“Hey Siri, how many days is it until Halloween?”
“10 days to go.”
“Can you wake me up at 6 tomorrow?”
“Sure. Alarm set for 6:00 am”
“Are there any popular eateries around this place?”
“Yes, there you go”
*presents a list of places sorted in the order of importance*
We commonly have such kind of conversations with our intelligent personal assistants, which are adept at understanding the context of the query and presenting results in spoken language, sometimes also providing useful links, maps for directions, etc. Such systems are based on Natural Language Processing (NLP) – a combination of computer science, artificial intelligence and computational linguistics – aimed to help humans and machines communicate in natural language, just like a human to human conversation. An effective NLP system is able to comprehend the question and its meaning, dissect it, determine appropriate action, and respond back in a language the user will understand. Alan Turing stated that if a machine can have a conversation with a person and trick him into believing that he is actually speaking to a human, then such a machine is artificially intelligent. This test eventually came to be known as the Turing test and passing it has been one of the most sought after goals in computer science. It is what NLP systems aim to achieve.
Apart from personal assistants like Siri, Alexa and Google Assistant, some other applications of NLP include social media sentiment analysis, summarizing information and e-mail spam filtering. NLP is a vast subject that comprises of speech recognition, speech synthesis, Natural Language Generation (NLG) and Natural Language Understanding (NLU). While speech recognition software transcribes spoken language, speech synthesis software focuses on text to speech conversion.
NLU attempts to understand the meaning behind written text. After having the speech recognition software convert speech into text, NLU software comes into the picture to decipher its meaning. It is quite possible that the same text has various meanings, or different words have the same meaning, or that the meaning changes with the context. Knowing the rules and structure of the language, understanding the text without ambiguity are some of the challenges faced by NLU systems. Popular applications include sentiment detection and profanity filtering among others. Google acquired API.ai provides tools for speech recognition and NLU.
NLG does exactly the opposite. Given the data, it analyzes it and generates narratives in conversational language. It goes way beyond template based systems, having been configured with the domain knowledge and experience of a human expert to produce well-researched, accurate output within seconds. Narratives can be generated for people across all hierarchical levels in an organization, in multiple languages. Firms like vPhrase are leading this space with their NLG platform PHRAZOR. Data analysis, automated report writing, etc. are applications of NLG.
Most real-world applications are based on one or a combination of NLP technologies. For instance, if we were to consider a personal assistant like Siri, the software architecture can be as depicted below:
NLP is increasingly becoming an important area of interest and major tech giants like Google, Apple and IBM are investing heavily to make their systems more human-like. According to a study by Tractica, the global NLP market is expected to reach $22.3 billion by 2025. These systems are already trending and it is only a matter of time before they redefine the way we interact with technology on a daily basis.