Research on multi-dimensional end-to-end phrase recognition algorithm based on background knowledge

TL;DR

This paper introduces a multi-dimensional end-to-end phrase recognition algorithm that incorporates background knowledge and handles nested, multi-granular language features, improving accuracy and winning a competition.

Contribution

It proposes a novel annotation rule and matching algorithm that effectively recognize nested phrases and dependencies, integrating background knowledge into end-to-end recognition.

Findings

Improved accuracy on CPWD dataset by over 1 percentage point

Effective recognition of nested and multi-granular phrases

Won first place in Chinese humor type recognition at CCL 2018

Abstract

At present, the deep end-to-end method based on supervised learning is used in entity recognition and dependency analysis. There are two problems in this method: firstly, background knowledge cannot be introduced; secondly, multi granularity and nested features of natural language cannot be recognized. In order to solve these problems, the annotation rules based on phrase window are proposed, and the corresponding multi-dimensional end-to-end phrase recognition algorithm is designed. This annotation rule divides sentences into seven types of nested phrases, and indicates the dependency between phrases. The algorithm can not only introduce background knowledge, recognize all kinds of nested phrases in sentences, but also recognize the dependency between phrases. The experimental results show that the annotation rule is easy to use and has no ambiguity; the matching algorithm is more consistent with the multi granularity and diversity characteristics of syntax than the traditional end-to-end algorithm. The experiment on CPWD dataset, by introducing background knowledge, the new algorithm improves the accuracy of the end-to-end method by more than one point. The corresponding method was applied to the CCL 2018 competition and won the first place in the task of Chinese humor type recognition.