RDF-to-Text Generation with Graph-augmented Structural Neural Encoders

Gao, Hanning; Wu, Lingfei; Hu, Po; Xu, Fangli

doi:10.24963/ijcai.2020/419

Cited by 13 publications

(9 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The resulting performances confirmed the benefit of the graph-based encoder. Following this conclusion, several papers proposed graph-based encoder as a solution (Gao et al, 2020;Zhao et al, 2020;Moussallem et al, 2020).…”

Section: Related Workmentioning

confidence: 91%

See 1 more Smart Citation

Denoising Pre-Training and Data Augmentation Strategies for Enhanced RDF Verbalization with Transformers

Montella¹,

Fabre²,

Urvoy³

et al. 2020

Preprint

View full text Add to dashboard Cite

The task of verbalization of RDF triples has known a growth in popularity due to the rising ubiquity of Knowledge Bases (KBs). The formalism of RDF triples is a simple and efficient way to store facts at a large scale. However, its abstract representation makes it difficult for humans to interpret. For this purpose, the WebNLG challenge aims at promoting automated RDF-to-text generation. We propose to leverage pre-trainings from augmented data with the Transformer model using a data augmentation strategy. Our experiment results show a minimum relative increases of 3.73%, 126.05% and 88.16% in BLEU score for seen categories, unseen entities and unseen categories respectively over the standard training.

show abstract

Section: Related Workmentioning

confidence: 91%

“…IE and NLU, research directions. For instance, Iso et al (2020) and Gao et al (2020) have obtained state-of-the-art performances on the WebNLG RDF-to-text task. On the other hand, Guo et al (2020) considered both NLG and IE objectives within the same learning framework via cycle training.…”

Section: Introductionmentioning

confidence: 99%

Denoising Pre-Training and Data Augmentation Strategies for Enhanced RDF Verbalization with Transformers

Montella¹,

Fabre²,

Urvoy³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Data-to-text Generation: Data-to-text generation transforms structured data into descriptive texts (Siddharthan, 2001;Gatt and Krahmer, 2018). Recent works have brought great promising performance to several data-to-text generation tasks, e.g., Puduppully et al (2019a,b); Gong et al (2019a); Wiseman et al (2017) focus on report generation; Chisholm et al (2017); Lebret et al (2016) target at biography generation; ; Gao et al (2020) generate texts from a set of RDF triples considering structural information. Previous works have also designed content selection and text planning models to determine what to say and how to say (Puduppully et al, 2019a;Perez-Beltrachini and Lapata, 2018).…”

Section: Related Workmentioning

confidence: 99%

DISK: Domain-constrained Instance Sketch for Math Word Problem Generation

Cao¹,

Zeng²,

Xu³

et al. 2022

Preprint

View full text Add to dashboard Cite

A math word problem (MWP) is a coherent narrative which reflects the underlying logic of math equations. Successful MWP generation can automate the writing of mathematics questions. Previous methods mainly generate MWP text based on inflexible pre-defined templates. In this paper, we propose a neural model for generating MWP text from math equations. Firstly, we incorporate a matching model conditioned on the domain knowledge to retrieve a MWP instance which is most consistent with the ground-truth, where the domain is a latent variable extracted with a domain summarizer. Secondly, by constructing a Quantity Cell Graph (QCG) from the retrieved MWP instance and reasoning over it, we improve the model's comprehension of real-world scenarios and derive a domainconstrained instance sketch to guide the generation. Besides, the QCG also interacts with the equation encoder to enhance the alignment between math tokens (e.g., quantities and variables) and MWP text. Experiments and empirical analysis on educational MWP set show that our model achieves impressive performance in both automatic evaluation metrics and human evaluation metrics. Equations: x = 6 * y ; (x + y) * 3= 147 Problem: Jane travels 6 times faster than mike. Traveling in opposite directions they are 147 miles apart after 3 hrs. Find their rates of travel. Equations: (1 -1/3 -9/20) * x = 245 Problem: At a local high school, 3/8 of the students are freshman. 1/4 are juniors. And 245 are seniors. Find the total number of students.

show abstract

“…The prevailing sequence-to-sequence (seq2seq) architectures typically address this issue via reranking (Wen et al, 2015a;Juraska et al, 2018) or some sophisticated training techniques (Nie et al, 2019;Kedzie and McKeown, 2019;Qader et al, 2019). For applications where structured inputs are present, neural graph encoders (Marcheggiani and Perez-Beltrachini, 2018;Rao et al, 2019;Gao et al, 2020) or decoding of explicit graph references (Logan et al, 2019) are applied for higher accuracy. Recently, large-scale pretraining has achieved SoTA results on WebNLG by fine-tuning T5 (Kale and Rastogi, 2020b).…”

Section: Related Workmentioning

confidence: 99%

AggGen: Ordering and Aggregating while Generating

Xu¹,

Dusek²,

Rieser³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

We present AGGGEN (pronounced 'again'), a data-to-text model which re-introduces two explicit sentence planning stages into neural datato-text systems: input ordering and input aggregation. In contrast to previous work using sentence planning, our model is still endto-end: AGGGEN performs sentence planning at the same time as generating text by learning latent alignments (via semantic facts) between input representation and target text. Experiments on the WebNLG and E2E challenge data show that by using fact-based alignments our approach is more interpretable, expressive, robust to noise, and easier to control, while retaining the advantages of end-to-end systems in terms of fluency. Our code is available at https://github.com/XinnuoXu/ AggGen.

show abstract

RDF-to-Text Generation with Graph-augmented Structural Neural Encoders

Cited by 13 publications

References 55 publications

Denoising Pre-Training and Data Augmentation Strategies for Enhanced RDF Verbalization with Transformers

Denoising Pre-Training and Data Augmentation Strategies for Enhanced RDF Verbalization with Transformers

DISK: Domain-constrained Instance Sketch for Math Word Problem Generation

AggGen: Ordering and Aggregating while Generating

Contact Info

Product

Resources

About