Automatic metaphor rhetoric sentence analysis and judgment method based on part of speech, syntax and dictionary
A judgment method and automatic analysis technology, applied in natural language data processing, special data processing applications, instruments, etc., can solve problems such as inability to process metaphorical sentences, and achieve the effect of high degree of automation and high judgment accuracy.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0146] S1. Use the open source ICTCLAS program to perform word segmentation and part-of-speech tagging on the sentence "the surrounding mountains are like a continuous carpet". The result is:
[0147] Surrounding / part of speech: f; of / part of speech: ude1; mountains / part of speech: n; like / part of speech: v; one / part of speech: m; article / part of speech: q; rug / part of speech: n;
[0148] S2. Use Stanford Parser for syntax analysis, see the analysis results figure 2 ,according to figure 2 The syntax tree shown in , at this time, there are modifiers in the sentence: "surrounding", "a piece" and "continuously". After the sentence modifiers are deleted according to S2, the original sentence is reduced to: mountains are like carpets. Word segmentation and part-of-speech tagging are performed again, and the result is: mountains / part-of-speech: n image / part-of-speech: p; carpet / part-of-speech: n; at this time, the sentence has only two valid nouns, namely "mountains" and "carpet...
Embodiment 2
[0152] S1. Use the open-source ICTCLAS program to perform word segmentation and part-of-speech tagging on the sentence "spring breeze is like a colorful colored pen that outlines the whole world", and the result is: spring breeze / part of speech: n; image / part of speech: v; one / part of speech: m; branch / part of speech: q; put / part of speech: pba; whole / part of speech: b; world / part of speech: n; outline / part of speech: v; of / part of speech: ude1; colorful / part of speech: vl; ; hand / part of speech: n;
[0153] S2. Use Stanford Parser for syntax analysis, see the analysis results image 3 ,according to image 3 The syntax tree shown in ; at this time, according to step S2-1, delete the modifier "one pair"; according to step S-3-2, take "outline the whole world" as cp1, and there are nouns before and after it respectively " "spring breeze" and "hand", so delete "outlining the whole world", and the original sentence is reduced to: spring breeze is like colorful hands. Re-segment...
Embodiment 3
[0157] S1. Segment and part-of-speech the sentence "the devil sitting on the edge of the kang with green eyes like wolf eyes in the dark", the result is:
[0158] Kang Yan / Part of Speech: s; Up / Part of Speech: f; Sitting / Part of Speech: v; Author / Part of Speech: uzhe; De / Part of Speech: ude1; That / Part of Speech: rz; / part of speech: q; eye / part of speech: n; green / part of speech: a; of / part of speech: ude1; like / part of speech: p; :n; eye / part of speech:n;
[0159] S2. The sentence contains five nouns, and the sentence is analyzed syntactically using Stanford Parser. The analysis results are shown in Figure 4 ,according to Figure 4 The syntax tree shown in ; at this time, there are modifiers, such as "sitting on the edge of the kang", "that" and "in the dark night". After removing the modifiers according to the grammatical rules, the sentence is: The devil has green eyes like a wolf eye; Segment the sentence and tag the part of speech again, the result is as follows: gho...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com