Towards Table-to-Text Generation with Numerical Reasoning

By Lya Hulliyyatus Suadaa, Hidetaka Kamigaito, Kotaro Funakoshi, Manabu Okumura, Hiroya Takamura. 2021

71 citations recorded by the source corpus.

Recent neural text generation models have shown significant improvement in generating descriptive text from structured data such as table formats. One of the remaining important challenges is generating more analytical descriptions that can be inferred from facts in a data source. The use of a template-based generator and a pointer-generator is among the potential alternatives for table-to-text generators. In this paper, we propose a framework consisting of a pre-trained model and a copy mechanism. The pre-trained models are fine-tuned to produce fluent text that is enriched with numerical reasoning. However, it still lacks fidelity to the table contents. The copy mechanism is incorporated in the fine-tuning step by using general placeholders to avoid producing hallucinated phrases that are not supported by a table while preserving high fluency. In summary, our contributions are (1) a new dataset for numerical table-to-text generation using pairs of a table and a paragraph of a table description with richer inference from scientific papers, and (2) a table-to-text generation framework enriched with numerical reasoning.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Pascale Fung
2. Andrea Madotto
3. Ji-rong Wen
4. Wayne Xin Zhao
5. Wenliang Dai
6. Nayeon Lee
7. Yan Xu
8. Etsuko Ishii

In Natural Language Processing

1. Pascale Fung
2. Nayeon Lee
3. Andrea Madotto
4. Etsuko Ishii
5. Yejin Bang
6. Yan Xu
7. Rita Frieske
8. Jian-Yun Nie

Citations in the corpus

• Survey of Hallucination in Natural Language Generation (2022, background): “Firstly, numbers contain information about scales and are common and crucial in the Data-toText task [175, 230].”
• TaTa: A Multilingual Table-to-Text Dataset for African Languages (2022, unknown): “Data-to-text tasks are also an effective testbed to assess reasoning capabilities of models (Suadaa et al., 2021).”
• LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks (2022, background): “[118] Lya Hulliyyatus Suadaa, Hidetaka Kamigaito, Kotaro Funakoshi, Manabu Okumura, and Hiroya Takamura.”
• Pre-Trained Language Models for Text Generation: A Survey (2022, background): “[172]; Adding Target Information as Input: Chen et al.”