arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.03147cs.CL
收藏

OpenIE6:开放式信息抽取的迭代网格标注和协调分析

OpenIE6: Iterative Grid Labeling and Coordination Analysis for Open Information Extraction

Indian Institute of Technology Delhi(德里印度理工学院);Indian Institute of Technology Bombay(孟买印度理工学院)

Keshav Kolluru, Vaibhav Adlakha, Samarth Aggarwal, Mausam, Soumen Chakrabarti

摘要:

最近的最先进的神经开放信息抽取(OpenIE)系统迭代地生成提取,需要部分输出的重复编码。这是一个巨大的计算成本。另一方面,OpenIE的序列标记方法要快得多,但提取质量较差。在本文中,我们通过提出一个基于迭代标记的系统来弥合这种权衡,该系统为OpenIE建立了一个新的最新技术水平,同时提取速度提高了10倍。这是通过一种新的迭代网格标记(IGL)架构来实现的,该架构将OpenIE视为二维网格标记任务。我们通过在训练时对网格应用覆盖(软)约束来进一步提高其性能。此外,在观察到最好的OpenIE系统在处理协调结构时会出现问题时,我们的OpenIE系统还采用了一个新的协调分析器,该分析器采用了相同的IGL架构。这个基于IGL的协调分析器帮助我们的OpenIE系统处理复杂的协调结构,同时也在协调分析任务上建立了一个新的技术水平,与以前的分析器相比,F1提高了12.3个百分点。我们的OpenIE系统,OpenIE6,在F1中击败了以前的系统多达4分,同时速度更快。

英文摘要:

A recent state-of-the-art neural open information extraction (OpenIE) system generates extractions iteratively, requiring repeated encoding of partial outputs. This comes at a significant computational cost. On the other hand, sequence labeling approaches for OpenIE are much faster, but worse in extraction quality. In this paper, we bridge this trade-off by presenting an iterative labeling-based system that establishes a new state of the art for OpenIE, while extracting 10x faster. This is achieved through a novel Iterative Grid Labeling (IGL) architecture, which treats OpenIE as a 2-D grid labeling task. We improve its performance further by applying coverage (soft) constraints on the grid at training time. Moreover, on observing that the best OpenIE systems falter at handling coordination structures, our OpenIE system also incorporates a new coordination analyzer built with the same IGL architecture. This IGL based coordination analyzer helps our OpenIE system handle complicated coordination structures, while also establishing a new state of the art on the task of coordination analysis, with a 12.3 pts improvement in F1 over previous analyzers. Our OpenIE system, OpenIE6, beats the previous systems by as much as 4 pts in F1, while being much faster.

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。

↑