Data-to-text Generation with Entity Modeling

By Ratish Puduppully, Li Dong, Mirella Lapata. 2019

130 citations recorded by the source corpus.

Recent approaches to data-to-text generation have shown great promise thanks to the use of large-scale datasets and the application of neural network architectures which are trained end-to-end. These models rely on representation learning to select content appropriately, structure it coherently, and verbalize it grammatically, treating entities as nothing more than vocabulary tokens. In this work we propose an entity-centric neural architecture for data-to-text generation. Our model creates entity-specific representations which are dynamically updated. Text is generated conditioned on the data input and entity memory representations using hierarchical attention at each time step. We present experiments on the RotoWire benchmark and a (five times larger) new dataset on the baseball domain which we create. Our results show that the proposed model outperforms competitive baselines in automatic and human evaluation.

Subfields: 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 Natural Language Processing

In Natural Language Generation

Citations in the corpus

DART: Open-Domain Structured Data Record to Text Generation (2020, background): “…domains (e.g., WebNLG (Gar-dent et al., 2017b) on 15 categories from DB-Pedia, WikiBio on biographies, E2E on restau-rants, RotoWire on basketball, MLB on base-ball (Puduppully et al., 2019), WeatherGov (Liang et al., 2009) on weather forecasts, RoboCup (Chen and Mooney, 2008) on soccer reports).”
ESPRIT: Explaining Solutions to Physical Reasoning Tasks (2020, methodology): “ion (Bahdanau et al.,2015;Luong et al., 2015) and copy mechanisms (Gu et al.,2016; Gulcehre et al.,2016) have shown promising results on table-to-text tasks (Wiseman et al., 2017;Gehrmann et al.,2018;Puduppully et al., 2019a,b;Iso et al.,2019;Castro Ferreira et al., 2019;Zhao et al.,2020;Chen et al.”
Data-to-text Generation with Macro Planning (2021, methodology): “We discuss our model considering mainly an example from the MLB dataset (Puduppully et al., 2019b) but also touch on how the approach can be straightforwardly adapted to R OTO W IRE (Wiseman et al., 2017).”
Towards Table-to-Text Generation with Numerical Reasoning (2021, methodology): “Following earlier work (Puduppully et al., 2019), we also evaluated text ﬂuency in terms of gram-maticality, coherence, and conciseness by using best-worst scaling (BWS) (Louviere and Wood-worth, 1991; Louviere et al., 2015).”
Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation (2019, background): “…rewards (Paulus et al., 2018; Pasunuru & Bansal, 2018), semi-Markov models to learn neural templates (Wiseman et al., 2018), data augmentation (Ma et al., 2019; Kedzie & McKeown, 2019), content planning (Puduppully et al., 2019a), and constrained vocabulary decoding (Wu et al., 2017).”
Controlling hallucinations at word level in data-to-text generation (2021, unknown): “Based on the now-standard encoder-decoder architecture, with attention and copy mechanisms [1, 59], neural methods for DTG are able to produce ﬂuent text conditioned on structured data in a number of domains [29, 70, 50], without relying on heavy manual work from ﬁeld experts.”
Revisiting Challenges in Data-to-Text Generation with Fact Grounding (2020, background): “Moreover, Qin et al. (2018) proposed to automatically align the game summary with the record types in the input table on the phrase level.”
Learning to Select, Track, and Generate for Data-to-Text (2019, methodology): “While the models by Wiseman et al. (2017) and Puduppully et al. (2019) respec- 8In the NBA, a player who accumulates a double-digit score in one of five categories (points, rebounds, assists, steals, and blocked shots) in a game, is regarded as a good player.”
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code (2022, background): “, 2021)), and a class of data-to-text datasets with the communicative goal to generate game summaries from large sports statistic tables (e.g., Hayashi et al., 2019; Thomson et al., 2020; Puduppully et al., 2019a).”
Plan-then-Generate: Controlled Data-to-Text Generation via Planning (2021, methodology): “We compare our model with the latest models on ToTTo dataset, including NCP (Puduppully et al., 2019a), Pointer-Generator (See et al., 2017), BERT-to-BERT (Rothe et al., 2020) and T5-3B (Kale and Rastogi, 2020).”
Controlled Hallucinations: Learning to Generate Faithfully from Noisy Data (2020, unknown): “…network-based (DNN) models have demonstrated remarkable performance on a multitude of text-to-text (Bahdanau et al., 2015; Rothe et al., 2019; Narayan et al., 2018; Rush et al., 2015, inter alia) as well as data-to-text generation tasks (Wiseman et al., 2017; Puduppully et al., 2019, inter alia).”