data Summaries, and Natural-Language Generation , 2010, IEEE Transactions on Fuzzy Systems.

[10]  Ehud Reiter,et al.  Using Spatial Reference Frames to Generate Grounded Textual Summaries of Georeferenced Data , 2008, INLG.

[11]  Daniel Sánchez,et al.  Linguistic query answering on data cubes with time dimension , 2011, Int. J. Intell. Syst..

[12]  Peter Fisher,et al.  An investigation of the meaning of near and close on a university campus , 1991 .

[13]  Senén Barro,et al.  A Probabilistic Quantifier Fuzzification Mechanism: The Model and Its Evaluation for Information Retrieval , 2005, IEEE Transactions on Fuzzy Systems.

[14]  Emiel Krahmer,et al.  Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation , 2017, J. Artif. Intell. Res..

[15]  Ehud Reiter,et al.  Should Corpora Texts Be Gold Standards for NLG? , 2002, INLG.

[16]  Deb Roy,et al.  Connecting language to the world , 2005, Artif. Intell..

[17]  Ehud Reiter,et al.  An Architecture for Data-to-Text Systems , 2007, ENLG.

[18]  Richard I. Kittredge,et al.  Using natural-language processing to produce weather forecasts , 1994, IEEE Expert.

[19]  Rodrigo de Oliveira,et al.  Designing an Algorithm for Generating Named Spatial References , 2015, ENLG.

[20]  Nicolás Marín,et al.  Linguistic Summarization of Time Series Data using Genetic Algorithms , 2011, EUSFLAT Conf..

[21]  Albert Gatt,et al.  Automatic generation of natural language nursing shift summaries in neonatal intensive care: BT-Nurse , 2012, Artif. Intell. Medicine.

[22]  Daniel Sánchez,et al.  Fuzzy quantification: a state of the art , 2014, Fuzzy Sets Syst..

[23]  Juan Carlos Vidal,et al.  Characterizing Quantifier Fuzzification Mechanisms: a behavioral guide for practical applications , 2016, Fuzzy Sets Syst..

[24]  S. Levinson.  Space in language and cognition: Explorations in cognitive diversity , 2003 .

[25]  Jim Hunter,et al.  SumTime-Turbine: A Knowledge-Based System to Communicate Gas Turbine Time-Series Data , 2003, IEA/AIE.

[26]  Jim Hunter,et al.  Choosing words in computer-generated weather forecasts , 2005, Artif. Intell..

[27]  Daniel Sánchez,et al.  On generating linguistic descriptions of time series , 2016, Fuzzy Sets Syst..

[28]  Daniel Sánchez,et al.  Fuzzy cardinality based evaluation of quantified sentences , 2000, Int. J. Approx. Reason..

[29]  Rodrigo de Oliveira,et al.  Absolute and Relative Properties in Geographic Referring Expressions , 2016, INLG.

[30]  Daniel Sánchez,et al.  A discussion on fuzzy cardinality and quantification. Some applications in image processing , 2014, Fuzzy Sets Syst..

[31]  Senén Barro,et al.  Fuzzy sets across the natural language generation pipeline , 2016, Progress in Artificial Intelligence.

[32]  Verena Rieser,et al.  The E2E Dataset: New Challenges For End-to-End Generation , 2017, SIGDIAL Conference.