Summary

Conversational agents, also knowns as chatbots, are text-based dialogue systems that understand human language in order to hold a "real" conversation with people. To achieve a good understanding of what a human is saying, chatbots need to classify dialogue into intents, that is, a set of sentences representing a meaning. Conversational agents can be classified into several groups, depending on the type of input-output data and knowledge limits. This representation of meaning is not easy. To have sound knowledge supporting a chatbot, a huge corpus is needed. Finding the best way to represent a word is a challenge, and one-hot encoding is useless. The main problem with one-hot encoding is the size of the encoded vectors. If we have a corpus of 88,000 words, then the vectors will have a size of 88,000, and without any relationship between the words. This is where the concept of word embeddings enters the picture.

Word embeddings are a collection of techniques and methods to map words...