Towards Controlled Table-to-Text Generation with Scientific Reasoning
This work addresses the challenge of automating scientific document analysis for individuals needing to extract information from complex tabular data, but it is incremental as it builds on existing pre-trained language models.
The paper tackles the problem of generating fluent and logical descriptions from scientific tables that match user preferences, and it introduces a new dataset CTRLSciTab and a novel architecture that outperforms baseline models, though large models still struggle with accuracy.
The sheer volume of scientific experimental results and complex technical statements, often presented in tabular formats, presents a formidable barrier to individuals acquiring preferred information. The realms of scientific reasoning and content generation that adhere to user preferences encounter distinct challenges. In this work, we present a new task for generating fluent and logical descriptions that match user preferences over scientific tabular data, aiming to automate scientific document analysis. To facilitate research in this direction, we construct a new challenging dataset CTRLSciTab consisting of table-description pairs extracted from the scientific literature, with highlighted cells and corresponding domain-specific knowledge base. We evaluated popular pre-trained language models to establish a baseline and proposed a novel architecture outperforming competing approaches. The results showed that large models struggle to produce accurate content that aligns with user preferences. As the first of its kind, our work should motivate further research in scientific domains.