arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.10322cs.CLcs.AIcs.IRcs.LG
收藏

消除无标记语言模型的差距

Bridging the Gap for Tokenizer-Free Language Models

Google AI(谷歌人工智能)

Dokook Choe, Rami Al-Rfou, Mandy Guo, Heeyoung Lee, Noah Constant

摘要:

在大规模数据集上,基于字符的语言模型(LM)在质量上一直滞后,并且当前最先进的LM依赖于单词标记化。它已被假定,注入到模型中的标记器的先验知识是必不可少的,以实现竞争的结果。在本文中,我们表明,与传统观点相反,具有足够容量的无标记LM可以在大规模数据集上实现有竞争力的性能。我们训练了一个基于十亿字(lm1b)基准测试的具有40个自我注意力层的香草Transformer网络,并实现了无标记器LM的最新技术水平,使这些模型与基于单词的模型不相上下。

英文摘要:

Purely character-based language models (LMs) have been lagging in quality on large scale datasets, and current state-of-the-art LMs rely on word tokenization. It has been assumed that injecting the prior knowledge of a tokenizer into the model is essential to achieving competitive results. In this paper, we show that contrary to this conventional wisdom, tokenizer-free LMs with sufficient capacity can achieve competitive performance on a large scale dataset. We train a vanilla transformer network with 40 self-attention layers on the One Billion Word (lm1b) benchmark and achieve a new state of the art for tokenizer-free LMs, pushing these models to be on par with their word-based counterparts.

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。

↑