WikiLingua
Introduced by Ladhak et al. in WikiLingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarization
WikiLingua includes ~770k article and summary pairs in 18 languages from WikiHow. Gold-standard article-summary alignments across languages are extracted by aligning the images that are used to describe each how-to step in an article.
Source: https://github.com/esdurmus/WikilinguaBenchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
WikiLingua (es->en)
|
mBART+
|
|||
|
WikiLingua (ru->en)
|
mBART+
|
|||
|
WikiLingua (tr->en)
|
mBART+
|
|||
|
WikiLingua (vi->en)
|
mBART+
|
|||
|
WikiLingua (tr->en)
|
DOCmT5
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
