Film and television entity identification method based on Bilstm-crf and knowledge graph

Abstract

The invention discloses a film and television entity identification method based on Bilstm-crf and knowledge graph, which comprises the steps of obtaining a character vector and a part-of-speech vector of a to-be-recognized text, performing weighted summation on the character vector and the part-of-speech vector, and inputting a result into a target bidirectional LSTM model for processing to obtain a text feature sequence; inputting the text feature sequence into a target CRF model for processing to obtain a named entity recognition result of the to-be-recognized text; and inquiring the namedentity recognition result in the film and television knowledge graph to further verify the result. According to the method, entity extraction can be effectively carried out on the movie and televisionsearch text of the user, the movie and television knowledge graph is fully utilized to mine the abstract movie and television search intention of the user, and the use experience of the user is improved. Word vectors trained through the language model are used as bottom layer input of the neural network under the condition of less annotation data, so that the training efficiency is improved, andthe method has a good application prospect and can be widely applied to entity recognition scenes in various fields.

Description

technical field [0001] The invention relates to the technical field of deep learning natural language processing, in particular to a video and television entity recognition method based on Bilstm-crf and knowledge graph. Background technique [0002] TV is a must-have device for every family, almost every day there are new movies and TV shows on the shelves, which allows people to search for a large number of movie and TV resources from TV, such as people can search for movies and TV shows based on information such as directors, actors, titles, genres, etc. Resources, how to accurately extract film and television entities in an effective way to help users quickly find their favorite film and television dramas has become an important requirement. [0003] Traditional named entity recognition mostly uses rule-based and statistical machine learning methods. Initially, named entity recognition took a lexicon- and rule-based approach. Most of these methods are based on rule kno...

AI Technical Summary

Problems solved by technology

This method makes the training of the model an end-to-end overall process, rather than the traditional pipeline (pipeline), which does not rely on feature engineering, and is a data-driven method; however, there are many network variants and a large dependence on parameter settings. Poor explanatory

In addition, a disadvantage of this method is that the process of labeling each token is an independent classification, and the above-predicted labels cannot be directly used (only the above information can be transmitted by the hidden state), which leads to the predicted labels. The sequence may be illegal. For example, it is impossible to follow the label B-PER (BIO sequence labeling mode) followed by I-LOC (BIO sequence labeling mode), but Softmax (normalized exponential function) will not use this information

Images