arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1904.02306cs.CL
收藏

一种用于改进上下文神经词形还原的简单联合模型

A Simple Joint Model for Improved Contextual Neural Lemmatization

Allen Institute for Artificial Intelligence(艾伦人工智能研究所);Johns Hopkins University(约翰斯·霍普金斯大学);University of Cambridge(剑桥大学)

Chaitanya Malaviya, Shijie Wu, Ryan Cotterell

AI总结:

本文提出一种简单的联合神经模型,同时进行词形还原和形态标注,在通用依赖语料库的20种语言上取得最先进结果,尤其对低资源语言和形态复杂语言有益。

摘要:

英语动词有多种形式。例如,talk 也可能根据上下文出现为 talks、talked 或 talking。词形还原的 NLP 任务旨在将这些多样化的形式映射回一个规范形式,即词元。我们提出了一种用于词形还原和形态标注的简单联合神经模型,该模型在通用依赖语料库的 20 种语言上取得了最先进的结果。我们的论文描述了该模型以及训练和解码过程。错误分析表明,联合形态标注和词形还原在低资源词形还原和形态复杂性程度较高的语言中尤其有帮助。代码和预训练模型可在 https://sigmorphon.github.io/sharedtasks/2019/task2/ 获取。

英文摘要:

English verbs have multiple forms. For instance, talk may also appear as talks, talked or talking, depending on the context. The NLP task of lemmatization seeks to map these diverse forms back to a canonical one, known as the lemma. We present a simple joint neural model for lemmatization and morphological tagging that achieves state-of-the-art results on 20 languages from the Universal Dependencies corpora. Our paper describes the model in addition to training and decoding procedures. Error analysis indicates that joint morphological tagging and lemmatization is especially helpful in low-resource lemmatization and languages that display a larger degree of morphological complexity. Code and pre-trained models are available at https://sigmorphon.github.io/sharedtasks/2019/task2/.

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。

↑