Research on Annotation Rules and Recognition Algorithm Based on Phrase Window

TL;DR

This paper introduces phrase window-based labeling rules and recognition algorithms to improve dependency parsing in NLP, addressing complexity and multi-granularity issues, and demonstrates enhanced accuracy and competitive performance.

Contribution

It proposes a novel phrase window labeling scheme and recognition algorithm that effectively handle multi-granularity and nested phrases in dependency parsing.

Findings

Improved parsing accuracy by about 1 point on CPWD dataset.

Achieved first place in Chinese Metaphor Sentiment Analysis Task.

Labeling rules are simple, unambiguous, and facilitate nested phrase recognition.

Abstract

At present, most Natural Language Processing technology is based on the results of Word Segmentation for Dependency Parsing, which mainly uses an end-to-end method based on supervised learning. There are two main problems with this method: firstly, the la-beling rules are complex and the data is too difficult to label, the workload of which is large; secondly, the algorithm cannot recognize the multi-granularity and diversity of language components. In order to solve these two problems, we propose labeling rules based on phrase windows, and designed corresponding phrase recognition algorithms. The labeling rule uses phrases as the minimum unit, di-vides sentences into 7 types of nestable phrase types, and marks the grammatical dependencies between phrases. The corresponding algorithm, drawing on the idea of identifying the target area in the image field, can find the start and end positions of various phrases in the sentence, and realize the synchronous recognition of nested phrases and grammatical dependencies. The results of the experiment shows that the labeling rule is convenient and easy to use, and there is no ambiguity; the algorithm is more grammatically multi-granular and diverse than the end-to-end algorithm. Experiments on the CPWD dataset improve the accuracy of the end-to-end method by about 1 point. The corresponding method was applied to the CCL2018 competition, and the first place in the Chinese Metaphor Sentiment Analysis Task.