Causal relation extraction using cue phrase and lexical pair probabilities

This work aims to extract causal relations that exist between two events expressed by noun phrases or sentences. The previous works for the causality made use of causal patterns such as causal verbs. We concentrate on the information obtained from other causal event pairs. If two event pairs share some lexical pairs and one of them is revealed to be causally related, the causal probability of another event pair tends to increase. We introduce the lexical pair probability and the cue phrase probability. These probabilities are learned from raw corpus in unsupervised manner. With these probabilities and the Naive Bayes classifier, we try to resolve the causal relation extraction problem. Our inter-NP causal relation extraction shows the precision of 81.29%, that is 7.05% improvement over the baseline model. The proposed models are also applied to inter-sentence causal relation extraction.
Publisher
SPRINGER-VERLAG BERLIN
Issue Date
2005
Language
ENG
Citation

NATURAL LANGUAGE PROCESSING - IJCNLP 2004 BOOK SERIES: LECTURE NOTES IN COMPUTER SCIENCE, v.3248, pp.61-70

ISBN
978-3-540-24475-2; 978-3-540-24475-2
ISSN
0302-9743
URI
http://hdl.handle.net/10203/3579
Appears in Collection
CS-Journal Papers(저널논문)
Files in This Item
Causal Relation Extraction Using Cue Phrase and Lexical Pair Probabilities.pdf(249.23 kB)Download
  • Hit : 449
  • Download : 564
  • Cited 0 times in thomson ci
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡClick to seewebofscience_button
⊙ Cited 3 items in WoSClick to see citing articles inrecords_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0