TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Data-to-Text Generation	ToTTo	BERT-to-BERT	BLEU	44	# 3
Data-to-Text Generation	ToTTo	BERT-to-BERT	PARENT	52.6	# 3
Data-to-Text Generation	ToTTo	NCP+CC (Puduppully et al 2019)	BLEU	19.2	# 5
Data-to-Text Generation	ToTTo	NCP+CC (Puduppully et al 2019)	PARENT	29.2	# 5
Data-to-Text Generation	ToTTo	Pointer Generator	BLEU	41.6	# 4
Data-to-Text Generation	ToTTo	Pointer Generator	PARENT	51.6	# 4

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/totto-a-controlled-table-to-text-generation/data-to-text-generation-on-totto)](https://paperswithcode.com/sota/data-to-text-generation-on-totto?p=totto-a-controlled-table-to-text-generation)`

ToTTo: A Controlled Table-To-Text Generation Dataset

EMNLP 2020 · Ankur P. Parikh, Xuezhi Wang, Sebastian Gehrmann, Manaal Faruqui, Bhuwan Dhingra, Diyi Yang, Dipanjan Das ·

We present ToTTo, an open-domain English table-to-text dataset with over 120,000 training examples that proposes a controlled generation task: given a Wikipedia table and a set of highlighted table cells, produce a one-sentence description. To obtain generated targets that are natural but also faithful to the source table, we introduce a dataset construction process where annotators directly revise existing candidate sentences from Wikipedia. We present systematic analyses of our dataset and annotation process as well as results achieved by several state-of-the-art baselines. While usually fluent, existing methods often hallucinate phrases that are not supported by the table, suggesting that this dataset can serve as a useful research benchmark for high-precision conditional text generation.

PDF Abstract EMNLP 2020 PDF EMNLP 2020 Abstract

Code

Add Remove Mark official

google-research-datasets/ToTTo official

419

Tasks

Add Remove

Conditional Text Generation

Data-to-Text Generation

Sentence

Table-to-Text Generation

Text Generation

Datasets

Introduced in the Paper:

ToTTo

Used in the Paper:

WikiBio

RotoWire

Results from the Paper

Edit

Ranked #3 on Data-to-Text Generation on ToTTo

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
Data-to-Text Generation	ToTTo	BERT-to-BERT	BLEU	44	# 3	Compare
Data-to-Text Generation	ToTTo	BERT-to-BERT	PARENT	52.6	# 3	Compare
Data-to-Text Generation	ToTTo	NCP+CC (Puduppully et al 2019)	BLEU	19.2	# 5	Compare
Data-to-Text Generation	ToTTo	NCP+CC (Puduppully et al 2019)	PARENT	29.2	# 5	Compare
Data-to-Text Generation	ToTTo	Pointer Generator	BLEU	41.6	# 4	Compare
Data-to-Text Generation	ToTTo	Pointer Generator	PARENT	51.6	# 4	Compare

Methods

Add Remove

No methods listed for this paper. Add relevant methods here

Edit Social Preview

ToTTo: A Controlled Table-To-Text Generation Dataset

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods

Add Remove