GenNI: Human-AI Collaboration for Data-Backed Text Generation

TL;DR

GenNI is an interactive visual system that enables high-level human-AI collaboration for data-backed text generation, improving control and accuracy in natural language outputs from structured data.

Contribution

It introduces a novel visual interface with explicit control states for better human-AI collaboration in text generation tasks.

Findings

Improved generation quality over uncontrolled approaches

Fine-grained control enhances user satisfaction

Effective use cases demonstrated in experiments

Abstract

Table2Text systems generate textual output based on structured data utilizing machine learning. These systems are essential for fluent natural language interfaces in tools such as virtual assistants; however, left to generate freely these ML systems often produce misleading or unexpected outputs. GenNI (Generation Negotiation Interface) is an interactive visual system for high-level human-AI collaboration in producing descriptive text. The tool utilizes a deep learning model designed with explicit control states. These controls allow users to globally constrain model generations, without sacrificing the representation power of the deep learning models. The visual interface makes it possible for users to interact with AI systems following a Refine-Forecast paradigm to ensure that the generation system acts in a manner human users find suitable. We report multiple use cases on two experiments that improve over uncontrolled generation approaches, while at the same time providing fine-grained control. A demo and source code are available at https://genni.vizhub.ai .