arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1805.05089cs.CL
收藏

基于异构树库的语法分析器训练

Parser Training with Heterogeneous Treebanks

Uppsala University(乌普萨拉大学);Department of Linguistics and Philology(语言学与文献学系)

Sara Stymne, Miryam de Lhoneux, Aaron Smith, Joakim Nivre

摘要:

在训练单语依存分析器时,如何充分利用多个异构树库是一个有待解决的问题。我们首先调查以前提出的,但很少评估,利用多个树库的基础上连接训练集,有或没有微调的战略。我们接着提出了一种基于树库嵌入的新方法。我们对几种语言进行了实验,结果表明,在许多情况下,微调和树库嵌入导致了单树库或级联的实质性改进,平均增益为2.0- 3.5 LAS点。我们认为,树库嵌入应首选由于其概念的简单性,灵活性和可扩展性。

英文摘要:

How to make the most of multiple heterogeneous treebanks when training a monolingual dependency parser is an open question. We start by investigating previously suggested, but little evaluated, strategies for exploiting multiple treebanks based on concatenating training sets, with or without fine-tuning. We go on to propose a new method based on treebank embeddings. We perform experiments for several languages and show that in many cases fine-tuning and treebank embeddings lead to substantial improvements over single treebanks or concatenation, with average gains of 2.0--3.5 LAS points. We argue that treebank embeddings should be preferred due to their conceptual simplicity, flexibility and extensibility.

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。

↑