# Table Caption Generation in Scholarly Documents Leveraging Pre-trained Language Models

arXiv: https://arxiv.org/abs/2108.08111 · HTML: https://mlsanity.com/paper/2108.08111/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 20 references that are in the map.
- First posted on arXiv 18 Aug 2021.

## Builds on (most cited first, 12 of 12)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [TAPAS: Weakly Supervised Table Parsing via Pre-training](https://mlsanity.com/paper/2004.02349/) (2020)
- [Challenges in Data-to-Document Generation](https://mlsanity.com/paper/1707.08052/) (2017)
- [DocBank: A Benchmark Dataset for Document Layout Analysis](https://mlsanity.com/paper/2006.01038/) (2020)
- [Data-to-Text Generation with Content Selection and Planning](https://mlsanity.com/paper/1809.00582/) (2018)
- [Logical Natural Language Generation from Open-Domain Tables](https://mlsanity.com/paper/2004.10404/) (2020)
- [Table-to-Text: Describing Table Region with Natural Language](https://mlsanity.com/paper/1805.11234/) (2018)
- [Data-to-text Generation with Macro Planning](https://mlsanity.com/paper/2102.02723/) (2021)
- [A Hierarchical Model for Data-to-Text Generation](https://mlsanity.com/paper/1912.10011/) (2019)
- [Web Table Extraction, Retrieval and Augmentation: A Survey](https://mlsanity.com/paper/2002.00207/) (2020)
- [Learning to Select, Track, and Generate for Data-to-Text](https://mlsanity.com/paper/1907.09699/) (2019)

## Built on by (most cited first, 1 of 1)

- [Multimodal hierarchical Variational AutoEncoders with Factor Analysis latent space](https://mlsanity.com/paper/2207.09185/) (2022)

## Abstract (arXiv)

This paper addresses the problem of generating table captions for scholarly documents, which often require additional information outside the table. To this end, we propose a method of retrieving relevant sentences from the paper body, and feeding the table content as well as the retrieved sentences into pre-trained language models (e.g. T5 and GPT-2) for generating table captions. The contributions of this paper are: (1) discussion on the challenges in table captioning for scholarly documents; (2) development of a dataset DocBank-TB, which is publicly available; and (3) comparison of caption generation methods for scholarly documents with different strategies to retrieve relevant sentences from the paper body. Our experimental results showed that T5 is the better generation model for this task, as it outperformed GPT-2 in BLEU and METEOR implying that the generated text are clearer and more precise. Moreover, inputting relevant sentences matching the row header or whole table is effective.