DeepTagger: Knowledge Enhanced Named Entity Recognition for Web-Based Ads Queries

TL;DR

DeepTagger is a novel knowledge-enhanced NER model tailored for web-based ad queries, addressing challenges of data scarcity and query characteristics by leveraging unlabeled data, search results, and large language models.

Contribution

The paper introduces DeepTagger, combining model-free and model-based knowledge enhancement techniques, including data augmentation and prompt-based labeling, for improved web query NER.

Findings

DeepTagger outperforms baseline models on multiple NER benchmarks.

Knowledge augmentation significantly improves recognition accuracy.

Prompt-based labeling reduces reliance on annotated datasets.

Abstract

Named entity recognition (NER) is a crucial task for online advertisement. State-of-the-art solutions leverage pre-trained language models for this task. However, three major challenges remain unresolved: web queries differ from natural language, on which pre-trained models are trained; web queries are short and lack contextual information; and labeled data for NER is scarce. We propose DeepTagger, a knowledge-enhanced NER model for web-based ads queries. The proposed knowledge enhancement framework leverages both model-free and model-based approaches. For model-free enhancement, we collect unlabeled web queries to augment domain knowledge; and we collect web search results to enrich the information of ads queries. We further leverage effective prompting methods to automatically generate labels using large language models such as ChatGPT. Additionally, we adopt a model-based knowledge enhancement method based on adversarial data augmentation. We employ a three-stage training framework to train DeepTagger models. Empirical results in various NER tasks demonstrate the effectiveness of the proposed framework.