Bootstrapping Large-Scale Fine-Grained Contextual Advertising Classifier from Wikipedia

TL;DR

This paper introduces wiki2cat, a scalable method for fine-grained contextual advertising classification that leverages Wikipedia's category graph to generate training data without manual labeling, improving large-scale categorization accuracy.

Contribution

The paper presents wiki2cat, a novel approach that uses Wikipedia categories to bootstrap large-scale fine-grained classifiers without manual annotation or expert rules.

Findings

Achieves competitive performance on multiple datasets

Handles over 300 fine-grained categories effectively

Outperforms keyword-based baselines

Abstract

Contextual advertising provides advertisers with the opportunity to target the context which is most relevant to their ads. However, its power cannot be fully utilized unless we can target the page content using fine-grained categories, e.g., "coupe" vs. "hatchback" instead of "automotive" vs. "sport". The widely used advertising content taxonomy (IAB taxonomy) consists of 23 coarse-grained categories and 355 fine-grained categories. With the large number of categories, it becomes very challenging either to collect training documents to build a supervised classification model, or to compose expert-written rules in a rule-based classification system. Besides, in fine-grained classification, different categories often overlap or co-occur, making it harder to classify accurately. In this work, we propose wiki2cat, a method to tackle the problem of large-scaled fine-grained text classification by tapping on Wikipedia category graph. The categories in IAB taxonomy are first mapped to category nodes in the graph. Then the label is propagated across the graph to obtain a list of labeled Wikipedia documents to induce text classifiers. The method is ideal for large-scale classification problems since it does not require any manually-labeled document or hand-curated rules or keywords. The proposed method is benchmarked with various learning-based and keyword-based baselines and yields competitive performance on both publicly available datasets and a new dataset containing more than 300 fine-grained categories.