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 1909.02607cs.CL
收藏

作为转换的广义语义解析

Broad-Coverage Semantic Parsing as Transduction

Johns Hopkins University(约翰斯·霍普金斯大学)

Sheng Zhang, Xutai Ma, Kevin Duh, Benjamin Van Durme

摘要:

我们统一了不同的广泛覆盖的语义解析任务下的转导范式,并提出了一个基于注意力的神经框架,逐步建立一个意义表示通过一系列的语义关系。通过利用多个注意力机制,可以有效地训练换能器而不依赖于预先训练的对准器。在三个独立的广泛覆盖的语义解析任务- AMR,SDP和UCCA -上进行的实验表明,我们的基于注意力的神经传感器提高了AMR和UCCA的最新技术水平,并且与SDP的最新技术水平相竞争。

英文摘要:

We unify different broad-coverage semantic parsing tasks under a transduction paradigm, and propose an attention-based neural framework that incrementally builds a meaning representation via a sequence of semantic relations. By leveraging multiple attention mechanisms, the transducer can be effectively trained without relying on a pre-trained aligner. Experiments conducted on three separate broad-coverage semantic parsing tasks -- AMR, SDP and UCCA -- demonstrate that our attention-based neural transducer improves the state of the art on both AMR and UCCA, and is competitive with the state of the art on SDP.

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。

↑