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

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 .

IEEE VIS 2021

References in corpus (13)

• Auto-Encoding Variational Bayes
• Sequence to Sequence Learning with Neural Networks
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Building Natural-Language Generation Systems
• Visualizing and Understanding Recurrent Networks
• CTRL: A Conditional Transformer Language Model for Controllable Generation
• Style Transfer from Non-Parallel Text by Cross-Alignment
• TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents
• Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings
• A Flexible Shallow Approach to Text Generation
• RNNbow: Visualizing Learning via Backpropagation Gradients in Recurrent Neural Networks
• Text-to-Text Pre-Training for Data-to-Text Tasks
• Latent Template Induction with Gumbel-CRFs

Cited by in corpus (3)

• generAItor: Tree-in-the-Loop Text Generation for Language Model Explainability and Adaptation
• Comparing Native and Non-native English Speakers' Behaviors in Collaborative Writing through Visual Analytics
• Human-Computer Interaction and Visualization in Natural Language Generation Models: Applications, Challenges, and Opportunities