Toward Interface Defaults for Vague Modifiers in Natural Language Interfaces for Visual Analysis

Natural language interfaces for data visualizations tools are growing in importance, but little research has been done on how a system should respond to questions that contain vague modifiers like "high" and "expensive." This paper makes a first step toward design guidelines for this problem, based on existing research from cognitive linguistics and the results of a new empirical study with 274 crowdsourcing participants. A comparison of four bar chart-based views finds that highlighting the top items according to distribution-sensitive values is preferred in most cases and is a good starting point as a design guideline.

[1]  Daniel Jurafsky,et al.  Textual Analogy Parsing: What’s Shared and What’s Compared among Analogous Facts , 2018, EMNLP.

[2]  Stephanie Solt,et al.  Experimenting with Degree , 2012 .

[3]  A R Rodolfo Pazos,et al.  Natural Language Interfaces to Databases: An Analysis of the State of the Art , 2013, HIS 2013.

[4]  Stefano Vegnaduzzo.  Acquisition of Subjective Adjectives with Limited Resources , 2004 .

[5]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[6]  Kees van Deemter.  Not Exactly: In Praise of Vagueness , 2010 .

[7]  Noah D. Goodman,et al.  Subjectivity Predicts Adjective Ordering Preferences , 2017, Open Mind.

[8]  Vidya Setlur,et al.  Eviza: A Natural Language Interface for Visual Analysis , 2016, UIST.

[9]  Catherine Blake,et al.  Identifying Comparative Claim Sentences in Full-Text Scientific Articles , 2012, ACL 2012.

[10]  Christopher Kennedy.  Vagueness and grammar: the semantics of relative and absolute gradable adjectives , 2007 .

[11]  Karrie Karahalios,et al.  DataTone: Managing Ambiguity in Natural Language Interfaces for Data Visualization , 2015, UIST.

[12]  John T. Stasko,et al.  Orko: Facilitating Multimodal Interaction for Visual Exploration and Analysis of Networks , 2018, IEEE Transactions on Visualization and Computer Graphics.

[13]  Bert Weijters,et al.  When Cheap Isn't the Same as Not Expensive: Generic Price Terms and Their Negations , 2018 .

[14]  Eytan Adar,et al.  The impact of social information on visual judgments , 2011, CHI.

[15]  Rodolfo A. Pazos Rangel,et al.  Natural Language Interfaces to Databases: An Analysis of the State of the Art , 2013, Recent Advances on Hybrid Intelligent Systems.

[16]  Noah D. Goodman,et al.  How Tall Is Tall? Compositionality, Statistics, and Gradable Adjectives , 2009 .

[17]  Vidya Setlur,et al.  Applying Pragmatics Principles for Interaction with Visual Analytics , 2018, IEEE Transactions on Visualization and Computer Graphics.

[18]  Michael Franke,et al.  Meaning and Use of Gradable Adjectives: Formal Modeling Meets Empirical Data , 2014, CogSci.

[19]  Jeffrey Heer,et al.  Crowdsourcing graphical perception: using mechanical turk to assess visualization design , 2010, CHI.

[20]  Jonas Kuhn,et al.  A Corpus of Comparisons in Product Reviews , 2014, LREC.

[21]  Oren Etzioni,et al.  Modern Natural Language Interfaces to Databases: Composing Statistical Parsing with Semantic Tractability , 2004, COLING.

[22]  Christopher Kennedy,et al.  Scale Structure, Degree Modification, and the Semantics of Gradable Predicates , 2005 .

[23]  Gerard de Melo,et al.  Good, Great, Excellent: Global Inference of Semantic Intensities , 2013, Transactions of the Association for Computational Linguistics.

[24]  Vidya Setlur,et al.  Inferencing underspecified natural language utterances in visual analysis , 2019, IUI.

[25]  Eric Fosler-Lussier,et al.  Identification, characterization, and grounding of gradable terms in clinical text , 2016, BioNLP@ACL.

[26]  Peter Thanisch,et al.  Natural language interfaces to databases – an introduction , 1995, Natural Language Engineering.