A Hierarchical Model for Data-to-Text Generation

Rebuffel, Clément; Soulier, Laure; Scoutheeten, Geoffrey; Gallinari, Patrick

doi:10.1007/978-3-030-45439-5_5

Cited by 47 publications

(53 citation statements)

References 32 publications

(78 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The RCT model 33 considers the row, column, and time dimension information in the input table, and then combines the three-dimensional representations into a dense vector through the table cell fusion gate. The Hierarch-k model 36 employ a novel two-level Transformer encoder to hierarchically capture the structure of the data. Two variants of hierarchical attention mechanism are used to get context as the input of decoder.…”

Section: Resultsmentioning

confidence: 99%

Table-to-Text Generation with Accurate Content Copying

Yang

Cao

Wen

et al. 2021

Preprint

View full text Add to dashboard Cite

Table-to-text generation is an important task in natural language generation that aims to generate smooth, informative text based on structured data. In this paper, we propose a novel transformer-based autoregressive model that incorporates table content copying and language model based generation. At first, we propose a word transformation method to process a target text. By using target text containing fields and position information, we can help the model learn the relationship between target text and table and gain the position of where to copy. We then propose two auxiliary learning goals: table-text constraint loss and copy loss. Table-text constraint loss is introduced to effectively model table inputs, whereas copy loss is exploited to precisely copy word fragments from a table. In addition, we change the maximization-based text search strategy to reduce the probability of problems such as sentence repetition and inconsistency. On the WIKIBIO dataset, our model improves its BLUE scores from 45.47 to 46.87 and ROUGE scores from 41.54 to 42.28, outperforming state-of-the-art baseline models on automatic evaluation metrics. On the ROTOWIRE test set, compared with the best baseline model, our model gets 4.29% higher on CO metric, and 1.93 points higher on BLEU.

show abstract

Section: Resultsmentioning

confidence: 99%

Table-to-Text Generation with Accurate Content Copying

Yang

Cao

Wen

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Another work presented by Kanerva, J et al [27] aims to generate news articles about Finnish sports news using structured templates/tables of data and pointer-generation network. In the work of Rebuffel, C et al [28], a hierarchical encoder-decoder model is proposed for transcribing structured data into natural language descriptions. In other papers, like the one presented by Mihir Kale [29], they use pretrained models, such as T5 [25] and BART [24], for data-to-text generation, achieving state-of-the-art results in various datasets.…”

Section: Related Workmentioning

confidence: 99%

An AI-Enabled Framework for Real-Time Generation of News Articles Based on Big EO Data for Disaster Reporting

et al. 2021

View full text Add to dashboard Cite

In the field of journalism, the collection and processing of information from different heterogeneous sources are difficult and time-consuming processes. In the context of the theory of journalism 3.0, where multimedia data can be extracted from different sources on the web, the possibility of creating a tool for the exploitation of Earth observation (EO) data, especially images by professionals belonging to the field of journalism, is explored. With the production of massive volumes of EO image data, the problem of their exploitation and dissemination to the public, specifically, by professionals in the media industry, arises. In particular, the exploitation of satellite image data from existing tools is difficult for professionals who are not familiar with image processing. In this scope, this article presents a new innovative platform that automates some of the journalistic practices. This platform includes several mechanisms allowing users to early detect and receive information about breaking news in real-time, retrieve EO Sentinel-2 images upon request for a certain event, and automatically generate a personalized article according to the writing style of the author. Through this platform, the journalists or editors can also make any modifications to the generated article before publishing. This platform is an added-value tool not only for journalists and the media industry but also for freelancers and article writers who use information extracted from EO data in their articles.

show abstract

“…They also proposed automatic evaluation metrics for measuring the informativeness of generated summaries. Their dataset and metrics have also been used by other researchers (Nie, Wang, Yao, Pan, and Lin 2018;Li and Wan 2018;Puduppully et al 2019a;Puduppully, Dong, and Lapata 2019b;Rebuffel, Soulier, Scoutheeten, and Gallinari 2020). Puduppully et al (2019a) proposed a two-stage method that first predicts the sequence of data records to be mentioned and then generates a summary conditioned on the predicted sequences.…”

Section: Data-to-text Generationmentioning

confidence: 99%

“…• Hierarchical: the model consists of the encoder with hierarchical attention proposed by Rebuffel et al (2020) • NCP: the model first predicts the sequence of data records and then generates a summary conditioned on the predicted sequences proposed by Puduppully et al (2019a).…”

Section: Models To Be Comparedmentioning

confidence: 99%

Learning to Select, Track, and Generate for Data-to-Text

Iso

Uehara²,

Ishigaki

et al. 2020

Journal of Natural Language Processing

View full text Add to dashboard Cite

We propose a data-to-text generation model with two modules, one for tracking and the other for text generation. Our tracking module selects and keeps track of salient information and remembers which record has been mentioned. Our generation module generates a summary conditioned on the state of tracking module. In addition, we also explore the effectiveness of the writer information for generation. Experimental results show that our model outperforms existing models in all evaluation metrics even without writer information. Incorporating writer information further improves the performance, contributing to content planning and surface realization.

show abstract

A Hierarchical Model for Data-to-Text Generation

Cited by 47 publications

References 32 publications

Table-to-Text Generation with Accurate Content Copying

Table-to-Text Generation with Accurate Content Copying

An AI-Enabled Framework for Real-Time Generation of News Articles Based on Big EO Data for Disaster Reporting

Learning to Select, Track, and Generate for Data-to-Text

Contact Info

Product

Resources

About