Papers › XF2T: Cross-lingual Fact-to-Text Generation for Low-Resource Languages

XF2T: Cross-lingual Fact-to-Text Generation for Low-Resource Languages

22 Sep 2022arXiv:2209.11252archive 2025-07-28

Shivprasad Sagare, Tushar Abhishek, Bhavyajeet Singh, Anubhav Sharma, Manish Gupta, Vasudeva Varma

Multiple business scenarios require an automated generation of descriptive human-readable text from structured input data. Hence, fact-to-text generation systems have been developed for various downstream tasks like generating soccer reports, weather and financial reports, medical reports, person biographies, etc. Unfortunately, previous work on fact-to-text (F2T) generation has focused primarily on English mainly due to the high availability of relevant datasets. Only recently, the problem of cross-lingual fact-to-text (XF2T) was proposed for generation across multiple languages alongwith a dataset, XALIGN for eight languages. However, there has been no rigorous work on the actual XF2T generation problem. We extend XALIGN dataset with annotated data for four more languages: Punjabi, Malayalam, Assamese and Oriya. We conduct an extensive study using popular Transformer-based text generation models on our extended multi-lingual dataset, which we call XALIGNV2. Further, we investigate the performance of different text generation strategies: multiple variations of pretraining, fact-aware embeddings and structure-aware input encoding. Our extensive experiments show that a multi-lingual mT5 model which uses fact-aware embeddings with structure-aware input encoding leads to best results on average across the twelve languages. We make our code, dataset and model publicly available, and hope that this will help advance further research in this critical area.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Data-to-Text GenerationDescriptiveQuestion AnsweringText Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Data-to-Text Generation XAlign Fact-aware embedding with mT5 BLEU4 29.27 #1 of 6 Archive leaderboard report
Data-to-Text Generation XAlign Fact-aware embedding with mT5 METEOR 53.64 #1 of 6 Archive leaderboard report
Data-to-Text Generation XAlign Bi-lingual mT5 BLEU4 25.88 #2 of 6 Archive leaderboard report
Data-to-Text Generation XAlign Bi-lingual mT5 METEOR 50.91 #2 of 6 Archive leaderboard report
Data-to-Text Generation XAlign Translate-Output mT5 BLEU4 18.91 #5 of 6 Archive leaderboard report
Data-to-Text Generation XAlign Translate-Output mT5 METEOR 42.83 #5 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AdafactorAttentionAttention DropoutBPEDense ConnectionsDropoutGated Linear UnitInverse Square Root ScheduleLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSentencePieceSoftmaxT5mT5

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections