Data-to-text generation method based on fine-grained topic modeling

Abstract

The invention discloses a data-to-text generation method based on fine-grained topic modeling. The data-to-text generation method comprises the following steps: learning semantic representation of each data record on a coding layer based on a bidirectional long-short-term memory network; learning topic distribution corresponding to each data record and word distribution corresponding to each topicbased on a non-negative matrix factorization method to obtain a topic word table corresponding to each data record; based on the semantic representation of each data record in a decoding layer, carrying out text generation by utilizing a long-term and short-term memory network, an attention mechanism and fine-grained topic representation in combination with a topic word table; and performing model training to obtain an optimal text generation result. According to the method, topic distribution of data and word distribution corresponding to topics are mined by utilizing a non-negative matrix factorization method, so that topic consistency between a generated text and a data table is restrained, and a model is guided to learn a more accurate word use mode; a copying mechanism is introducedin the text generation process, and it is guaranteed that the model can accurately generate numerical description.

Description

technical field [0001] The invention relates to the field of computer application technology, in particular to a data-to-text generation method based on fine-grained topic modeling. Background technique [0002] With the development of information technology, industry data accumulated in various fields is growing rapidly, for example, financial statements accumulated in the financial field, live game data accumulated in the sports field, etc. In order to solve the problem of information overload brought by massive data, the task of data-to-text generation has attracted more and more attention from researchers. The data-to-text generation task aims to describe the main information contained in structured data in natural language, and then help people better grasp the specific meaning behind massive data. [0003] Early research work mainly split this task into three independent subtasks: content planning, sentence planning, and surface realization, and constructed a series o...

AI Technical Summary

Problems solved by technology

However, these models mainly rely on the neural network's own representation learning ability to improve the quality of the generated text, while ignoring the modeling of topical consistency between text and data.

Images