SQL ChatBot – using Context Free Grammar

Patil, Rajvardhan; Boit, Sorio; Bowman, Nathaniel

doi:10.1109/iemtronics55184.2022.9795814

Cited by 2 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The task is to understand and represent the given natural language query in its equivalent SQL format. Authors from [6], [7] demonstrated how the KWS systems give more accurate results by giving particular importance to logical operators (and, or, not); similarly, [8] focused on words such as 'average, count, total' etc., to deal with advanced NLP queries. However, such attempts were limited in scope and domain, as the set of words to focus upon was domain specific.…”

Section: Regular Expressionsmentioning

confidence: 99%

“…This representation is called a one-hot encoding because, in a given row, only one column index has a non-zero value of '1'. Consider the following example: Sentence ="he started driving when he was 22 years old" Here, vocab = ['22', 'driving', 'he', 'old', 'started', 'was', 'when', 'years'] The one-hot matrix for the above sentence is shown in Table 1, having dimensions (9,8). If logical operations are performed on these one-hot vectors, they can be used to do a basic keyword search, which looks for the presence of one or more query words in a given document or corpus.…”

Section: A One Hot Embedding (Ohe)mentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Text Representation and Embedding Techniques in NLP

et al. 2023

View full text Add to dashboard Cite

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

show abstract

Section: Regular Expressionsmentioning

confidence: 99%

Section: A One Hot Embedding (Ohe)mentioning

confidence: 99%