Aravindan Kamatchi Sundaram, B. Pabitramohan Prusty, Rohit Batra · 2026 · arXiv
DOI: 10.48550/arXiv.2610.29895 · open-access PDF
Durante la última década, se han dedicado esfuerzos sustanciales al desarrollo de métodos de aprendizaje automático (ML) para extraer datos de materiales y, cuando sea posible, conocimientos de materiales directamente de la literatura científica. Esta revisión rastrea la evolución de estos métodos desde conductos heurísticos basados en reglas a través de modelos de procesamiento de lenguaje natural (NLP) y codificadores basados en transformadores hasta, finalmente, modelos de lenguaje grande (LLM) y sistemas de agentes capaces de extraer información de materiales en múltiples modalidades, incluyendo texto, tablas y figuras.
Machine translation (Meta M2M100); the English original follows.
Over the past decade, substantial efforts have been devoted to developing machine learning (ML) methods for extracting materials data and, where possible, materials knowledge directly from the scientific literature. This review traces the evolution of these methods from heuristic, rule-based pipelines through natural language processing (NLP) models and transformer-based encoders to, lastly, large language models (LLMs) and agentic systems capable of extracting materials information across multiple modalities, including text, tables, and figures. Beside construction of large, queryable materia
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29895, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange