arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.07067cs.CL
收藏

利用下一短语预测改进文本自动补全

Improving Text Auto-Completion with Next Phrase Prediction

University of Southern California(南加州大学);Upstage AI Research(Upstage AI 研究院);Singapore University of Technology and Design(新加坡科技设计大学)

Dong-Ho Lee, Zhiqiang Hu, Roy Ka-Wei Lee

摘要:

语言模型,如GPT-2,在构建文本自动完成任务的句法健全的句子表现良好。然而,这样的模型通常需要相当大的训练努力来适应特定的写作领域(例如,医学)。在本文中,我们提出了一种中间训练策略,以提高预训练的语言模型在文本自动完成任务中的性能,并使其快速适应特定领域。我们的策略包括一个新的自监督训练目标,称为下一个短语预测(NPP),它鼓励语言模型完成部分查询与丰富的短语,并最终提高模型的文本自动完成性能。初步实验表明,我们的方法是能够超越基线的自动完成电子邮件和学术写作领域。

英文摘要:

Language models such as GPT-2 have performed well on constructing syntactically sound sentences for text auto-completion task. However, such models often require considerable training effort to adapt to specific writing domains (e.g., medical). In this paper, we propose an intermediate training strategy to enhance pre-trained language models' performance in the text auto-completion task and fastly adapt them to specific domains. Our strategy includes a novel self-supervised training objective called Next Phrase Prediction (NPP), which encourages a language model to complete the partial query with enriched phrases and eventually improve the model's text auto-completion performance. Preliminary experiments have shown that our approach is able to outperform the baselines in auto-completion for email and academic writing domains.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑