Information analysis system based on bidirectional recursive neural network

Abstract

The invention relates to the field of processing of natural languages, and in particular relates to an information analysis system based on a bidirectional recursive neural network. The information analysis system comprises a bidirectional recursive neural network module; the system identifies enterprise names in a text to be analyzed into a beginning part, a keyword part, an industry part and a organizational form part in a segmented manner through the bidirectional recursive neural network module; and the keyword part as enterprise abbreviation is extracted and put in an enterprise abbreviation library. According to the system disclosed by the invention, the text to be processed is serialized through word segmentation; segmented words, phrases or punctuation marks are converted into vector data through a dictionary mapping table and input in the bidirectional recursive neural network; the barrier between the natural language and the neural network is broken; when enterprise names are identified, both above information and following information are depended; the accurate rate is relatively high; on the basis of identification of the enterprise names, the enterprise abbreviation is identified; furthermore, a corresponding enterprise abbreviation database is established; and powerful technical support is provided for related information analysis of an informal text.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to an information analysis system based on a bidirectional recursive neural network. Background technique [0002] With the rapid development of the Internet, a large amount of public web data has been generated, which has also spurred various emerging industries based on big data technology, such as Internet medical care, Internet education, corporate or personal credit investigation, etc. The rise of these Internet industries is inseparable from the analysis of a large amount of information and data, and the value of information analysis lies in sharpness and accuracy. Sharp analysis requires timely and rapid discovery of new information; but most of the data obtained directly from web pages are very Structured, in order to use these data, data cleaning has become the place where companies spend the most time and energy. In data cleaning, the extraction of specific info...

AI Technical Summary

Problems solved by technology

To use conditional random fields, you first need to design and construct feature templates based on the characteristics of the entity to be recognized. Feature templates include first-order words or multi-order phrases with a specified window size context, word prefixes, suffixes, part-of-speech tags and other status features; feature templates The construction is very time-consuming and labor-intensive, and the feature templates set manually are often only based on the characteristics of some samples, which has poor versatility; the recognition results are highly dependent on the feature templates, and usually only local context information can be used. The use is also independent of each other. The prediction cannot rely on longer historical state information, nor can it use longer future information feedback to correct possible historical errors; the prediction process is time-consuming and laborious, and the prediction results are difficult to achieve global optimality

In addition, due to the randomness and irregularity of the company's abbreviation, it is difficult to extract the company's abbreviation using the traditional CRF method

Images