Hierarchical Neural Network for Extracting Knowledgeable Snippets and Documents

TL;DR

This paper introduces a CNN-based hierarchical model for extracting knowledgeable snippets and annotating knowledgeable documents from social media, improving efficiency and accuracy over pattern-based methods.

Contribution

A novel semantic-based CNN model with a hierarchical structure that handles multiple domains simultaneously for extracting knowledgeable content.

Findings

The proposed model outperforms pattern-based methods in accuracy.

Joint training across domains reduces training time.

Demonstrated effectiveness on WeChat social media data.

Abstract

In this study, we focus on extracting knowledgeable snippets and annotating knowledgeable documents from Web corpus, consisting of the documents from social media and We-media. Informally, knowledgeable snippets refer to the text describing concepts, properties of entities, or relations among entities, while knowledgeable documents are the ones with enough knowledgeable snippets. These knowledgeable snippets and documents could be helpful in multiple applications, such as knowledge base construction and knowledge-oriented service. Previous studies extracted the knowledgeable snippets using the pattern-based method. Here, we propose the semantic-based method for this task. Specifically, a CNN based model is developed to extract knowledgeable snippets and annotate knowledgeable documents simultaneously. Additionally, a "low-level sharing, high-level splitting" structure of CNN is designed to handle the documents from different content domains. Compared with building multiple domain-specific CNNs, this joint model not only critically saves the training time, but also improves the prediction accuracy visibly. The superiority of the proposed method is demonstrated in a real dataset from Wechat public platform.