Data-to-Text Generation with Content Selection and Planning

By Ratish Puduppully, Li Dong, Mirella Lapata. 2018

336 citations recorded by the source corpus.

Recent advances in data-to-text generation have led to the use of large-scale datasets and neural network models which are trained end-to-end, without explicitly modeling what to say and in what order. In this work, we present a neural network architecture which incorporates content selection and planning without sacrificing end-to-end training. We decompose the generation task into two stages. Given a corpus of data records (paired with descriptive documents), we first generate a content plan highlighting which information should be mentioned and in which order and then generate the document while taking the content plan into account. Automatic and human-based evaluation experiments show that our model1 outperforms strong baselines improving the state-of-the-art on the recently released RotoWIRE dataset.

Subfields: Artificial Intelligence, Natural Language Processing

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

Citations in the corpus

Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text (2022, background): “While separate reasoning steps are starting to be incorporated into current NLG approaches (e.g., Puduppully et al., 2019; 17See Belinkov and Glass (2019) for a recent survey of analysis methods.”
Survey of Hallucination in Natural Language Generation (2022, methodology): “Planning is a common method to control and restrict what the model generates by informing the content and its order [147].”
DART: Open-Domain Structured Data Record to Text Generation (2020, neutral): “…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 al., 2019b;…”
ToTTo: A Controlled Table-To-Text Generation Dataset (2020, methodology): “• Puduppully et al. (2019): A Seq2Seq model with an explicit content selection and planning mechanism designed for data-to-text.”
Text-to-Text Pre-Training for Data-to-Text Tasks (2020, methodology): “• Content Planner (Puduppully et al., 2019) - A seq2seq model with separate content planning and generation stages.”
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).”
Detecting Hallucinated Content in Conditional Neural Sequence Generation (2020, methodology): “Neural sequence models for tasks such as data-to-text generation (Puduppully et al., 2019), machine translation (MT; Vaswani et al. (2017); Wu et al. (2016)) and text summarization (Rothe et al., 2020) can often generate ﬂuent text that is sometimes preferred to human-written content (L¨aubli et…”
Few-Shot NLG with Pre-Trained Language Model (2019, methodology): “…been used, including the end-to-end methods that jointly model context selection and surface realization (Liu et al. 2018; Wiseman, Shieber, and Rush 2018; Puduppully, Dong, and Lapata 2018), and the methods using neural network to tackle realization component (Moryossef, Goldberg, and Dagan 2019).”
Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue (2019, background): “Puduppully et al. (2018) builds a modular end-to-end neural architecture that performs content planning in addition to realization, although they focus on generating text from structured tables, and don’t consider discourse structure.”
Findings of the Fourth Workshop on Neural Generation and Translation (2020, methodology): “We use a two-stage model from (Puduppully et al., 2019) for NLG tracks.”
Text Generation from Knowledge Graphs with Graph Transformers (2019, background): “Data-totext generation models (Konstas and Lapata, 2013; Lebret et al., 2016; Wiseman et al., 2017; Puduppully et al., 2019) condition text generation on table-structured inputs.”
A Gold Standard Methodology for Evaluating Accuracy in Data-To-Text Systems (2020, methodology): “With these caveats in mind, Table 2 suggests that Puduppully et al. (2019) and Wiseman et al. (2017) have similar profiles for accuracy errors.”
A Tree-to-Sequence Model for Neural NLG in Task-Oriented Dialog (2019, background): “Puduppully et al. (2019) add a content planning step where a set of input database records are mapped to an ordered list of selected records; however, their approach does not employ hierarchical content plans as in our approach.”
Logical Natural Language Generation from Open-Domain Tables (2020, methodology): “As such, existing methods based on surface-level copying (See et al., 2017; Gu et al., 2016; Puduppully et al., 2019a) becomes insufﬁcient, so are the existing ﬁdelity evaluation based on the surface-level information extraction (Wiseman et al., 2017; Rohrbach et al., 2018; Dhingra et al., 2019),…”
AggGen: Ordering and Aggregating while Generating (2021, background): “Puduppully et al. (2019) include a jointly trained content selection and ordering module that is applied before the main text generation step.”
Data-to-text Generation with Entity Modeling (2019, methodology): “Various attempts have also been made to improve these models, e.g., by adding content selection (Perez-Beltrachini and Lapata, 2018) and content planning (Puduppully et al., 2019) mechanisms.”
Controlling hallucinations at word level in data-to-text generation (2021, positive): “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].”
Bridging the Structural Gap Between Encoding and Decoding for Data-To-Text Generation (2020, background): “This suggests a need for an intermediate “planning” stage (Reiter and Dale, 2000; Puduppully et al., 2019) to help with organizing the output.”
Progressive Generation of Long Text with Pretrained Language Models (2021, methodology): “Recent neural approaches have also adopted similar planning-then-generation strategies for data-to-text (Moryossef et al., 2019; Puduppully et al., 2019), story-telling (Fan et al., 2019; Yao et al., 2019; Xu et al., 2020), machine translation (Ford et al., 2018), and others (Hua and Wang, 2019;…”