Event Relation Extraction

Slide 1

Slide 1 text

1/10 1 2019/03/07 @izuna385 (event relation extraction)

Slide 2

Slide 2 text

2/10 vs • RSebe7K _ be;?Z D(Chambers, 2008 ACL) RSeZJd`^/6e>cKC \]9YBp (FX, NLP2015) 5%'1(2,MWShibata(2011,IJCNLP) 3 fQ7Lm;jIPMI"PU:@ n: 7L.#o!(Higashiyama, 2016) 8: Shibata,2011 IJCNLP iH"→O hE→G :@ tke.# rfQ<keqVl A! s Apriori Algorithm t T-02/(ke *$%,4e&),[! +2'&),) 340,000.#7Lmag"N= 2

Slide 3

Slide 3 text

3/10 !#+ -', ) • (NLP2011) LifeNet data ( Temporal("-.) & / 0 *-. / %.$

Slide 4

Slide 4 text

4/10 BDT ( • %(NLP, 2008) ]7A&=Y85 "#@H →,1 Z,&= I+V+*> ^[→-6 ,1 4FZ, 9P 2Q< • `J(HLT-NAACL, 2006) .C3SKL&=YZ,?/ →0OWT \aNb!$#_→ aNbX • E:(';MQ9), 2016) RUG

Slide 5

Slide 5 text

5/10 DEY Higashiyama 2017 • F8(+9QU6,, 2016) \2^(IEEE,2017) PMI: )?%0Z WY$#('→WY$#('0Z )?% 1;O7S PMI )?7S0ZRM[B7S 2016<Web!($"2017IDCTCorpus-N /4 VGCabocha X.20173A:)?%L=PO+@ &*HK>]NJ20165

Slide 6

Slide 6 text

6/10 or • Kayesh(arxiv,2019) Preprocess + WordVec emb layer feature extraction NN Train+test 500

Slide 7

Slide 7 text

7/10 I3(Deep$M) • #7KAF 0C given /J9; → 2F(Common Sense)?5P given >*189;NFAQO → "H ?5P '(L% :K@NTemporal relation, )4L%O -

Slide 8

Slide 8 text

8/10 " (Deep$) • ! Improving Event Causality Recognition with Multiple Background Knowledge Sources Using Multi- Column Convolutional Neural Networks (AAAI2017) • Embedding + #→ Relation Classification % !&