TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Data-to-Text Generation	XAlign	mT5	BLEU4	25	# 3
Data-to-Text Generation	XAlign	Graph Attention Network Encoder +Transformer Decoder	BLEU4	18.3	# 6
Data-to-Text Generation	XAlign	Vanilla Transformer	BLEU4	19.9	# 4

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/xalign-cross-lingual-fact-to-text-alignment/data-to-text-generation-on-xalign)](https://paperswithcode.com/sota/data-to-text-generation-on-xalign?p=xalign-cross-lingual-fact-to-text-alignment)`

XAlign: Cross-lingual Fact-to-Text Alignment and Generation for Low-Resource Languages

1 Feb 2022 · Tushar Abhishek, Shivprasad Sagare, Bhavyajeet Singh, Anubhav Sharma, Manish Gupta, Vasudeva Varma ·

Multiple critical scenarios (like Wikipedia text generation given English Infoboxes) need automated generation of descriptive text in low resource (LR) languages from English fact triples. Previous work has focused on English fact-to-text (F2T) generation. To the best of our knowledge, there has been no previous attempt on cross-lingual alignment or generation for LR languages. Building an effective cross-lingual F2T (XF2T) system requires alignment between English structured facts and LR sentences. We propose two unsupervised methods for cross-lingual alignment. We contribute XALIGN, an XF2T dataset with 0.45M pairs across 8 languages, of which 5402 pairs have been manually annotated. We also train strong baseline XF2T generation models on the XAlign dataset.

PDF Abstract

Code

Add Remove Mark official

tushar117/xalign official

Tasks

Add Remove

Data-to-Text Generation

Descriptive

Text Generation

Datasets

Introduced in the Paper:

XAlign

Used in the Paper:

T-REx

WikiBio KELM

WikiTableT GenWiki

Results from the Paper

Edit

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

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
Data-to-Text Generation	XAlign	mT5	BLEU4	25	# 3	Compare
Data-to-Text Generation	XAlign	Graph Attention Network Encoder +Transformer Decoder	BLEU4	18.3	# 6	Compare
Data-to-Text Generation	XAlign	Vanilla Transformer	BLEU4	19.9	# 4	Compare

Methods

Add Remove

No methods listed for this paper. Add relevant methods here

Edit Social Preview

XAlign: Cross-lingual Fact-to-Text Alignment and Generation for Low-Resource Languages

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