arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1904.02244cs.CL
收藏

日语谓词论元结构分析的多任务学习

Multi-task Learning for Japanese Predicate Argument Structure Analysis

Tokyo Metropolitan University(东京都立大学)

Hikaru Omori, Mamoru Komachi

摘要:

事件名词是具有类似于谓词的论元结构的名词。最近的作品,包括那些被认为是最先进的,忽略事件名词或建立一个单一的模型来解决日语谓词论元结构分析(PASA)和事件名词论元结构分析(ENASA)。然而,由于谓词和事件名词之间存在相互作用,因此仅针对谓词是不够的。为了解决这个问题,我们提出了一个多任务学习方法的PASA和ENASA。与单任务模型相比,我们的多任务模型通过共享每个任务的知识来提高两个任务的性能。此外,在PASA中,我们的模型在NAIST文本语料库上的总体F1分数方面取得了最先进的结果。此外,这是在ENASA中首次采用神经网络的工作。

英文摘要:

An event-noun is a noun that has an argument structure similar to a predicate. Recent works, including those considered state-of-the-art, ignore event-nouns or build a single model for solving both Japanese predicate argument structure analysis (PASA) and event-noun argument structure analysis (ENASA). However, because there are interactions between predicates and event-nouns, it is not sufficient to target only predicates. To address this problem, we present a multi-task learning method for PASA and ENASA. Our multi-task models improved the performance of both tasks compared to a single-task model by sharing knowledge from each task. Moreover, in PASA, our models achieved state-of-the-art results in overall F1 scores on the NAIST Text Corpus. In addition, this is the first work to employ neural networks in ENASA.

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。

↑