Download presentation

Presentation is loading. Please wait.

Published byKristen Hush Modified over 2 years ago

1
Center for PersonKommunikation P.1 N-grams Sentence: S = w1 w2... wQ Ideal sentence probability: P(S) = P(w1 w2... wQ)= P(w1)P(w2|w1)P(w3|w1 w2)...P(wQ|w1 w2...wQ-1) Approximate conditional word probability: P(wQ|w1 w2... wQ-1) p(wQ|wQ-N+1... wQ-1) - where N has a constant “windowing” size: Unigram (N=1), Bigram (N=2), Trigram (N=3)

2
Center for PersonKommunikation P.2 Trigram smoothing (Jellinek) Used when there are insufficient data for real trigrams P(w3|w1 w2)= p1 F(w1,w2,w3) + p2 F(w1,w2) + p3 F(w1) F(w1, w2) F(w1) F(wi) Where: F is number of occurences of the string in its argument F(wi) is the number of words in corpus p1, p2, p3 are positive values and p1+p2+p3=1

3
Center for PersonKommunikation P.3 Clustering words in N-grams N-grams of word classes, categorical N-grams: –Words are “replaced” by (semantic, syntactic) categories before training. (e.g. “w_day” for Monday, Tuesday...) Data-driven clustering

4
Center for PersonKommunikation P.4 N-gram problems Long distance dependencies exceeding n: [kommoden/bordet/stolene] i værelset på tredje etage skal males [rød, rødt, røde] Stochastic grammars “freezes” human verbal behaviour at a state reflected in the training data. The verbal behaviour may change. Adaptive approach? Finding corpora reflecting how humans will communicate with the final system –(Human-human dialogs vs. WOZ-experiments).

Similar presentations

© 2017 SlidePlayer.com Inc.

All rights reserved.

Ads by Google