Open AccessApplying Machine Learning to the Task of Generating Search Queries
Author(s) -
Александр Михайлович Гусенков,
Alina R. Sittikova
Publication year - 2021
Publication title -
èlektronnye biblioteki
Language(s) - English
Resource type - Journals
ISSN - 1562-5419
DOI - 10.26907/1562-5419-2021-24-2-271-292
Subject(s) - computer science , latent semantic analysis , tf–idf , artificial intelligence , recurrent neural network , natural language processing , transformer , information retrieval , cosine similarity , artificial neural network , task (project management) , singular value decomposition , machine learning , pattern recognition (psychology) , term (time) , physics , management , quantum mechanics , voltage , economics
In this paper we research two modifications of recurrent neural networks – Long Short-Term Memory networks and networks with Gated Recurrent Unit with the addition of an attention mechanism to both networks, as well as the Transformer model in the task of generating queries to search engines. GPT-2 by OpenAI was used as the Transformer, which was trained on user queries. Latent-semantic analysis was carried out to identify semantic similarities between the corpus of user queries and queries generated by neural networks. The corpus was convert-ed into a bag of words format, the TFIDF model was applied to it, and a singular value decomposition was performed. Semantic similarity was calculated based on the cosine measure. Also, for a more complete evaluation of the applicability of the models to the task, an expert analysis was carried out to assess the coherence of words in artificially created queries.