Tài liệu Báo cáo khoa học: "k-best Spanning Tree Parsing" pptx
Tài liệu Báo cáo khoa học: "Fine-grained Tree-to-String Translation Rule Extraction" docx
... Work
2.1 Tree- to-string and string-to -tree
translations
Tree- to-string translation (Liu et al., 2006; Huang
et al., 2006) first uses a parser to parse a source
sentence into a 1-best tree and ...
parsing
Bottom-up
decoding
tree- to-string
string-to -tree
Figure 1: Illustration of the training and decod-
ing processes for tree- to-string and string-to -tree
translations.
f
J...
Tài liệu Báo cáo khoa học: "Accurate Context-Free Parsing with Combinatory Categorial Grammar" pptx
... corpus of CCG derivations that was semi-
automatically converted from the Wall Street Jour-
nal section of the Penn treebank. Figure 2 shows
a categorization of the rules used in CCGbank ac-
cording ... parse trees as a whole, we
evaluate the categories assigned to words. In the
supertagging literature, POS tagging and supertag-
ging are distinguished – POS tags are the tradi-
tional Penn tre...
Tài liệu Báo cáo khoa học: "Shift-Reduce CCG Parsing" docx
... in-
cluding those consisting of grammatical relations
(Clark and Curran, 2007), Penn Treebank phrase-
structure trees (Clark and Curran, 2009), and un-
bounded dependencies (Rimell et al., 2009).
The ... English is CCGbank (Hockenmaier
and Steedman, 2007), a version of the Penn Tree-
bank in which each phrase-structure tree has been
transformed into a normal-form CCG derivation.
There are...
Tài liệu Báo cáo khoa học: "Non-Projective Dependency Parsing in Expected Linear Time" pptx
... non-projective
dependency trees, as illustrated in Figure 1. In a
projective dependency tree, the yield of every sub-
tree is a contiguous substring of the sentence. This
is not the case for the tree in Figure ... pro-
duce a tree with root 0.
For completeness, we note first that projectiv-
ity is not a property of a dependency tree in itself,
but of the tree in combination with a w...
Tài liệu Báo cáo khoa học: "Quadratic-Time Dependency Parsing for Machine Translation" pdf
... non-projective
tree is any tree that does not satisfy the following
definition of a projective tree:
Definition. Let x = x
1
·· ·x
n
be an input sentence,
and let y be a rooted tree represented ... eliminated, the algorithm
maps back the maximum spanning tree of the con-
tracted graph onto the original graph G, and it can
be shown that this yields a spanning tree that is op-
tim...
Tài liệu Báo cáo khoa học: "Hidden Markov Tree Model in Dependency-based Machine Translation∗" pptx
... is that
the independence assumptions made by Markov
Tree Models can be useful for modeling syntactic
trees. Especially, they fit dependency trees well,
because these models assume conditional ... de-
pendency trees. Moreover, analogously to applica-
tions of HMM on sequence labeling, HMTM can
be used for labeling nodes of a dependency tree,
interpreted as revealing the hidden states
1
in t...
Tài liệu Báo cáo khoa học: "Fast Unsupervised Incremental Parsing" pdf
... to having
depth 0 or 1. This restriction means that any tree
represented by a shortest common cover link set will
be skewed - every subtree must have a short branch.
It seems that this is indeed ... tested the incremental parser on the Chinese Tree-
bank version 5.0, achieving an F
1
score of 54.6 on CTB10 and
38.0 on CTB40. Because this version of the treebank is newer
and clearly differ...
Tài liệu Báo cáo khoa học: "Pseudo-Projective Dependency Parsing" doc
... (2003).
This is in contrast to dependency treebanks, e.g.
Prague Dependency Treebank (Haji
ˇ
c et al., 2001b),
Danish Dependency Treebank (Kromann, 2003),
and the METU Treebank of Turkish (Oflazer et al.,
2003), ... the
Prague Dependency Treebank and the Danish De-
pendency Treebank. In section 5, we then evaluate
the entire parsing system by training and evaluating
on data from the Prague Dep...
Tài liệu Báo cáo khoa học: "Fragments and Text Categorization" pptx
... tasks are Accom-
pagnements vs. Cremes, Cremes vs. Pates-Pains-
Crepes, Desserts vs. Douceurs, Entrees vs. Plats-
Chauds and Pates-Pains-Crepes vs. Sauces, among
others.
We also used both methods ... the best re-
sults. We utilized three learning algorithms from the
Weka
4
system – the decision tree learner J48, the
Na¨ıve Bayes, the SVM Sequential Minimal Opti-
mization (SMO). All the algo...