A Question Answering Method Based on Hierarchical Memory Network
A layered and memorized technology, applied in instrumentation, computing, semantic analysis, etc., can solve problems such as inability to select accurate user information, and achieve the effect of solving the problem of answer selection, improving efficiency, and reducing the amount of calculation.
Active Publication Date: 2019-08-23
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0010] Assuming that "Williamson", "577838771" and "0016178290851" are low-frequency words or unregistered words, if traditional methods discard these words or replace them with "unk" symbols, these methods cannot select accurate words from the dialogue text. User information for
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0029] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.
[0030] The invention discloses a question answering method based on a hierarchical memory network, which is based on an end-to-end model of a full neural network structure, which can realize information reasoning, screening and word granularity selection in sentence sets, and effectively solve question and answer under big data The system selects questions for answers to low-frequency words or unregistered words. The question answering method of the present invention performs two hierarchical memory coding for sentence sets with time sequence information, respectively: sentence granularity memory coding and word granularity memory coding. Then based on the hierarchical memory network for information reasoning, screening...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides a Q&A method based on a hierarchal memory network. The method comprises the following steps: firstly performing sentence granularity memory encoding, and finishing the information inference of the sentence granularity memory unit through an attention mechanism in multi-rounds of iterations under the stimulation of the problem semantic encoding, screening the sentence through k maximum sampling, and further performing the word granularity memory encoding on the basis of the sentence granularity encoding, namely, performing the memory encoding on two levels to form the hierarchal memory encoding; the output word probability distribution is predicted through the combination of the sentence granularity memory unit and the word granularity memory unit, the accuracy of the automatic Q&A is improved, and the answer selection problem of low-frequency word and unlisted word is effectively solved.
Description
Technical field [0001] The invention relates to the technical field of automatic question answering system construction, and more specifically to an end-to-end question answering method based on a hierarchical memory network. Background technique [0002] For a long time, automatic question answering has been one of the most challenging tasks in natural language processing problems. This task requires a deep understanding of the text and selection of candidate answers as a system response. The existing traditional methods include: using pipeline mode to independently train each module in the text processing process, and then fusing the output mode; constructing a large-scale structured knowledge base, and based on this knowledge base for information reasoning and answer prediction. In recent years, end-to-end systems based on deep learning methods have been widely used to solve various tasks. These methods do not require manual feature construction and individual tuning of each m...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/332G06F17/27
CPCG06F16/3329G06F40/30
Inventor 许家铭石晶姚轶群徐波
Owner INST OF AUTOMATION CHINESE ACAD OF SCI