This is an old revision of the document!
Jacana word aligner
Slides accompanying the article are located at http://cs.jhu.edu/~xuchen/paper/yao-jacana-wordalign-acl2013.ppt
1/ Describe parameters of feature function in section 3.1
2/ Section 3.1 describes problem with unknown number of states.
For example, we have following source sentence: “Linda is married to Charles.”
Target sentence: “Charles likes his new role as the husband.”
And tags: NOUN, VERB, ADJ, ADV, PRON, DET, ADP, NUM, CONJ, PRT
How many states will be used?
3/ Search WordNet (http://wordnetweb.princeton.edu/perl/webwn) for following words and write answers:
a / Imagine, that source sentence countains word “well” and target “part”.
Find differences with incorporating POS tagger and without it. How big will be gain in number of comparisons (just roughly)?
b/ Is there a synset containing both “well” and “water” words?
4/ Have a look at Table 3. How big was gain from incorporating Wordnet with POS tagger? Would you use two external resources for this gain (refer discussion in section 4.6)?
5/ Why do you think, authors add Hamming distance into first formula in section 3.1. Can normalization function work without it?