... Linguistics
A Comparison of Loopy Belief Propagation and Dual Decomposition for
Integrated CCG Supertagging and Parsing
Michael Auli
School of Informatics
University of Edinburgh
m.auli@sms.ed.ac.uk
Adam ... su-
pertagger and parser, which are then combined us-
ing belief propagation (BP) and dual decomposition
(DD). We run the algorithms for many i...
...
policy, an agreement of 92.8% was achieved
among annotators for the set of start and stop
locations for arguments. Examples of semantic
role annotations in our corpus for each of the
four predicates ... comparative performance
of the parse tree paths for each of the five encod-
ings, we divided the corpus in to equal-sized
training and test sets (50 training and...
... Zens and Ney (2003) explore
the re-orderings allowed by ITGs, and provide a
formulation for the number of structures that can
be built for a sentence pair of size n. ITGs explore
almost all of ... 1)!]
permutations for a given tree, where θ stands for a
head node in the tree, and m
θ
counts θ’s m odifiers.
Dependency space is not a subspace of ITG space,
as it can create...
... processing of
different grammatical formalisms. At the same time
it is of course a natural test bed for experiments with
various control strategies.
Previously a number of comparisons of rule- ... conditions for and ways
of predicting new edges 4. This section will therefore
in effect constitute a survey of different methods for
predicting new edges.
2.1 Top-Down St...
... ISF and ITF values are 5.5
and 10.4 higher than IDF. All language
models appeared to follow a power law
distribution with a slope coefficient of
1.6 for documents and 1.7 for sentences
and ...
This comparison reflects a previous analysis
comprising a random sample of 193 words from
a 50 million word corpus of 85,432 news articles
(Church and Gale 1999). Church an...
... only and exclude gen-
eration of basic Stanford dependencies (for constituent parsers) and part -of- speech tagging (for dependency parsers).
3 Results
Table 3 tabulates efficiency and performance for ... 3: Performance and efficiency for all parsers on CTB data: unlabeled and labeled attachment scores (UAS/LAS)
are for both development and test data sets; parsing times (m...
... entire
derivation.
Selection of a pair of dependent words w I and
v ~ and transducer M I given head words w and v
and source and target dependency relations el
and r2.
(w,w' E V1; v,v' ... and Development Effort
The performance comparison above is, of course, not
the whole story, particularly since manual effort was
required to build the model structures...
... the
document.
From a linguistic point of view, a document is
made up of words, and the semantics of the doc-
ument is determined by the meaning of the words
and the linguistic structure of the document. The
Naive ... cases, precision and recall were differ-
ent over the entire range of the number of selected
words. In these cases we give the recall and accu-
racy for t...
...
involve the generation of pro-forms instead of, or in addi-
tion to, the ellipsis proper. For example, John laughed, and
Mary did, too—a case of VP Ellipsis—includes the pro-
form did. Nor do we ... form of a non-finite complement
3
For lack of space, here we cannot go into aspects of word-
order variation (both Estonian and German are languages
with relatively fre...
... b
1
and b
2
stand for the two bigrams and
w stands for any word containing both of them.
The overall information quantity is obtained by
subtracting the redundancy between each pair of
bigrams ...
4.2 Overall Information Quantity of a Fea-
ture Space
The performance limit of a classification is re-
lated to the quantity of information used. So a
quantitative metric...