The reviewed record of science sign in
Pith

arxiv: 2203.05437 · v2 · pith:332HJRBS · submitted 2022-03-10 · cs.CL · cs.AI

IndicNLG Benchmark: Multilingual Datasets for Diverse NLG Tasks in Indic Languages

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:332HJRBSrecord.jsonopen to challenge →

classification cs.CL cs.AI
keywords languagesbenchmarkdatasetsgenerationmodelsmultilingualtasksdataset
0
0 comments X
read the original abstract

Natural Language Generation (NLG) for non-English languages is hampered by the scarcity of datasets in these languages. In this paper, we present the IndicNLG Benchmark, a collection of datasets for benchmarking NLG for 11 Indic languages. We focus on five diverse tasks, namely, biography generation using Wikipedia infoboxes, news headline generation, sentence summarization, paraphrase generation and, question generation. We describe the created datasets and use them to benchmark the performance of several monolingual and multilingual baselines that leverage pre-trained sequence-to-sequence models. Our results exhibit the strong performance of multilingual language-specific pre-trained models, and the utility of models trained on our dataset for other related NLG tasks. Our dataset creation methods can be easily applied to modest-resource languages as they involve simple steps such as scraping news articles and Wikipedia infoboxes, light cleaning, and pivoting through machine translation data. To the best of our knowledge, the IndicNLG Benchmark is the first NLG benchmark for Indic languages and the most diverse multilingual NLG dataset, with approximately 8M examples across 5 tasks and 11 languages. The datasets and models are publicly available at https://ai4bharat.iitm.ac.in/indicnlg-suite.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.