Variational Template Machine for Data-to-Text Generation

By Rong Ye, Wenxian Shi, Hao Zhou, Zhongyu Wei, Lei Li. 2020

45 citations recorded by the source corpus.

How to generate descriptions from structured data organized in tables? Existing approaches using neural encoder-decoder models often suffer from lacking diversity. We claim that an open set of templates is crucial for enriching the phrase constructions and realizing varied generations. Learning such templates is prohibitive since it often requires a large paired corpus, which is seldom available. This paper explores the problem of automatically learning reusable "templates" from paired and non-paired data. We propose the variational template machine (VTM), a novel method to generate text descriptions from data tables. Our contributions include: a) we carefully devise a specific model architecture and losses to explicitly disentangle text template and semantic content information, in the latent spaces, and b)we utilize both small parallel data and large raw text without aligned tables to enrich the template learning. Experiments on datasets from a variety of different domains show that VTM is able to generate more diversely while keeping a good fluency and quality.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, 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. Jianfeng Gao
2. Caiming Xiong
3. Mohit Bansal
4. Richard Socher
5. Percy Liang
6. Luke S. Zettlemoyer
7. Graham Neubig
8. Noah A. Smith

In Computer Vision and Pattern Recognition

1. Caiming Xiong
2. Jianfeng Gao
3. Richard Socher
4. Luc Van Gool
5. Chunhua Shen
6. Cordelia Schmid
7. Lei Li
8. Dacheng Tao

In Natural Language Processing

1. Jianfeng Gao
2. Caiming Xiong
3. Richard Socher
4. Luke S. Zettlemoyer
5. Mohit Bansal
6. Percy Liang
7. Samuel R. Bowman
8. Dragomir R. Radev

In Natural Language Generation

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

Citations in the corpus

• DART: Open-Domain Structured Data Record to Text Generation (2020, background): “Recently, neural encoder-decoder models based on attention and copy mechanisms have shown promising results (Wiseman et al., 2017; Liu et al., 2018; Gehrmann et al., 2018; Puduppully et al., 2018, 2019; Iso et al., 2019; Castro Ferreira et al., 2019; Shen et al., 2019; Roberti et al., 2019; Zhu et a”
• Plan-then-Generate: Controlled Data-to-Text Generation via Planning (2021, background): “Many existing studies are dedicated to building end-to-end neural models with different strategies like soft-templates (Wiseman et al., 2018; Ye et al., 2020), attention awareness (Liu et al., 2018; Colin and Gardent, 2019), and retrieved prototypes (Li et al., 2020; Su et al., 2021b).”
• Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View (2021, background): “2020b), template-like (Liu et al. 2017; Wiseman, Shieber, and Rush 2018; Shen et al. 2020; Li and Rush 2020; Ye et al. 2020) or controllable generation (Peng et al.”
• A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation (2021, background): “text sequences which specify the narrative ordering, and implicit plans (Wiseman et al., 2018; Ye et al., 2020; Shen et al., 2020; Li and Rush, 2020), e.”
• Generate Your Counterfactuals: Towards Controlled Counterfactual Generation for Text (2020, background): “The condition can also be structured data such as a Wikipedia infobox or even a knowledge graph (Ye et al. 2020).”
• MTG: A Benchmark Suite for Multilingual Text Generation (2021, background): “, 2018), tables (Ye et al., 2020) or texts (Guan et al.”