... obvious way to learn these
grammars. In particular, learning procedures are
not able to take direct advantage of manually an-
notated corpora like the Penn Treebank, which are
not marked for derivations ... Proceedings of the ACL-IJCNLP 2009 Conference Short Papers, pages 45–48,
Suntec, Singapore, 4 August 2009.
c
2009 ACL and AFNLP
Bayesian Learning of a Tree Substitution Gr...
... a nutshell. We can train
this model using a two-dimensional extension of the
inside-outside algorithm on bilingual data, assuming
every phrase pair that can appear as a leaf in a parse
tree of ... 14627
gildea@cs.rochester.edu
Abstract
We combine the strengths of Bayesian mod-
eling and synchronous grammar in unsu-
pervised learning of basic translation phrase
pairs. The s...
... lack of automatic met-
ric that is capable to measure all the three criteria in
paraphrase generation. Two issues are also raised
in (Zhao and Wang, 2010) about using automatic
metrics: paraphrase ... two cri-
teria in paraphrase generation: adequacy measuring
the semantic equivalency and paraphrase rate mea-
suring the surface dissimilarity. As they are incom-
patible (Zhao and Wang, 2010)...
... Online Learning of Approximate Dependency Parsing Algorithms
Ryan McDonald Fernando Pereira
Department of Computer and Information Science
University of Pennsylvania
Philadelphia, PA 19104
{ryantm,pereira}@cis.upenn.edu
Abstract
In ... lead to state -of- the-art accuracy
for English and the best accuracy we know of for
Czech and Danish.
2 Maximum Spanning Tree Parsing
Dependency -...
... over a conventional Bayesian TSG
parser, and better than state -of- the-art discrim-
inative reranking parsers.
1 Introduction
Syntactic parsing has played a central role in natural
language processing. ... et al., 2010), rather than constituent
syntax parsing.
An all-fragments grammar (Bansal and Klein,
2010) is another variant of TSG that aims to uti-
lize all possible subtrees as rul...
... 1999).
Usually, entire documents are translated by humans,
and the sentence pairs are subsequently aligned by
automatic means. A small parallel corpus can be
available when native speakers and translators ... AlAst
$
Aryp
Task: stem AlAst
$
Aryp
Choices Score
AlAst$Aryp 0.2
AlAst$Aryp 0.7
AlAst$Aryp 0.8
AlAst$Aryp 0.1
.
.
.
.
.
.
Figure 3: Scoring the Stem
However, this approach has several...
... Structure and function of a regulated archaeal
triosephosphate isomerase adapted to high temperature.
J Mol Biol 342, 861–875.
12 Gayathri P, Banerjee M, Vijayalakshmi A, Azeez S,
Balaram H, Balaram ... mutations
Mousumi Banerjee
1
, Hemalatha Balaram
2
and Padmanabhan Balaram
1
1 Molecular Biophysics Unit, Indian Institute of Science, Bangalore, India
2 Molecular Biology and Genetics...
... M, Hasegawa K, Horita
C & Akera S (1999) A new matrix protein family
related to the nacreous layer formation of Pinctada
fucata. FEBS Lett 462, 225–229.
5 Kono M, Hayashi N & Samata T ... structure–function
relationship analysis of Prismalin–14 from the prismatic
layer of the Japanese pearl oyster, Pinctada fucata.
FEBS J 274, 5158–5166.
9 Murayama E, Takagi Y, Ohira T, Davis...
... absorption bands. Heme catabolism by
HOs of mammals, pathogenic bacteria, cyanobacteria
and probably insects is considered to have a similar
mechanism, because the characteristic absorption
bands of verdoheme ... T, Zhang X, Sun D,
Sato M, Sasahara M, Kayama T, Ikeda-Saito M &
Yoshida T (2000) Histidine 20, the crucial proximal
axial heme ligand of bacterial heme oxygenase Hmu O
f...
... 25% of the accessible
surface area of a monomer contributes to Ll
PDH
dimer formation. Whereas LlPDH and OaPDH have a
buried surface area of 5500 A
˚
2
, TbPDH has a larger
interface surface area ... suite: programs for protein crystallo-
graphy.
Acta Crystallogr D Biol Crystallogr 50, 760–763.
28 Navaza J (1994) Amore – an automated package for
molecular replacement. Acta Cry...