Representing and Querying Line Graphs in Natural Language: The iGraph System

Numerical information is often presented in graphs. However, this medium is problematic for certain audiences such as inexperienced graph readers, people with visual impairments and users of mobile technologies featuring small screens. We have developed a system called iGraph which provides short verbal descriptions with the information depicted in graphs and a way of interacting with it by means of dialogue in natural language. In this paper, we present the general architecture of the system and its representational and querying mechanisms, together with a glimpse of the natural language interface.

[1]  Marc Schröder,et al.  The German Text-to-Speech Synthesis System MARY: A Tool for Research, Development and Teaching , 2003, Int. J. Speech Technol..

[2]  Stuart M. Shieber,et al.  Prolog and Natural-Language Analysis , 1987 .

[3]  Kathleen McKeown,et al.  Text generation: using discourse strategies and focus constraints to generate natural language text , 1985 .

[4]  Chris Mellish.  Generating natural language explanations from plans , 1990 .

[5]  C. Pollard,et al.  Center for the Study of Language and Information , 2022 .

[6]  Jim Hunter,et al.  Exploiting a parallel TEXT - DATA corpus , 2003 .

[7]  Robert Dale,et al.  Building applied natural language generation systems , 1997, Natural Language Engineering.

[8]  Guy Lapalme,et al.  A Prolog implementation of the Functional Unification Grammar Formalism , 1998 .

[9]  Stephan M. Kerpedjiev.  Automatic Generation of Multimodal Weather Reports from Datasets , 1992, ANLP.

[10]  Michael A. Covington,et al.  Natural Language Processing for Prolog Programmers , 1993 .

[11]  Jim Hunter,et al.  A New Architecture for Summarising Time Series Data , 2004 .

[12]  Michael Wollowski,et al.  Search and Inference with Diagrams , 2005, IMSA.

[13]  Jacques Robin,et al.  Revision-based generation of natural language summaries providing historical background: corpus-based analysis, design, implementation and evaluation , 1995 .

[14]  David Milward,et al.  Ontology-Based Dialogue Systems , 2003 .

[15]  M. Corio,et al.  Generation of texts for information graphics , 1999 .

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

[17]  Massimo Fasciano.  Génération intégrée de textes et de graphiques statistiques , 1996 .

[18]  Nancy Green,et al.  Towards generating textual summaries of graphs , 2001, HCI.

[19]  Johanna D. Moore,et al.  Describing Complex Charts in Natural Language: A Caption Generation System , 1998, CL.

[20]  Avi Parush,et al.  Helping People with Visual Impairments Gain Access to Graphical Information Through Natural Language: The iGraph System , 2006, ICCHP.

[21]  Guy Lapalme,et al.  PostGraphe: A System for the Generation of Statistical Graphics and Text , 1996, INLG.

[22]  SWI-Prolog 5.6 Reference Manual , 2004 .

[23]  Volker Haarslev,et al.  Proceedings of the 2004 International Workshop on Description Logics (DL2004), Whistler, British Columbia, Canada, June 6-8, 2004 , 2004, Description Logics.

[24]  Chris Mellish,et al.  An Architecture for Opportunistic Text Generation , 1998, INLG.

[25]  Guy Lapalme,et al.  Intentions in the Coordinated Generation of Graphics and Text from Tabular Data , 2000, Knowledge and Information Systems.

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