IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation
Samuel Cahyawijaya1 , Genta Indra Winata1∗, Bryan Wilie3∗, Karissa Vincentio4∗, Xiaohong Li2∗, Adhiguna Kuncoro5∗, Sebastian Ruder5, Zhi Yuan Lim2, Syafri Bahar2, Masayu Leylia Khodra3, Ayu Purwarianti3,6, Pascale Fung1 1The Hong Kong University of Science and Technology 2Gojek 3Institut Teknologi Bandung 4Universitas Multimedia Nusantara 5DeepMind 6Prosa.ai These authors contributed equally.
Abstract
Natural language generation (NLG) benchmarks provide an important avenue to measure progress and develop better NLG systems. Unfortunately, the lack of publicly available NLG benchmarks for low-resource languages poses a challenging barrier for building NLG systems that work well for languages with limited amounts of data. Here we introduce IndoNLG, the first benchmark to measure natural language generation (NLG) progress in three low-resource—yet widely spoken—languages of Indonesia: Indonesian, Javanese, and Sundanese. Altogether, these languages are spoken by more than 100 million native speakers, and hence constitute an important use case of NLG systems today. Concretely, IndoNLG covers six tasks: summarization, question answering, chit-chat, and three different pairs of machine translation (MT) tasks. We collate a clean pretraining corpus of Indonesian, Sundanese, and Javanese datasets, Indo4B-Plus, which is used to pretrain our models: IndoBART and IndoGPT. We show that IndoBART and IndoGPT achieve competitive performance on all tasks—despite using only one-fifth the parameters of a larger multilingual model, mBART ${}_{\text{LARGE}}$ Liu et al. (2020). This finding emphasize
中文速览
低资源语言（如印尼的爪哇语、巽他语）长期缺乏自然语言生成（NLG）的公开数据集和评测基准，导致相关系统几乎无从构建。研究团队为此推出了 IndoNLG——首个面向印度尼西亚语、爪哇语和巽他语三种语言的 NLG 综合基准，涵盖摘要生成、问答、闲聊对话和三对机器翻译共六项任务，并整理了干净的预训练语料库 Indo4B-Plus。在此基础上，他们训练了两个专用模型 IndoBART 和 IndoGPT，参数量仅为大型多语言模型 mBART-LARGE 的五分之一。实验表明，这两个模型在所有任务上均能与参数量大得多的多语言模型持平甚至超越，在爪哇语和巽他语等极低资源语言任务上尤为突出。这一发现说明，针对亲缘语言进行有针对性的预训练，可以用更少的数据和算力实现高效的低资源语言生成，为类似处境的其他语言提供了可借鉴的路径。
原文 arXiv:2104.08200;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2104.08200v3