{"id":12657,"date":"2019-11-15T12:47:00","date_gmt":"2019-11-15T11:47:00","guid":{"rendered":"https:\/\/www.fundacionbankinter.org\/noticias\/comprension-de-lenguaje-natural\/"},"modified":"2025-12-01T23:35:51","modified_gmt":"2025-12-01T22:35:51","slug":"comprension-de-lenguaje-natural","status":"publish","type":"noticias","link":"https:\/\/www.fundacionbankinter.org\/en\/news\/comprension-de-lenguaje-natural\/","title":{"rendered":"Natural Language comprehension"},"content":{"rendered":"\n

The field of\u00a0computational linguistics<\/strong>\u2013the study of language from a computational perspective\u2013is over 70 years old and still has a long way to go. From the first translations done by a machine to the current boom in personal assistants, chatbots, etc., the increase in the number of natural language processing and language analysis tools in the 2000s has resulted in an obvious evolution of this field, whose limitations are still blurred.\u00a0Now the technology is working on Natural Language comprehension.<\/p>\n\n\n\n

During the FTF, the following computational linguistics tools were mentioned: <\/strong><\/p>\n\n\n\n

– Voice recognition<\/strong> is the transcription of audio content, someone\u2019s voice and what they say, into words.<\/p>\n\n\n\n

– Natural language comprehension<\/strong>, which involves language comprehension and correlating what we see and what we believe.<\/p>\n\n\n\n


Manch\u00f3n believes that these systems exercise \u201ccompetence without comprehension,\u201d<\/strong> a statement that is both widely shared and questioned in the scientific community. Philosopher of the mind and cognitive scientist Daniel Dennett<\/a> proposed it. The statement essentially means that, at a functional level, a system can reach a performance level (competence) that would be attributed to comprehension in human settings (intelligence); however, the system would not comprehend what it is doing.<\/p>\n\n\n\n

 – Dialogue management <\/strong>is essential to having a conversation. We need to teach machines how to understand speaking times,<\/strong> how to associate what someone just said with the information that was shared in the conversation.<\/p>\n\n\n\n

  – Natural language generation<\/strong> allows the machine to communicate in a way that a human can understand, by having an idea of what the interaction will be about and how it will take place. It\u2019s about generating a task, a message, information, anything, in natural language. 
– Speech synthesis<\/strong> makes it possible to generate natural language in the form of a voice.<\/p>\n\n\n\n

\n