Inferencing underspecified natural language utterances in visual analysis

TLDR

Ambiguity and underspecification in user utterances pose challenges for natural language interfaces in visual analytics, where platform constraints and high precision/recall expectations demand careful inferencing. The paper introduces a system that resolves partial utterances using syntactic and semantic constraints of the underlying analytical expressions. The system extends inferencing with information‑visualization best practices, uses heuristics to constrain inference candidates and ranks them by relevancy, and evaluates inferred interpretations for relevancy and analytical usefulness.

Abstract

Handling ambiguity and underspecification of users' utterances is challenging, particularly for natural language interfaces that help with visual analytical tasks. Constraints in the underlying analytical platform and the users' expectations of high precision and recall require thoughtful inferencing to help generate useful responses. In this paper, we introduce a system to resolve partial utterances based on syntactic and semantic constraints of the underlying analytical expressions. We extend inferencing based on best practices in information visualization to generate useful visualization responses. We employ heuristics to help constrain the solution space of possible inferences, and apply ranking logic to the interpretations based on relevancy. We evaluate the quality of inferred interpretations based on relevancy and analytical usefulness.