... Generating with a Grammar Based on Tree Descriptions: a
Constraint -Based Approach
Claire Gardent
CNRS
LORIA, BP 239 Campus Scientifique
54506 Vandoeuvre-les-Nancy, France
claire.gardent@loria.fr
Stefan ... differences with
the more traditional generative approach usually
pursued in tactical generation and further, that the
combination of this static view with a TAG-like...
... Disambiguation based on Semantic Correspondence
Lea Frermann
Department of Computational Linguistics
Saarland University
frermann@coli.uni-saarland.de
Francis Bond
Linguistics and Multilingual ... other language.
In particular, we select one language as the tar-
get language, translate the other language’s seman-
tics for every parse into the target language and thus
align maximally simil...
... Prediction
In addition, we take a more general statistical
approach to capture the cross-event relations and
predict unknown time arguments. We manually
labeled some ACE data and trained a Maximum ... include any
time arguments. We then manually labeled
“Propagate/Not-Propagate” for each sample. The
annotation for both training and test sets took one
human annotator about 10 hours...
... Asn77 of chain B, then Asn77 of chain A is
close to Ala25 of chain B.
Chain A Chain B Hydrogen bonds
Ala25 Asn77, Arg80 AlaO–ArgNH1
AlaO–ArgND2
Asn26 His35, Arg80, Asn39 AsnOD1–ArgNH1
AsnOD1–HisNE2
Ser28 ... in detail, as it diffracts to a
Table 1. Statistics on data collection and refinement. A wavelength of 0.8726 A
˚
was used. Rotations of 1° were performed. The Ramachan-
dran p...
... 14114–14121.
23 Paulucci AA, Katsuyama AM, Sonsa AD & Farah CS
(2004) A specific C-terminal deletion in tropomyosin
results in a stronger head–to–tail interaction and
increased polymerization. Eur ... under the
same conditions and at the same heating rate as the DSC
experiments. Scattering of F-actin solutions containing the
same concentration of actin as in the Tm–F-actin samples
was...
... annotated for song titles and song
features. Feature annotation consists of marking
a phrase as a feature and matching it with the song
to which the feature is attributed. Note that we
have no a ... natural
language parsing. In Advances in Neural Informa-
tion Processing Systems 15, pages 3–10.
Susan McRoy, Songsak Ukul, and Syed Ali. 2003. An
augmented template -based approach to te...
... paper and its citation contexts in a literature
collection with consideration of citation autority and
proximity.
To evaluate impact summarization, we created a
test set based on ACM SIGIR papers. ... based on which all summaries generated by
the system are evaluated. This data set is available at
http://timan.cs.uiuc.edu/data/impact.html. We must
admit that using only 14 papers...
... Siddharthan & Ann Copestake
Natural Language and Information Processing Group
Computer Laboratory, University of Cambridge
{as372,aac10}@cl.cam.ac.uk
Abstract
We describe an application that ... Visualisation of Collaborations of
ARG Group; zoomed into Europe and having clicked on
Catonia (Italy) for a popup summary
each location on. The space constraints are dic-
tated by the interf...
... labeled data.
While labeled data are difficult to obtain,
unlabeled data are readily available and plentiful.
Therefore, this paper advocates using a
bootstrapping framework and a feature projection ... is also a
difficult task to create training data for each
application area (Nigam et al., 1998). In this light,
we consider learning algorithms that do not require
such a large...
... representation or query languages.
Elsewhere (Evans and Power, 2003) we have
described a library package for developing
Wysiwym applications. This package was a
consolidation of work carried out in a series ... aspirin
modality
the pa tient may take an aspir in
the pa tient must take an aspirin
the pa tient might take an aspirin
the pa tient should take an aspirin
modifier
the pa tient...