arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.00407cs.CLcs.AI
收藏

形态学信息在上下文词元还原中的作用

On the Role of Morphological Information for Contextual Lemmatization

University of the Basque Country UPV/EHU(巴斯克大学(UPV/EHU))

Olia Toporkov, Rodrigo Agerri

AI总结:

本文实证研究了形态学信息在六种语言上下文词元还原中的作用,发现细粒度形态特征对训练并非关键,现代上下文词表示已隐式编码足够信息,使用简单UPOS标签或无形态学训练的模型在领域外表现更优。

摘要:

词元还原是一项自然语言处理(NLP)任务,旨在从给定的屈折词生成其规范形式或词元。词元还原是促进下游NLP应用的基础任务之一,对于高屈折语言尤为重要。鉴于从屈折词获取词元的过程可以通过观察其形态句法类别来解释,在训练上下文词元还原器时包含细粒度的形态句法信息已成为一种常见做法,而未考虑这是否在下游性能方面达到最优。为了解决这一问题,本文在形态复杂度各异的六种语言(巴斯克语、土耳其语、俄语、捷克语、西班牙语和英语)中,实证研究了形态学信息在开发上下文词元还原器中的作用。此外,与以往绝大多数研究不同,我们还在领域外设置下评估了词元还原器,毕竟这是它们最常见的应用场景。研究结果令人惊讶。事实证明,在训练期间为词元还原器提供细粒度的形态学特征并没有那么有益,甚至对黏着语也是如此。实际上,现代的上下文词表示似乎隐式地编码了足够的形态学信息,即使没有任何显式的形态学信号,也能获得具有竞争力的上下文词元还原器。此外,我们的实验表明,领域外表现最好的词元还原器是那些使用简单的UPOS标签或在没有形态学信息的情况下训练的模型;最后,当前的词元还原评估实践不足以清晰地区分不同模型。

英文摘要:

Lemmatization is a natural language processing (NLP) task which consists of producing, from a given inflected word, its canonical form or lemma. Lemmatization is one of the basic tasks that facilitate downstream NLP applications, and is of particular importance for high-inflected languages. Given that the process to obtain a lemma from an inflected word can be explained by looking at its morphosyntactic category, including fine-grained morphosyntactic information to train contextual lemmatizers has become common practice, without considering whether that is the optimum in terms of downstream performance. In order to address this issue, in this paper we empirically investigate the role of morphological information to develop contextual lemmatizers in six languages within a varied spectrum of morphological complexity: Basque, Turkish, Russian, Czech, Spanish and English. Furthermore, and unlike the vast majority of previous work, we also evaluate lemmatizers in out-of-domain settings, which constitutes, after all, their most common application use. The results of our study are rather surprising. It turns out that providing lemmatizers with fine-grained morphological features during training is not that beneficial, not even for agglutinative languages. In fact, modern contextual word representations seem to implicitly encode enough morphological information to obtain competitive contextual lemmatizers without seeing any explicit morphological signal. Moreover, our experiments suggest that the best lemmatizers out-of-domain are those using simple UPOS tags or those trained without morphology and, finally, that current evaluation practices for lemmatization are not adequate to clearly discriminate between models.

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。

↑