TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/XAlign: Cross-lingual Fact-to-Text Alignment and Generatio...

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

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

2022-02-01Data-to-Text GenerationText GenerationDescriptive
PaperPDFCode(official)

Abstract

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.

Results

TaskDatasetMetricValueModel
Text GenerationXAlignBLEU425mT5
Text GenerationXAlignBLEU419.9Vanilla Transformer
Text GenerationXAlignBLEU418.3Graph Attention Network Encoder +Transformer Decoder
Data-to-Text GenerationXAlignBLEU425mT5
Data-to-Text GenerationXAlignBLEU419.9Vanilla Transformer
Data-to-Text GenerationXAlignBLEU418.3Graph Attention Network Encoder +Transformer Decoder

Related Papers

Making Language Model a Hierarchical Classifier and Generator2025-07-17DiffRhythm+: Controllable and Flexible Full-Length Song Generation with Preference Optimization2025-07-17Mitigating Object Hallucinations via Sentence-Level Early Intervention2025-07-16Assay2Mol: large language model-based drug design using BioAssay context2025-07-16Describe Anything Model for Visual Question Answering on Text-rich Images2025-07-16The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs2025-07-15Seq vs Seq: An Open Suite of Paired Encoders and Decoders2025-07-15Hashed Watermark as a Filter: Defeating Forging and Overwriting Attacks in Weight-based Neural Network Watermarking2025-07-15