Keyword extraction method integrating theme information and bidirectional LSTM

Abstract

The invention relates to a keyword extraction method integrating theme information and bidirectional LSTM. The method comprises the following steps: firstly, combining LDA and Skip-gram model to learnthe topic word vector representation of the word; taking the subject word vector of the word as the input of a bidirectional LSTM model; time memory characteristics of a bidirectional LSTM model arefully utilized, and semantic information of themes of words is modeled at the same time; and finally, outputting a label prediction probability of the word through a softmax function. According to themethod, the context semantic information of different distances can be fully utilized to predict the keywords, the obtained correct rate, recall rate and F value are all good, the keyword recognitioneffect obviously surpassing the prior art is achieved, and the requirements of practical application can be well met.

Description

technical field [0001] The invention belongs to the technical field of text processing, and in particular relates to a method for extracting keywords by integrating subject information and bidirectional LSTM. Background technique [0002] With the advent of the era of big data, network information has shown explosive growth, how to quickly obtain valuable key information from massive literature resources is of great significance to information retrieval and knowledge discovery. In the field of NLP, automatic keyword extraction is the basis for natural language processing tasks such as natural language understanding, automatic summarization, text classification and clustering, and machine translation. Traditional keyword extraction methods often rely on complex features manually set, and the recognition effect is not good. In recent years, with the popularity and development of deep learning theory, deep neural networks have been widely used in various fields such as images,...

AI Technical Summary

Problems solved by technology

The traditional LSTM sequence model cannot fully capture contextual semantic information with topic-distinguishing properties in keyword recognition tasks

Images