Beam Search is a search algorithm that explores a graph by expanding the most promising nodes in a limited set, rather than considering all possible nodes. It is commonly used in procesamiento de lenguaje natural and traducción automática tareas, donde el objetivo es generar secuencias, como oraciones o frases.
Unlike traditional search algorithms that may evaluate all possible paths (like breadth-first or búsqueda en profundidad), Beam Search maintains a fixed number of the best candidates at each step, known as the ancho de haz. This means that only the top ‘N’ most promising candidates are kept for further exploration, while the rest are discarded. This approach helps to reduce the computational complexity and improves the efficiency of the search process.
Por ejemplo, en una modelo de lenguaje generating text, at each word prediction step, Beam Search would consider the top ‘N’ most likely words based on previous context, forming a new set of candidate sentences. The algorithm continues this process until a complete sentence is formed, selecting the best options at each stage.
One important aspect of Beam Search is that it balances between exploration (trying out various options) and exploitation (focusing on the best-known options). A smaller beam width may lead to faster computations but risks missing better solutions, while a larger beam width may provide more comprehensive results at the cost of increased recursos computacionales.
En la práctica, Beam Search se usa ampliamente en aplicaciones como reconocimiento de voz, text summarization, and chatbot development, where generating coherent and contextually appropriate outputs is crucial.