Automatic composition evaluation method and device based on chapter component recognition and storage medium
A composition and text technology, applied in the field of text processing, can solve the problems of insufficient Chinese composition research, neglect of composition scoring, and inability to realize automatic composition evaluation, and achieve the effect of automatic evaluation.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0053] figure 1 It is a schematic flow chart of an automatic composition evaluation method based on discourse component recognition in an embodiment of the present application, such as figure 1 As shown, the composition automatic evaluation method based on discourse component recognition of the present embodiment includes:
[0054] S10. Acquiring a target composition for evaluation, which is a character-like Chinese narrative composition;
[0055] S20. Input the target composition into the pre-trained discourse component recognition model to obtain the discourse component recognition result; wherein, the discourse component recognition model is a Chinese narrative style composition that marks the structure of the paragraph as a training sample, and the two-way fusion attention mechanism A classification model trained by Bi-directional Long Short-Term Memory (BiLSTM);
[0056] S30. Input the target composition and the recognition results of the text components into the pre-tr...
Embodiment 2
[0094] On the basis of the above-mentioned embodiments, this embodiment specifically describes the structures of the discourse component identification model and the discourse structure rationality evaluation model that can be used. figure 2 It is a structural schematic diagram of a text component identification model and a text structure rationality evaluation model in another embodiment of the present application. Such as figure 2 As shown, the left part is the text component recognition model, and the right part is the text structure rationality evaluation model. The discourse component recognition part is to assign the integrated discourse component labels to m paragraphs in the corpus P=P 1 , P 2 ,...,P m ; The text structure rationality model is based on the results of the fusion of text components, and scores S for the articles in the corpus, S ∈ {excellent, good, medium, poor}.
[0095] The text component recognition model adopts the form of BiLSTM fusion attenti...
Embodiment 3
[0128] The second aspect of the present application provides an electronic device through Embodiment 3, including: a memory, a processor, and a computer program stored in the memory and operable on the processor. When the computer program is executed by the processor, the above embodiments are implemented. The steps of any one of the automatic composition evaluation methods based on discourse component recognition.
[0129] image 3 It is a schematic structural diagram of an electronic device in another embodiment of the present application.
[0130] image 3 The illustrated electronic device may include: at least one processor 101 , at least one memory 102 , at least one network interface 104 and other user interfaces 103 . Various components in the electronic device are coupled together through the bus system 105 . It can be understood that the bus system 105 is used to realize connection and communication between these components. In addition to the data bus, the bus sy...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More