arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1312.5129cs.CL
收藏

不连续语言单元的深度学习嵌入

Deep Learning Embeddings for Discontinuous Linguistic Units

Center for Information and Language Processing(信息与语言处理中心);University of Munich(慕尼黑大学)

Wenpeng Yin, Hinrich Schütze

摘要:

深度学习嵌入已成功用于许多自然语言处理问题。嵌入主要是为单词形式计算的,尽管最近的一些论文已经将其扩展到其他语言单位,如词素和短语。在本文中,我们认为,学习嵌入不连续的语言单位也应该考虑。在对共指消解的实验评估中,我们表明这种嵌入比单词形式的嵌入表现得更好。

英文摘要:

Deep learning embeddings have been successfully used for many natural language processing problems. Embeddings are mostly computed for word forms although a number of recent papers have extended this to other linguistic units like morphemes and phrases. In this paper, we argue that learning embeddings for discontinuous linguistic units should also be considered. In an experimental evaluation on coreference resolution, we show that such embeddings perform better than word form embeddings.

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。

↑