Table-to-text Generation by Structure-aware Seq2seq Learning
By Tianyu Liu, Kexiang Wang, Lei Sha, Baobao Chang, Zhifang Sui. 2017
284 citations recorded by the source corpus.
Table-to-text generation aims to generate a description for a factual table which can be viewed as a set of field-value records. To encode both the content and the structure of a table, we propose a novel structure-aware seq2seq architecture which consists of field-gating encoder and description generator with dual attention. In the encoding phase, we update the cell memory of the LSTM unit by a field gate and its corresponding field value in order to incorporate field information into table representation. In the decoding phase, dual attention mechanism which contains word level attention and field level attention is proposed to model the semantic relevance between the generated description and the table. We conduct experiments on the WIKIBIO dataset which contains over 700k biographies and corresponding infoboxes from Wikipedia. The attention visualizations and case studies show that our model is capable of generating coherent and informative descriptions based on the comprehensive understanding of both the content and the structure of a table. Automatic evaluations also show our model outperforms the baselines by a great margin. Code for this work is available on https://github.com/tyliupku/wiki2bio.
Subfields: Artificial Intelligence, Literature and Literary Theory, 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
- Mohit Bansal
- Jianfeng Gao
- Graham Neubig
- Luke S. Zettlemoyer
- Percy Liang
- Caiming Xiong
- Yejin Choi
- Richard Socher
In Literature and Literary Theory
- Anette Frank
- Lei Li
- Dong Yu
- William Yang Wang
- Thomas Lukasiewicz
- Graham Neubig
- Mirella Lapata
- Richard Socher
In Natural Language Processing
- Mohit Bansal
- Graham Neubig
- Jianfeng Gao
- Mirella Lapata
- Luke S. Zettlemoyer
- Caiming Xiong
- Richard Socher
- Yejin Choi
In Natural Language Generation
- Mirella Lapata
- Ratish Puduppully
- Mohit Bansal
- Rui Zhang
- William Yang Wang
- Lei Li
- Sebastian Gehrmann
- Li Dong
Citations in the corpus
- DART: Open-Domain Structured Data Record to Text Generation (2020, methodology): “…Reiter et al., 2005; Liang et al., 2009; Konstas and Lapata, 2012; Mei et al., 2016), biographical texts (Lebret et al., 2016; Sha et al., 2018; Liu et al., 2018; Vou-giouklis et al., 2018; Perez-Beltrachini and Lap-ata, 2018), knowledge-base descriptions (Oâ ˘A ´Z-Donnell et al., 2000; Banik…”
- ToTTo: A Controlled Table-To-Text Generation Dataset (2020, background): “…can also test a model’s ability for reasoning and numerical inference (Wiseman et al., 2017) and for building representations of structured objects (Liu et al., 2018), providing an interesting complement to tasks that test these aspects in the NLU setting (Pasupat and Liang, 2015; Chen et al.,…”
- Few-Shot NLG with Pre-Trained Language Model (2019, methodology): “As we can see, the original architecture FGoriginal (Liu et al., 2018), which obtains state-ofthe-art result on WIKIBIO full set, performs very poorly under few-shot learning.”
- Data-to-Text Generation with Content Selection and Planning (2018, methodology): “Perez-Beltrachini and Lapata (2018) introduce a content selection component (based on multi-instance learning) without content planning, while Liu et al. (2017) propose a sentence planning mechanism which orders the contents of a Wikipedia infobox in order to generate a single sentence.”
- 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).”
- TabNet: Attentive Interpretable Tabular Learning (2019, methodology): “Table-to-text models extract textual information from structured data, and some of the recent works propose a sequential mechanism for field-level attention (Liu et al., 2017) (Bao et al., 2019).”
- Latent Relation Language Models (2019, background): “…sequence modeling, prevalent approaches for language generation from KGs employ sequence-to-sequence models (Sutskever et al., 2014) with special attention mechanisms tailored for input structures such as graphs (Wang et al., 2018) or tables (Liu et al., 2018; Perez-Beltrachini and Lap-ata, 2018).”
- Using natural language generation to bootstrap missing Wikipedia articles: A human-centric perspective (2022, methodology): “There is a large body of work that uses the encoder-decoder framework from machine translation [12,82] for NLG [11,21,22,51,55,59,79,84,90,91].”
- Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation (2019, methodology): “• Structure Aware Seq2Seq (Liu et al., 2018): A state-of-the-art method on the WikiBio dataset in terms of BLEU.”
- Learning Neural Templates for Text Generation (2018, methodology): “Results were obtained using the NTemp+AR model from Table 1. database-to-text generation have since surpassed the results of Lebret et al. (2016) and our own, and we show the recent seq2seq style results of Liu et al. (2018), who use a somewhat larger model, at the bottom of Table 2.”
- PaperRobot: Incremental Draft Generation of Scientific Ideas (2019, background): “…et al., 2018; Xu et al., 2018; Madotto et al., 2018; Nie et al., 2018), biographies based on attributes (Lebret et al., 2016; Chisholm et al., 2017; Liu et al., 2018; Sha et al., 2018; Kaffee et al., 2018; Wang et al., 2018a; Wiseman et al., 2018), and image/video captions based on background…”
- Controlling hallucinations at word level in data-to-text generation (2021, unknown): “The use of Deep Learning based methods to solve DTG tasks has led to sudden improvements in state of the art performances [29, 70, 36, 49].”
- 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).”
- ESPRIT: Explaining Solutions to Physical Reasoning Tasks (2020, background): “, 2016), biographical texts from Wikipedia infoboxes (Lebret et al., 2016; Sha et al., 2018; Liu et al., 2018; Perez-Beltrachini and Lapata, 2018), descriptions of knowledge bases (ODonnell et al.”
- Explaining Patterns in Data with Language Models via Interpretable Autoprompting (2022, background): “The problem statement presented in this work closely resembles the widely studied problems of symbolic regression [49, 50], program synthesis [51, 52], text/table summarization [53, 54], and pattern discovery in data-mining [55].”
- Text Editing by Command (2020, methodology): “Following (Liu et al., 2018a) we use tf-idf scores to rerank. where N w ( G ) is the number of occurrences of w in G , N gw is the number of documents in G that contain w , and N g is the number of documents in G .”
- Towards a Decomposable Metric for Explainable Evaluation of Text Generation from AMR (2020, background): “The issues may become aggravated in settings where one maps from more abstract input to more concrete output, including, but not limited to AMR-to-text, Table-to-text (Liu et al., 2017; Parikh et al., 2020) or knowledge to text (Koncel-Kedziorski et al., 2019).”