A Survey of Text Representation and Embedding Techniques in NLP

Natural Language Processing (NLP) is a research field where language in consideration processed to understand its syntactic, semantic, and sentimental aspects. The advancement the NLP area has helped solve problems domains such as Neural Machine Translation, Name Entity Recognition, Sentiment Analysis, Chatbots, name few. topic of broadly consists two main parts: representation input text (raw data) into numerical format (vectors or matrix) design models for processing data. This paper focuses on former part surveys how evolved from rule-based, statistical more context-sensitive learned representations. For each embedding type, we list their representation, issues they addressed, limitations, applications. survey covers history representations 1970s onwards, regular expressions latest vector used encode raw It demonstrates progressed it could comprehend just bits pieces all significant aspects over time.