3.3 Probabilistic Topic Model
sim
LDA2
(D
i
, D
j
) = 10
W
(ˆ
θ
(
Di
)
,
θ
ˆ
(
Dj
)
)
Celikyilmaz et al. (2010) presented probabilistic
topic model based methods to measure the similar-
where θ ˆ
(D
i
)
is document D
i
’s probability distribu-
ity between question and candidate answers. The
candidate answers were ranked based on the hidden
tion of topics as defined earlier.
4 Information Need Prediction using
P r(f, a|e). For different alignment models differ-
Statistical Machine Translation Model
ent approaches were proposed to estimate the cor-
responding alignments and parameters. The detail-
There are two reasons that we need to predict in-
s can be found in (Och et al., 2003; Brown et al.,
formation need. It is often the case that the query
Bạn đang xem 3. - BÁO CÁO KHOA HỌC: "IMPROVING QUESTION RECOMMENDATION BY EXPLOITING INFORMATION NEED" PPTX