A Word-Complexity Lexicon and A Neural Readability Ranking Model for Lexical Simplification

弊研究室で行なったEMNLP2018読み会の発表資料です。

Transcript

1. EMNLP
    A Word-Complexity Lexicon and A Neural Readability Ranking Model 2018/12/18 M1 
2.  • 2  • 15000
    • SimplePPDB++ 2
3. 3 Complex Sentence The cat perched on the mat. Substitution Generation perched : rested, sat Substitution Ranking #1 : sat, #2 : rested Complex Word Identification The cat perched on the mat. Simplification Sentence The cat sat on the mat.
4. $,52(% *60#94
    -):3 • 60 • 
    $;!  '  .  • foolishness7 vs folly1 • 60 foolishness  • Google Ngram Corpus foolishness/;! • PPDB"&2272 • 21%60 8160 • 14%/;! 760 4 +2
5. - • Google Ngram Corpus • Wo 15000 • 11 L • 6 5 6 • e p bug n d • C Wo c • 1000 i 2-2.5h • 1 5-7 L • m l 5
6. - C 2 • 3% • L 0.55 → 0.64 • • ≦0.5 47% • ≦1.0 78% • ≦1.5 93% 6
7.     
    2 7
8.        • ,/+*23.0! • SemEval2012$! "% • )-2*15Candidates • $! "% • %'&(30Target300Candidate • #% 171Target1710Candidate 8 TEXT When you think about it, that’s pretty terrible. Target terrible Candidates bad, awful, deplorable
9. 9 P@1 1 S all binning WC R 15000
10. • PPDB P Ranking model • PPDB • • • + + + • PPDB D • 10B S 10
11. + 11 SimplePPDB++
12. Target Candidate • 100 Target Candidate • 2 • Candidate G • SimplePPDB++ 12
13.          13 • n Target • PPs Candidate • MAP Candidate • P@1 Top1
14. I • SemEval2016 CWIG3G2 • C WC 14
15. 
             15
16.  • 2'"#( &   • SOTA% • 15000'"#( 
     • 
    !*$  CWI) • SimplePPDB++ 16