Map&Make: Schema Guided Text to Table Generation
Preprint
Abstract
Transforming dense, detailed, unstructured text into an interpretable and summarised table, also colloquially known as Text-to-Table generation, is an essential task for information retrieval. Current methods, however, miss out on how and what complex information to extract; they also lack the ability to infer data from the text. In this paper, we introduce a versatile approach, Map&Make, which "dissects" text into propositional atomic statements. This facilitates granular decomposition to extract the latent schema. The schema is then used to populate the tables that capture the qualitative nuances and the quantitative facts in the original text. Our approach is tested against two challenging datasets, Rotowire, renowned for its complex and multi-table schema, and Livesum, which demands numerical aggregation. By carefully identifying and correcting hallucination errors in Rotowire, we aim to achieve a cleaner and more reliable benchmark. We evaluate our method rigorously on a comprehensive suite of comparative and referenceless metrics. Our findings demonstrate significant improvement results across both datasets with better interpretability in Text-to-Table generation. Moreover, through detailed ablation studies and analyses, we investigate the factors contributing to superior performance and validate the practicality of our framework in structured summarization tasks.Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- Table-GPT: Table Fine-tuned GPT for Diverse Table TasksProceedings of the ACM on Management of Data, 2024
- Automatic Evaluation of Attribution by Large Language Models2023
- Text-to-Table: A New Way of Information Extraction2022
- HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation2022
- A Frustratingly Easy Approach for Entity and Relation Extraction2021
- HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data2020
- On Faithfulness and Factuality in Abstractive Summarization2020
- Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraints2020
- Table-to-Text: Describing Table Region With Natural LanguageProceedings of the AAAI Conference on Artificial Intelligence, 2018
- Table-to-Text Generation by Structure-Aware Seq2seq LearningProceedings of the AAAI Conference on Artificial Intelligence, 2018