Who leads the wikibio benchmark?

MBD currently leads wikibio with a score of 56.16 on Parent.

What is the state-of-the-art score on wikibio?

The state-of-the-art result on wikibio is 56.16 (Parent), achieved by MBD as of 2021.

How many models are tracked on wikibio?

Codesota tracks 9 models on wikibio across 3 metrics.

When was the wikibio leaderboard last updated?

The wikibio leaderboard on Codesota includes results through 2021, with the earliest tracked result from 2016.

Codesota · Benchmark · wikibioHome/Leaderboards/Vision & Documents/Document OCR/wikibio

Unknown

wikibio.

Name: wikibio Benchmark Results
Creator: Unknown
Published: 2016-01-01
License: https://creativecommons.org/licenses/by/4.0/

wikibio is a state-of-the-art machine learning benchmark indexed on Codesota. This page tracks published model results, top scores per metric, and the SOTA timeline for wikibio.

Paper ↗Leaderboard ↓

§ 01 · Leaderboard

Results by metric.

Found a wrong score or missing run?

Use row edits to send a sourced correction into moderation.

Add / edit result ↗Report issue ↗

Parent

Parent is the reported evaluation metric for wikibio. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Parentverifiedpapervendorcommunityunverified

Rank	Model	Trust	Score	Year	Links	Fix
01	MBD From paper: Controlling Hallucinations at Word Level in Data-to-Text Generation	verified	56.16	2021	Paper ↗Code ↗	Looks wrong?
02	SANA From paper: Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation (arXiv:2105.14778)	verified	55.42	2021	Source ↗	Looks wrong?
03	Bert-to-Bert From paper: Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation (arXiv:2105.14778)	verified	53.54	2021	Source ↗	Looks wrong?

Bleu

Bleu is the reported evaluation metric for wikibio. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Bleuverifiedpapervendorcommunityunverified

Rank	Model	Trust	Score	Year	Links	Fix
01	Accurate Content Copying From paper: Table to text generation with accurate content copying (Yang et al., Scientific Reports 2021)	verified	46.87	2021	Source ↗	Looks wrong?
02	SANA From paper: Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation (arXiv:2105.14778)	verified	45.78	2021	Source ↗	Looks wrong?
03	Bert-to-Bert From paper: Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation (arXiv:2105.14778)	verified	45.62	2021	Source ↗	Looks wrong?
04	FA+RL From paper: Table to text generation with accurate content copying (Yang et al., Scientific Reports 2021)	verified	45.47	2021	Source ↗	Looks wrong?
05	NCP+BTA From paper: Table to text generation with accurate content copying (Yang et al., Scientific Reports 2021)	verified	45.46	2021	Source ↗	Looks wrong?
06	Field-gating Seq2seq + dual attention From paper: Table-to-text Generation by Structure-aware Seq2seq Learning	verified	44.89	2017	Paper ↗Code ↗	Looks wrong?
07	Field-gating Seq2seq + dual attention + beam search From paper: Table-to-text Generation by Structure-aware Seq2seq Learning	verified	44.71	2017	Paper ↗Code ↗	Looks wrong?
08	MBD From paper: Controlling Hallucinations at Word Level in Data-to-Text Generation	verified	41.56	2021	Paper ↗Code ↗	Looks wrong?
09	Table NLM From paper: Neural Text Generation from Structured Data with Application to the Biography Domain	verified	34.7	2016	Paper ↗Code ↗	Looks wrong?

Rouge

Rouge is the reported evaluation metric for wikibio. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Rougeverifiedpapervendorcommunityunverified

Rank	Model	Trust	Score	Year	Links	Fix
01	Accurate Content Copying From paper: Table to text generation with accurate content copying (Yang et al., Scientific Reports 2021)	verified	42.28	2021	Source ↗	Looks wrong?
02	Field-gating Seq2seq + dual attention + beam search From paper: Table-to-text Generation by Structure-aware Seq2seq Learning	verified	41.65	2017	Paper ↗Code ↗	Looks wrong?
03	FA+RL From paper: Table to text generation with accurate content copying (Yang et al., Scientific Reports 2021)	verified	41.54	2021	Source ↗	Looks wrong?
04	Field-gating Seq2seq + dual attention From paper: Table-to-text Generation by Structure-aware Seq2seq Learning	verified	41.21	2017	Paper ↗Code ↗	Looks wrong?
05	NCP+BTA From paper: Table to text generation with accurate content copying (Yang et al., Scientific Reports 2021)	verified	40.31	2021	Source ↗	Looks wrong?
06	Table NLM From paper: Neural Text Generation from Structured Data with Application to the Biography Domain	verified	25.8	2016	Paper ↗Code ↗	Looks wrong?

§ 04 · Submit a result

Add to the leaderboard.

← Back to Document OCR