Order-Planning Neural Text Generation From Structured Data

By Lei Sha, Lili Mou, Tianyu Liu, Pascal Poupart, Sujian Li, Baobao Chang, Zhifang Sui. 2017

117 citations recorded by the source corpus.

Generating texts from structured data (e.g., a table) is important for various natural language processing tasks such as question answering and dialog systems. In recent studies, researchers use neural language models and encoder-decoder frameworks for table-to-text generation. However, these neural network-based approaches typically do not model the order of content during text generation. When a human writes a summary based on a given table, he or she would probably consider the content order before wording. In this paper, we propose an order-planning text generation model, where order information is explicitly captured by link-based attention. Then a self-adaptive gate combines the link-based attention with traditional content-based attention. We conducted experiments on the WikiBio dataset and achieve higher performance than previous methods in terms of BLEU, ROUGE, and NIST scores; we also performed ablation tests to analyze each component of our model.

Subfields: Artificial Intelligence, 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

In Natural Language Processing

In Natural Language Generation

Citations in the corpus

DART: Open-Domain Structured Data Record to Text Generation (2020, background): “…et al., 1994; 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…”
Evaluation of Text Generation: A Survey (2020, neutral): “, 2019b) and data-to-text generation (Reiter, 2007; Lebret et al., 2016a; Sha et al., 2017; Puduppully et al., 2018; Wang, 2019; Nan et al., 2021).”
Data-to-Text Generation with Content Selection and Planning (2018, methodology): “Most previous approaches generate from Wikipedia infoboxes focusing either on single sentences (Lebret et al. 2016; 2017; Sha et al. 2017; Liu et al. 2017) or short texts (Perez-Beltrachini and Lapata 2018).”
Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View (2021, background): “Among them, some work introduces differentiable planning modules (Sha et al. 2018; Laha et al. 2018; Puduppully, Dong, and Lapata 2018).”
ESPRIT: Explaining Solutions to Physical Reasoning Tasks (2020, background): “…forecasts (Liang et al., 2009; Konstas and Lapata, 2012; Mei et al., 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., 2000; Trisedya et al.,…”
Bootstrapping Generators from Noisy Data (2018, background): “Most previous work (Lebret et al., 2016; Chisholm et al., 2017; Sha et al., 2017; Liu et al., 2017) targets the generation of single sentence biographies from Wikipedia infoboxes, while Wiseman et al. (2017) generate game summary documents from a database of basketball games where the input is…”
PaperRobot: Incremental Draft Generation of Scientific Ideas (2019, background): “…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 entities and events…”
Controlling Text Edition by Changing Answers of Specific Questions (2021, background): “WIKIBIO was originally designed for table-to-text generation (Lebret et al., 2016; Sha et al., 2018; Liu et al., 2018), which generates a celebrity’s biography according to his/her basic information.”
Generating Live Soccer-Match Commentary from Play Data (2019, background): “Recent work on data-to-text generation includes product review generation (Dong et al. 2017) and biography generation (Lebret, Grangier, and Auli 2016; Liu et al. 2018; Hachey, Radford, and Chisholm 2017; Sha et al. 2018).”
Learning to Select, Track, and Generate for Data-to-Text (2019, background): “…al., 1998; Chen and Mooney, 2008; Taniguchi et al., 2019), weather forecast (Liang et al., 2009; Mei et al., 2016), biographical text from infobox in Wikipedia (Lebret et al., 2016; Sha et al., 2018; Liu et al., 2018) and market comments from stock prices (Murakami et al., 2017; Aoki et al., 2018).”
Describing a Knowledge Base (2018, methodology): “Compared with the Wikibio dataset used in previous studies (Lebret et al., 2016; Sha et al., 2018; Liu et al., 2018), which contains one sentence only as the ground-truth description, our dataset contains multiple sentences to cover as many facts as possible in the input structured KB.”
Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation (2021, background): “Recent works that adopt end-to-end neural networks have achieve great success on this task (Mei et al., 2016; Lebret et al., 2016; Wiseman et al., 2017; Sha et al., 2018; Nema et al., 2018; Liu et al., 2018, 2019a).”
Table-to-text Generation by Structure-aware Seq2seq Learning (2017, methodology): “Recent work combines content selection and surface realization in a uniﬁed framework (Ratnaparkhi 2002; Konstas and Lapata 2012; 2013; Sha et al. 2017) Our model borrowed the idea of representing a structured table by its ﬁeld and content information from (Le-bret, Grangier, and Auli 2016).”
A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation (2021, background): “attention manipulation (Kiddon et al., 2016; Sha et al., 2018; Hua and Wang, 2019; Tian et al., 2019; Liu et al., 2019) or optimal transport (Wang et al.”