Table-to-Text: Describing Table Region With Natural Language

By Junwei Bao, Duyu Tang, Nan Duan, Zhao Yan, Yuanhua Lv, M. Zhou, Tuo Zhao. 2018

116 citations recorded by the source corpus.

In this paper, we present a generative model to generate a natural language sentence describing a table region, e.g., a row. The model maps a row from a table to a continuous vector and then generates a natural language sentence by leveraging the semantics of a table. To deal with rare words appearing in a table, we develop a flexible copying mechanism that selectively replicates contents from the table in the output sequence. Extensive experiments demonstrate the accuracy of the model and the power of the copying mechanism. On two synthetic datasets, WIKIBIO and SIMPLEQUESTIONS, our model improves the current state-of-the-art BLEU-4 score from 34.70 to 40.26 and from 33.32 to 39.12, respectively. Furthermore, we introduce an open-domain dataset WIKITABLETEXT including 13,318 explanatory sentences for 4,962 tables. Our model achieves a BLEU-4 score of 38.23, which outperforms template based and language model based approaches.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Extraction, Natural Language Generation

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. Caiming Xiong
2. Mohit Bansal
3. Richard Socher
4. Luke S. Zettlemoyer
5. Percy Liang
6. Hannaneh Hajishirzi
7. Jonathan Berant
8. Graham Neubig

In Computer Vision and Pattern Recognition

1. Caiming Xiong
2. Richard Socher
3. Lei Li
4. Luc Van Gool
5. Jingren Zhou
6. Jianfeng Gao
7. Hannaneh Hajishirzi
8. Sameer Singh

In Information Extraction

1. Alexandre Passos
2. Ming-Wei Chang
3. Hao Zhou
4. Richard Socher
5. Caiming Xiong
6. Sameer Singh
7. Nazneen Rajani

In Natural Language Generation

1. Lei Li
2. Rui Zhang
3. Tianyu Liu
4. Ming-Wei Chang
5. Richard Socher
6. Caiming Xiong
7. Zhifang Sui
8. Baobao Chang

Citations in the corpus

• DART: Open-Domain Structured Data Record to Text Generation (2020, background): “Recently, some open-domain table-to-text datasets have been proposed including WikiTableText (Bao et al., 2018), LogicNLP (Chen et al., 2020a), and ToTTo (Parikh et al., 2020).”
• Variational Template Machine for Data-to-Text Generation (2020, methodology): “There are several recent methods utilizing neural encoder-decoder frameworks to generate text description from data tables (Lebret et al., 2016; Bao et al., 2018; Chisholm et al., 2017; Liu et al., 2018).”
• Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation (2021, methodology): “Previous methods (Liu et al., 2018; Nie et al., 2018; Bao et al., 2018) are usually trained in an †Corresponding author. end-to-end fashion with the encoder-decoder architecture (Bahdanau et al., 2015).”
• Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View (2021, background): “Recently, end-to-end learning becomes a trend (Mei, Bansal, and Walter 2016; Chisholm, Radford, and Hachey 2017; Kaffee et al. 2018; Jhamtani et al. 2018; Bao et al. 2018; Liu et al. 2019a; Dušek, Novikova, and Rieser 2020) in this field.”
• FRUIT: Faithfully Reflecting Updated Information in Text (2021, methodology): “…works have developed sys- 048 tems for distilling external knowledge into text 049 (e.g., Wikipedia article generation) by treating the 050 problem as multi-document summarization (Liu 051 et al., 2018; Shi et al., 2021) or data-to-text genera- 052 tion (Bao et al., 2018; Parikh et al., 2020).”