Data-to-Text Generation
105 papers with code • 24 benchmarks • 22 datasets
A classic problem in natural-language generation (NLG) involves taking structured data, such as a table, as input, and producing text that adequately and fluently describes this data as output. Unlike machine translation, which aims for complete transduction of the sentence to be translated, this form of NLG is usually taken to require addressing (at least) two separate challenges: what to say, the selection of an appropriate subset of the input data to discuss, and how to say it, the surface realization of a generation.
( Image credit: Data-to-Text Generation with Content Selection and Planning )
Benchmarks
These leaderboards are used to track progress in Data-to-Text Generation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Data-to-Text Generation models and implementations
MultiWOZ
WebNLG
E2E
RotoWire
ToTTo
RoboCup
ViGGO
Chart2Text
Most implemented papers
Automated learning of templates for data-to-text generation: comparing rule-based, statistical and neural methods
The current study investigated novel techniques and methods for trainable approaches to data-to-text generation.
E2E NLG Challenge: Neural Models vs. Templates
UKPLab/e2e-nlg-challenge-2017
•
•
WS 2018
E2E NLG Challenge is a shared task on generating restaurant descriptions from sets of key-value pairs.
Data-to-Text Generation with Style Imitation
ha-lins/DTG-SI
•
•
Findings of the Association for Computational Linguistics 2020
That is, the model learns to imitate the writing style of any given exemplar sentence, with automatic adaptions to faithfully describe the content record.
Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation
We propose to split the generation process into a symbolic text-planning stage that is faithful to the input, followed by a neural generation stage that focuses only on realization.
Copy mechanism and tailored training for character-based data-to-text generation
marco-roberti/char-data-to-text-gen
•
•
In the last few years, many different methods have been focusing on using deep recurrent neural networks for natural language generation.
Creating a Corpus for Russian Data-to-Text Generation Using Neural Machine Translation and Post-Editing
shimorina/bsnlp-2019
•
•
WS 2019
In this paper, we propose an approach for semi-automatically creating a data-to-text (D2T) corpus for Russian that can be used to learn a D2T natural language generation model.
Neural data-to-text generation: A comparison between pipeline and end-to-end architectures
In contrast, recent neural models for data-to-text generation have been proposed as end-to-end approaches, where the non-linguistic input is rendered in natural language with much less explicit intermediate representations in-between.
Enhancing AMR-to-Text Generation with Dual Graph Representations
UKPLab/emnlp2019-dualgraph
•
•
IJCNLP 2019
Generating text from graph-based data, such as Abstract Meaning Representation (AMR), is a challenging task due to the inherent difficulty in how to properly encode the structure of a graph with labeled edges.
Improving Quality and Efficiency in Plan-based Neural Data-to-Text Generation
We follow the step-by-step approach to neural data-to-text generation we proposed in Moryossef et al (2019), in which the generation process is divided into a text-planning stage followed by a plan-realization stage.
Template-free Data-to-Text Generation of Finnish Sports News
News articles such as sports game reports are often thought to closely follow the underlying game statistics, but in practice they contain a notable amount of background knowledge, interpretation, insight into the game, and quotes that are not present in the official statistics.
