文章基本信息

标题：Dependency parsing with structure preserving embeddings
本地全文：下载
作者：Ákos Kádár ; Lan Xiao ; Mete Kemertas 等
期刊名称：Conference on European Chapter of the Association for Computational Linguistics (EACL)
出版年度：2021
卷号：2021
页码：1684-1697
DOI：10.18653/v1/2021.eacl-main.144
语种：English
出版社：ACL Anthology
摘要：Modern neural approaches to dependency parsing are trained to predict a tree structure by jointly learning a contextual representation for tokens in a sentence, as well as a head–dependent scoring function. Whereas this strategy results in high performance, it is difficult to interpret these representations in relation to the geometry of the underlying tree structure. Our work seeks instead to learn interpretable representations by training a parser to explicitly preserve structural properties of a tree. We do so by casting dependency parsing as a tree embedding problem where we incorporate geometric properties of dependency trees in the form of training losses within a graph-based parser. We provide a thorough evaluation of these geometric losses, showing that a majority of them yield strong tree distance preservation as well as parsing performance on par with a competitive graph-based parser (Qi et al., 2018). Finally, we show where parsing errors lie in terms of tree relationship in order to guide future work.