{"total":21,"rows":[{"id":"2105.14444","title":"NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search","created":"2021-05-30","cited_by_count":56,"area":null},{"id":"2110.08518","title":"MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding","created":"2021-10-16","cited_by_count":45,"area":null},{"id":"2202.00217","title":"WebFormer: The Web-page Transformer for Structure Information Extraction","created":"2022-02-01","cited_by_count":34,"area":null},{"id":"2305.14336","title":"Schema-Driven Information Extraction from Heterogeneous Tables","created":"2023-05-23","cited_by_count":25,"area":null},{"id":"2201.10608","title":"DOM-LM: Learning Generalizable Representations for HTML Documents","created":"2022-01-25","cited_by_count":24,"area":null},{"id":"2101.02415","title":"Simplified DOM Trees for Transferable Attribute Extraction from the Web","created":"2021-01-07","cited_by_count":16,"area":null},{"id":"2110.12320","title":"CoVA: Context-aware Visual Attention for Webpage Information Extraction","created":"2021-10-24","cited_by_count":6,"area":null},{"id":"2402.18262","title":"Hierarchical Multimodal Pre-training for Visually Rich Webpage Understanding","created":"2024-02-28","cited_by_count":4,"area":null},{"id":"2205.12386","title":"PLAtE: A Large-scale Dataset for List Page Web Extraction","created":"2022-05-24","cited_by_count":3,"area":null},{"id":"2111.02168","title":"The Klarna Product Page Dataset: Web Element Nomination with Graph Neural Networks and Large Language Models","created":"2021-11-03","cited_by_count":2,"area":null},{"id":"2502.15688","title":"XPath Agent: An Efficient XPath Programming Agent Based on LLM for Web Crawler","created":"2024-12-17","cited_by_count":2,"area":null},{"id":"2305.13805","title":"Towards Zero-shot Relation Extraction in Web Mining: A Multimodal Approach with Relative XML Path","created":"2023-05-23","cited_by_count":1,"area":null},{"id":"2403.01698","title":"Hypertext Entity Extraction in Webpage","created":"2024-03-04","cited_by_count":1,"area":null},{"id":"2208.13086","title":"Label-Efficient Self-Training for Attribute Extraction from Semi-Structured Web Documents","created":"2022-08-27","cited_by_count":0,"area":null},{"id":"2408.04673","title":"AutoFAIR : Automatic Data FAIRification via Machine Reading","created":"2024-08-07","cited_by_count":0,"area":null},{"id":"2410.19771","title":"Author Unknown: Evaluating Performance of Author Extraction Libraries on Global Online News Articles","created":"2024-10-13","cited_by_count":0,"area":null},{"id":"2411.08278","title":"Knowledge Bases in Support of Large Language Models for Processing Web News","created":"2024-11-13","cited_by_count":0,"area":null},{"id":"2603.13773","title":"LiveWeb-IE: A Benchmark For Online Web Information Extraction","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2606.14821","title":"Co-Scraper: query-aware DOM Pruning and Reusable Scraper Synthesis for Lightweight Web Data Extraction","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.21284","title":"news-crawler-LM: A Small Long-Context Model For High-Quality News Crawling","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.18727","title":"Visual-Aware Representation of Web Pages for Machine Learning Applications","created":"2026-08-19","cited_by_count":0,"area":null}],"next_cursor":null}