... 105–108,
Columbus, Ohio, USA, June 2008.
c
2008 Association for Computational Linguistics
A Unified Syntactic Model for Parsing Fluent and Disfluent Speech
∗
Tim Miller
University of Minnesota
tmill@cs.umn.edu
William ... using the mrg annotations
in directories 2 and 3 for training, and the files
sw4004.mrg to sw4153.mrg in directory 4 for evalu-
ation, following John...
... Marton and
Resnik, 2008; Cherry, 2008), our SDB model has
2
Here we expand the definition of phrase to include both
syntactic and non -syntactic phrases.
the following advantages
• The SDB model ... Experimental results and analy-
sis show that the new model outperforms
other previous methods and achieves a
substantial improvement over the baseline
which is not syntactically i...
... relaxed
and creative writing style and the frequent use of
unconventional and not yet standardized short-
forms. Direct modeling of these special phenom-
ena in MT requires tremendous effort. ... 1966), specific word set confusions (Gold-
ing and Roth, 1999) and pronunciation modeling
(Brill and Moore, 2000; Toutanova and Moore,
2002). These models are mostly character-based...
... identity
with the TRs from E. coli and Aeropyrum pernix (31%
and 34%, respectively), and possesses conserved motifs
responsible for the binding of FAD (GXGXXA and
GXFAAGD) and the binding of NADPH
(GXGXXA), ... ampicillin at 37 °CuptoanD
600
of
1.0, and FNR expression was induced by treatment with
1.0 mm IPTG for 5 h at 37 °C. Cells were harvested by cen-
trifugation at 5000 g...
... S(1) and S(2) or not.
4 Last action given by the classifier, and number of words in S(1) and S(2).
5 Headword and its POS of S(1), S(2), S(3) and S(4), and word and POS of Q(1), Q(2), Q(3) and ... similar model to
the BBN’s model in (Bikel and Chiang, 2000),
and augmented the model by semantic categori-
cal information and heuristic rules. They achieved
LR/LP of 78....
... kernels, more and more
kernels for restricted syntaxes or specific do-
mains, such as string kernel for text categoriza-
tion (Lodhi et al., 2002), tree kernel for syntactic
parsing (Collins and Duffy, ... Predicate Argument Feature space
necessity of syntactic parsing for semantic role la-
beling. However, the standard flat features cannot
model the syntactic informatio...
... since
x
is fixed during training and decod-
ing, and we assume that the model is fully identified
during decoding. This is for clarity only and does not
limit the class of models, though we will introduce
additional, ... Jansche,
2005). More specialized methods also exist, for ex-
ample for support vector machines (Musicant et al.,
2003) and for conditional random fields (Gross...
... accumul-
ation and computes the
Distractors
and all evalu-
ation properties accordingly. The property
Next-
prop
is the first non-category atomic descriptor
for successors of the root node. For successors ... referent(s).
Several algorithms have been developed for
this purpose, differing in terms of computational
efficiency, quality and coverage. For identifying
sets of objec...
... this data
and re-package it for their own needs, these being
informative, educational and entertainment ones.
Understanding and generation of multimedia dis-
course requires knowledge and skills ... devel-
oped for the exploration and the automatic expan-
sion/generalisation of the annotated semantic rela-
tions. This search interface is a support tool for
the theory and the...
...
Uk and vk often co-occur, as do uk and
uk+z. The direct association between uk and vk, and
the direct association between uk and Uk+l give rise
to an indirect association between v~ and uk+l. ... can be extrinsic to the model (Melamed, 1995;
Melamed, 1997).
3 The Basic Word-to-Word Model
Our translation model consists of the hidden param-
eters A + and A-, and li...