... Johnson,
2003). Language modeling for speech could well be
the first real problem for which syntactic techniques
are useful.
John ate the pizza on a plate with a fork .
NP:plate
NP:fork
PP:withPP:on
IN
IN
VB
NP
VP:ate
Figure ... Edges for
Unused Words
Is Agenda
Empty?
no
Continue
Multi-stage
Parsing
yes
PCFG
Word-lattice
Parser
Figure 5: Attention shifting parser.
Figure 5 depict...
... of log-
linear models for defining probability distributions
over the parses of a unification grammar. Un-
fortunately, the maximum likelihood estimator Ab-
ney proposed for SUBGs seems computationally ... Proceedings of the 40th Annual Meeting of the Association for
pus. For most linguistically realistic grammars this
set is finite, and for moderate sized grammars and
training corpora...
... kernel for
phrase grammar parse trees and for depen-
dency parse trees outperforms all known
tree kernel approaches alone suggesting
that both types of trees contain comple-
mentary information for ... dependency
parse tree kernel outperforms all others by 5.7%
F-Measure reaching an F-Measure of 71.2%. This
result shows that both types of parse trees contain
relevant information for r...
... Analysis
To use the DOP method not just for syntactic anal-
ysis, but also for semantic interpretation, four steps
must be taken:
1. decide on a formalism for representing the
meanings of sentences ... enough for repre-
senting the meanings of sentences and constituents
that are relevant for the intended application do-
main. For our exposition in this paper we will
use a...
... using some information of parsing re-
sults. However, as the approach runs somewhat in
a reverse direction to ours, we omit it from the dis-
cussion. Hence, this paper will seek for the meth-
ods ... sentence, f denotes a foreign sentence,
and S
X
denotes cumulative X-gram scores. For 3-
gram scores, the tendency to separate in two clus-
ters is slightly decreased. Furthermore, for 1-...
... "dictionary" for the LSP. This
dictionary need only contain part-
of -speech information for all the words
that will be used in definitions; other
information such as part- of -speech
subclass ...
decide whether to modify the entry for
that sense or create a new
entry
for a new
sense.
3. Part of speech, or "class." Our
classification of parts of spee...
... measures. Using the
addition rule for probabilities we get the following
formula for a disjunction of two clues:
P(ai U a2) =
P(ai)
P(a2) —
P(al
n
a2)
For simplicity, we assume that clues ... phrase
type labels bear much less information about spe-
cific words and phrases than POS tags, therefore,
a lower weight of 0.1 was chosen for these two
clues.
5.2 The results
For the eva...
... goto function for LR(0) parsing is defined by
goto(q,x) =
closure({[A * aX •/3] I [A ~ a • X/3] E Q})
For ELR parsing however, we need two goto func-
tions, goto I and goto2, one for kernel ... tabular form of CP parsing,
since this is the most simple parsing technique discussed
above. We will then move on to the more difficult ELR
technique. Tabular PLR parsing is fairly...
... printing devices, then the
above transformation is effected by a single-
state machine.
A word -for- word translation in which the
equivalents selected for an input word depend
upon the context ... transforma-
tion, called "conditional" is effected by the
rules:
A Model for MT 3
where r = 1, 2
We suppose that the
sequence of rules provides a course of action
fo...
... Association for Computational Linguistics, pages 497–505,
Jeju, Republic of Korea, 8-14 July 2012.
c
2012 Association for Computational Linguistics
Dependency Hashing for n-best CCG Parsing
Dominick ... supertagging, on parsing accuracy.
1 Introduction
Reranking techniques are commonly used for im-
proving the accuracy of parsing (Charniak and John-
son, 2005). Efficient decodin...