arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.04748cs.CL
收藏

打破字符:子词足够好的MRL毕竟?

Breaking Character: Are Subwords Good Enough for MRLs After All?

Tel Aviv University(特拉维夫大学);Bar Ilan University(巴伊兰大学)

Omri Keren, Tal Avinari, Reut Tsarfaty, Omer Levy

摘要:

大型预训练语言模型(PLM)通常在任何预训练或推断之前将输入字符串标记为连续的子词。然而,以前的研究声称,这种形式的子词标记化是不足以处理形态丰富的语言(MRL)。我们重新审视这一假设,通过预训练一个BERT风格的掩码语言模型字符序列,而不是词片。我们比较由此产生的模型,被称为TavBERT,对当代PLM的基础上的子词三个高度复杂和模糊的MRL(希伯来语,土耳其语和阿拉伯语),测试他们的形态和语义任务。我们的研究结果表明,对于所有测试的语言,虽然TavBERT获得了轻微的改进,在表面级的任务,如POS标记和完整的形态消歧,基于子词的PLM实现语义任务,如命名实体识别和提取问答的性能显着提高。这些结果展示并(重新)确认了子词标记化作为许多语言(包括MRL)的合理建模假设的潜力。

英文摘要:

Large pretrained language models (PLMs) typically tokenize the input string into contiguous subwords before any pretraining or inference. However, previous studies have claimed that this form of subword tokenization is inadequate for processing morphologically-rich languages (MRLs). We revisit this hypothesis by pretraining a BERT-style masked language model over character sequences instead of word-pieces. We compare the resulting model, dubbed TavBERT, against contemporary PLMs based on subwords for three highly complex and ambiguous MRLs (Hebrew, Turkish, and Arabic), testing them on both morphological and semantic tasks. Our results show, for all tested languages, that while TavBERT obtains mild improvements on surface-level tasks à la POS tagging and full morphological disambiguation, subword-based PLMs achieve significantly higher performance on semantic tasks, such as named entity recognition and extractive question answering. These results showcase and (re)confirm the potential of subword tokenization as a reasonable modeling assumption for many languages, including MRLs.

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。

↑