Improving User Controlled Table-To-Text Generation Robustness

TL;DR

This paper enhances table-to-text generation robustness by fine-tuning models with simulated noisy user inputs, significantly improving performance on realistic, noisy user data while maintaining state-of-the-art results.

Contribution

It introduces a fine-tuning approach using simulated noisy cell selections to improve robustness in user-controlled table-to-text generation.

Findings

Models fine-tuned with noisy data improve BLEU scores by 4.85 on noisy test cases.

Fine-tuning maintains competitive performance on clean test data.

Proposed method enhances real-world applicability of table-to-text generators.

Abstract

In this work we study user controlled table-to-text generation where users explore the content in a table by selecting cells and reading a natural language description thereof automatically produce by a natural language generator. Such generation models usually learn from carefully selected cell combinations (clean cell selections); however, in practice users may select unexpected, redundant, or incoherent cell combinations (noisy cell selections). In experiments, we find that models perform well on test sets coming from the same distribution as the train data but their performance drops when evaluated on realistic noisy user inputs. We propose a fine-tuning regime with additional user-simulated noisy cell selections. Models fine-tuned with the proposed regime gain 4.85 BLEU points on user noisy test cases and 1.4 on clean test cases; and achieve comparable state-of-the-art performance on the ToTTo dataset.