arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1504.05319cs.CL
收藏

大数据小数据,域内域外,已知单词未知单词:单词表征对序列标签任务的影响

Big Data Small Data, In Domain Out-of Domain, Known Word Unknown Word: The Impact of Word Representation on Sequence Labelling Tasks

NICTA(澳大利亚国家信息与通信技术研究院);The Australian National University(澳大利亚国立大学);The University of Melbourne(墨尔本大学);University of Edinburgh(爱丁堡大学)

Lizhen Qu, Gabriela Ferraro, Liyuan Zhou, Weiwei Hou, Nathan Schneider, Timothy Baldwin

摘要:

词嵌入--可以从未标记的数据中学习的分布式词表示--已经被证明在许多自然语言处理应用中具有很高的实用性。在本文中,我们进行外部评估的五个流行的词嵌入方法的背景下,四个序列标签的任务:POS标记,句法组块,NER和MWE识别。本文的一个特别重点是分析基于任务的更新单词表征的效果。我们发现,当使用词嵌入作为特征时,只要几百个训练实例就足以达到有竞争力的结果,并且词嵌入导致了OOV词和域外的改进。也许更令人惊讶的是,我们的结果表明,不同的词嵌入方法之间几乎没有差异,并且简单的布朗聚类通常在我们考虑的所有任务中与词嵌入竞争。

英文摘要:

Word embeddings -- distributed word representations that can be learned from unlabelled data -- have been shown to have high utility in many natural language processing applications. In this paper, we perform an extrinsic evaluation of five popular word embedding methods in the context of four sequence labelling tasks: POS-tagging, syntactic chunking, NER and MWE identification. A particular focus of the paper is analysing the effects of task-based updating of word representations. We show that when using word embeddings as features, as few as several hundred training instances are sufficient to achieve competitive results, and that word embeddings lead to improvements over OOV words and out of domain. Perhaps more surprisingly, our results indicate there is little difference between the different word embedding methods, and that simple Brown clusters are often competitive with word embeddings across all tasks we consider.

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。

↑