Research Article
TSHD: Topic Segmentation Based on Headings Detection (Case Study: Resumes)
| (1) | Input | | (2) | RE: Refined Enumerate | | (3) | D: Headings Dictionary (the output of Algorithm 1) | | (4) | Output | | (5) | D after adding the unified headings with their locations | | (6) | for all (lineIndex, line) RE do | | (7) | words tokenization of line | | (8) | for all word words_list do | | (9) | stemming of word | | (10) | match it to CueWords_table | | (11) | if matches then | | (12) | get unifiedHeading | | (13) | record lineIndex | | (14) | if unifiedHeading others then | | (15) | if unifiedHeading D and lineIndex D then | | (16) | add {unifiedHeading: lineIndex} to D | | (17) | end if | | (18) | else | | (19) | if stem(word) D and lineIndex D then | | (20) | add {stem(word): lineIndex} to D | | (21) | end if | | (22) | end if | | (23) | else | | (24) | continue | | (25) | end if | | (26) | end for | | (27) | end for |
|
