Multilingual Attribute Extraction from News Web Pages

TL;DR

This paper develops and evaluates multilingual neural models for extracting news article attributes across six languages, improving upon existing tools and addressing language diversity in web page information extraction.

Contribution

It introduces a multilingual dataset and fine-tunes state-of-the-art models, demonstrating improved extraction performance over existing tools for news web pages in multiple languages.

Findings

Fine-tuned models outperform existing open-source tools.

Translation into English affects extraction quality.

Pre-trained multilingual models enhance attribute extraction.

Abstract

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.