Generating Text from Anonymised Structures

Colin, Emilie; Gardent, Claire

doi:10.18653/v1/w19-8614

“…With recent advances in neural networks, researchers have built different neural models based on various strategies, e.g. latentvariables (Wiseman et al, 2018;Ye et al, 2020), structure awareness (Liu et al, 2018;Colin and Gardent, 2019), copy mechanism (Gehrmann et al, 2018;Puduppully et al, 2019a,b), and pre-trained language models (PLMs) (Chen et al, 2020a;Kale, 2020;Ribeiro et al, 2020) 2020) adapted the pre-trained GPT-2 model with different architectural designs, e.g. switch policy (Chen et al, 2020b) and content matching (Gong et al, 2020), to address the few-shot table-to-text generation problem.…”

Section: Discussionmentioning

confidence: 99%

Few-Shot Table-to-Text Generation with Prototype Memory

Su¹,

Meng²,

Baker³

et al. 2021

Findings of the Association for Computational Linguistics: EMNLP 2021

View full text Add to dashboard Cite

Neural table-to-text generation models have achieved remarkable progress on an array of tasks. However, due to the data-hungry nature of neural models, their performances strongly rely on large-scale training examples, limiting their applicability in real-world applications.To address this, we propose a new framework: Prototype-to-Generate (P2G), for table-to-text generation under the few-shot scenario. The proposed framework utilizes the retrieved prototypes, which are jointly selected by an IR system and a novel prototype selector to help the model bridging the structural gap between tables and texts. Experimental results on three benchmark datasets with three state-of-the-art models demonstrate that the proposed framework significantly improves the model performance across various evaluation metrics.

show abstract

“…End-to-End Models. 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 Su et al, 2021b). Gehrmann et al (2018), Puduppully et al (2019a,b), and Chen et al (2020b) adopted copy mechanism for content selection to improve the information coverage of the outputs.…”

Section: Related Workmentioning

confidence: 99%

Plan-then-Generate: Controlled Data-to-Text Generation via Planning

Su¹,

Vandyke²,

Wang³

et al. 2021

Preprint

0

View full text Add to dashboard Cite

Recent developments in neural networks have led to the advance in data-to-text generation. However, the lack of ability of neural models to control the structure of generated output can be limiting in certain real-world applications. In this study, we propose a novel Plan-then-Generate (PlanGen) framework to improve the controllability of neural data-totext models. Extensive experiments and analyses are conducted on two benchmark datasets, ToTTo and WebNLG. The results show that our model is able to control both the intrasentence and inter-sentence structure of the generated output. Furthermore, empirical comparisons against previous state-of-the-art methods show that our model improves the generation quality as well as the output diversity as judged by human and automatic evaluations.

show abstract

“…With recent advances in neural networks, researchers have built different neural models based on various strategies, e.g. latentvariables (Wiseman et al, 2018;Ye et al, 2020), structure awareness (Liu et al, 2018;Colin and Gardent, 2019), copy mechanism (Gehrmann et al, 2018;Puduppully et al, 2019a,b), and pre-trained language models (PLMs) (Chen et al, 2020a;Kale, 2020;Ribeiro et al, 2020). More recently, to alleviate the data-hungry nature of neural models, Ma et al (2019) 2020) applied a retrieval model to assist the generation of paraphrased sentence.…”

Section: A Related Workmentioning

confidence: 99%

Few-Shot Table-to-Text Generation with Prototype Memory

Su¹,

Meng²,

Baker³

et al. 2021

Preprint

4

0

View full text Add to dashboard Cite

Neural table-to-text generation models have achieved remarkable progress on an array of tasks. However, due to the data-hungry nature of neural models, their performances strongly rely on large-scale training examples, limiting their applicability in real-world applications.To address this, we propose a new framework: Prototype-to-Generate (P2G), for table-to-text generation under the few-shot scenario. The proposed framework utilizes the retrieved prototypes, which are jointly selected by an IR system and a novel prototype selector to help the model bridging the structural gap between tables and texts. Experimental results on three benchmark datasets with three state-of-the-art models demonstrate that the proposed framework significantly improves the model performance across various evaluation metrics.

show abstract

Generating Text from Anonymised Structures

Cited by 8 publications

References 20 publications

Few-Shot Table-to-Text Generation with Prototype Memory

Few-Shot Table-to-Text Generation with Prototype Memory

Plan-then-Generate: Controlled Data-to-Text Generation via Planning

Few-Shot Table-to-Text Generation with Prototype Memory

Contact Info

Product

Resources

About