Multilingual Attribute Extraction from News Web Pages
This addresses the challenge of multilingual information extraction for news domains, which is incremental as it adapts existing models to new data and languages.
The paper tackled the problem of automatically extracting attributes from news web pages in multiple languages by fine-tuning pre-trained models like MarkupLM and DOM-LM on a new multilingual dataset of 3,172 pages across six languages, achieving superior extraction metrics compared to existing tools.
This paper addresses the challenge of automatically extracting attributes from news article web pages across multiple languages. Recent neural network models have shown high efficacy in extracting information from semi-structured web pages. However, these models are predominantly applied to domains like e-commerce and are pre-trained using English data, complicating their application to web pages in other languages. We prepared a multilingual dataset comprising 3,172 marked-up news web pages across six languages (English, German, Russian, Chinese, Korean, and Arabic) from 161 websites. The dataset is publicly available on GitHub. We fine-tuned the pre-trained state-of-the-art model, MarkupLM, to extract news attributes from these pages and evaluated the impact of translating pages into English on extraction quality. Additionally, we pre-trained another state-of-the-art model, DOM-LM, on multilingual data and fine-tuned it on our dataset. We compared both fine-tuned models to existing open-source news data extraction tools, achieving superior extraction metrics.