An attentive neural architecture for joint segmentation and parsing and its application to real estate ads

作者：

Highlights：

• We convert textual real estate ads to structured representations as property trees.

• We propose a new neural model for joint segmentation and parsing in 1 step.

• Our joint model outperforms 2-step pipeline methods with 3.42%.

• Including attention models incurs an additional 2.1% F1 improvement.

摘要

•We convert textual real estate ads to structured representations as property trees.•We propose a new neural model for joint segmentation and parsing in 1 step.•Our joint model outperforms 2-step pipeline methods with 3.42%.•Including attention models incurs an additional 2.1% F1 improvement.

论文关键词：Neural networks,Joint model,Relation extraction,Entity recognition,Dependency parsing

论文评审过程：Received 2 October 2017, Revised 18 January 2018, Accepted 20 February 2018, Available online 19 March 2018, Version of Record 19 March 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.02.031