Жаңалықтар тақырыптарын генерациялау

AbstractHow to generate summaries of different styles without requiring corpora in the target styles, or training separate models? We present two novel methods that can be deployed during summary decoding …...

AbstractNatural Language Generation (NLG) for non-English languages is hampered by the scarcity of datasets in these languages. We present the IndicNLG Benchmark, a collection of datasets for benchmarking NLG for …...

AbstractRecent language generative models are mostly trained on large-scale datasets, while in some real scenarios, the training datasets are often expensive to obtain and would be small-scale. In this paper …...