... Michigan, June 2005.
c
2005 Association for Computational Linguistics
American Sign Language Generation:
Multimodal NLG with Multiple Linguistic Channels
Matt Huenerfauth
Computer and Information ... for a deaf user.
2 ASL NLG: A Form of Multimodal NLG
NLG researchers think of communication signals
in a variety of ways: some as a written text, other
as speech au...
... paper describes a software demo
integrating Natural Language Genera-
tion (NLG) techniques with recent de-
velopments in XML web technology.
The NLG techniques include a form of
template-based generation, ... software demo based
on this approach, showing a concrete example.
2 Brief Summary of NLG
The most common design for NLG systems is a
pipeline architecture. The version describe...
... with a comparison of in-
grammar recognition performance.
3 Language modelling
To generate the different trigram language models
we used the SRI language modelling toolkit (Stol-
cke, 2002) with ... the
same language as the Nuance grammar, gives such
an important gain in performance that it lowers
the WER with 22%. We used the Chi-square test
of significance to statistically comp...
... domains,
given appropriate linguistic and semantic
resources.
1 Introduction
The task of a cross -language information re-
trieval (CUR) system is to match user queries
specified in one language against ... information that the retrieval system is us-
ing. Crossing the language barrier from a query
in one language to the document collection in
another language is done via concept c...
... Computational Linguistics, pages 315–324,
Avignon, France, April 23 - 27 2012.
c
2012 Association for Computational Linguistics
Extending the Entity-based Coherence Model with Multiple Ranks
Vanessa ... experiment with the
stratified option, in which C ranks are assigned to
the permutations generated from the same source
document. The permutation with the smallest dis-
similarity scor...
... showed that the induction
time, s, with BzCh as substrate was much shorter than with
NMIA [16]. Moreover, with NMIA and BuSCh, it was
found that s increased with decreasing pH [25]. Therefore,
to ... Indeed, with BuSCh, deacylation is partly rate
limiting for wild-type and fully rate-limiting for D70G [37].
With BzSCh, k
cat
is much lower than k
cat
for BzCh (18-fold
with wild-t...
... Computational Linguistics, pages 568–575,
Prague, Czech Republic, June 2007.
c
2007 Association for Computational Linguistics
Improving the Interpretation of Noun Phrases with Cross -linguistic
Information
Roxana ... constructions of
the form N P N in Romance languages where, as
we will show below, the P (preposition) varies in
ways that correlate with the semantics. Thus Ro-
mance lang...
... on
production accuracy in experiments with speakers
with AOS and speakers with conduction aphasia.
3.2 Implications on motor learning
In that view, practicing with high-frequency sylla-
bles could ... community. Existing applications for
selecting linguistic stimuli, although undoubtedly
useful, are not based on spoken language data,
and are generally not designed for utilization...
... constructs new hypotheses by extend-
ing existing hypotheses. New hypotheses are placed
in appropriate hypothesis stacks. In the simplest
case, a new hypothesis extends an existing hypothe-
sis by ... phrase-based translation lat-
tice. Within each decoder stack t, each hypothe-
sis h is augmented with a syntactic language model
state ˜τ
t
h
. Each syntactic language model state is
a ra...
... Viterbi-style PCFG
parser, together with a suite of bottom-up
probabilistic chart parsers.
4 Teaching with NLTK
Natural language processing is often taught within
the confines of a single-semester ... USA
Abstract
The Natural Language Toolkit is a suite of
program modules, data sets and tutorials
supporting research and teaching in com-
putational linguistics and natural language
pro...