|
concatenation languages [ RCL ]
</term>
can be parsed
|
in
|
<term>
polynomial time
</term>
and many classical
|
#1633
In particular, range concatenation languages [RCL] can be parsed in polynomial time and many classical grammatical formalisms can be translated into equivalent RCGs without increasing their worst-case parsing time complexity. |
|
tree adjoining grammar
</term>
can be parsed
|
in
|
<term>
O ( n6 ) time
</term>
. In this paper
|
#1672
For example, after translation into an equivalent RCG, any tree adjoining grammar can be parsed in O(n6) time. |
|
<term>
words
</term>
appear frequently enough
|
in
|
<term>
dialog
</term>
to warrant serious
<term>
|
#1851
These words appear frequently enough in dialog to warrant serious attention, yet present natural language search engines perform poorly on queries containing them. |
|
</term>
) , a
<term>
parsing-as-deduction
</term>
|
in
|
a
<term>
resource sensitive logic
</term>
,
|
#1969
Our logical definition leads to a neat relation to categorial grammar, (yielding a treatment of Montague semantics), a parsing-as-deductionin a resource sensitive logic, and a learning algorithm from structured data (based on a typing-algorithm and type-unification). |
|
success of
<term>
ensemble methods
</term>
|
in
|
<term>
machine learning
</term>
and other areas
|
#2313
Motivated by the success of ensemble methodsin machine learning and other areas of natural language processing, we developed a multi-strategy and multi-source approach to question answering which is based on combining the results from different answering agents searching for answers in multiple corpora. |
|
</term>
searching for
<term>
answers
</term>
|
in
|
multiple
<term>
corpora
</term>
. The
<term>
|
#2348
Motivated by the success of ensemble methods in machine learning and other areas of natural language processing, we developed a multi-strategy and multi-source approach to question answering which is based on combining the results from different answering agents searching for answersin multiple corpora. |
|
improvement over our
<term>
baseline system
</term>
|
in
|
the number of
<term>
questions correctly
|
#2415
Experiments evaluating the effectiveness of our answer resolution algorithm show a 35.0% relative improvement over our baseline systemin the number of questions correctly answered, and a 32.8% improvement according to the average precision metric. |
|
speech recognition hypotheses ( SRH )
</term>
|
in
|
terms of their
<term>
semantic coherence
</term>
|
#2472
We apply our system to the task of scoring alternative speech recognition hypotheses (SRH)in terms of their semantic coherence. |
|
that , it successfully classifies 73.2 %
|
in
|
a
<term>
German corpus
</term>
of 2.284
<term>
|
#2518
An evaluation of our system against the annotated data shows that, it successfully classifies 73.2% in a German corpus of 2.284 SRHs as either coherent or incoherent (given a baseline of 54.55%). |
|
</term>
that describes an end-to-end process
|
in
|
the
<term>
noisy channel framework
</term>
|
#2688
In this paper, we introduce a generative probabilistic optical character recognition (OCR) model that describes an end-to-end process in the noisy channel framework, progressing from generation of true text through its transformation into the noisy output of an OCR system. |
|
The
<term>
model
</term>
is designed for use
|
in
|
<term>
error correction
</term>
, with a focus
|
#2718
The model is designed for use in error correction, with a focus on post-processing the output of black-box OCR systems in order to make it more useful for NLP tasks. |
|
</term>
of black-box
<term>
OCR systems
</term>
|
in
|
order to make it more useful for
<term>
NLP
|
#2733
The model is designed for use in error correction, with a focus on post-processing the output of black-box OCR systemsin order to make it more useful for NLP tasks. |
|
iii ) effective use of
<term>
priors
</term>
|
in
|
<term>
conditional loglinear models
</term>
|
#2963
We present a new part-of-speech tagger that demonstrates the following ideas: (i) explicit use of both preceding and following tag contexts via a dependency network representation, (ii) broad use of lexical features, including jointly conditioning on multiple consecutive words, (iii) effective use of priorsin conditional loglinear models, and (iv) fine-grained modeling of unknown word features. |
|
out-of-domain
<term>
bilingual corpus
</term>
and ,
|
in
|
addition , the
<term>
language model
</term>
|
#3103
In order to boost the translation quality of EBMT based on a small-sized bilingual corpus, we use an out-of-domain bilingual corpus and, in addition, the language model of an in-domain monolingual corpus. |
|
morphology
</term>
by identifying
<term>
hubs
</term>
|
in
|
an
<term>
automaton
</term>
. For our purposes
|
#3165
We describe a simple unsupervised technique for learning morphology by identifying hubsin an automaton. |
|
, a
<term>
hub
</term>
is a
<term>
node
</term>
|
in
|
a
<term>
graph
</term>
with
<term>
in-degree
</term>
|
#3178
For our purposes, a hub is a nodein a graph with in-degree greater than one and out-degree greater than one. |
|
to be mapped to non-overlapping intervals
|
in
|
the
<term>
French sentence
</term>
. We evaluate
|
#3254
It requires disjoint English phrases to be mapped to non-overlapping intervals in the French sentence. |
|
the utility of this
<term>
constraint
</term>
|
in
|
two different
<term>
algorithms
</term>
. The
|
#3266
We evaluate the utility of this constraintin two different algorithms. |
|
it can provide a significant improvement
|
in
|
<term>
alignment quality
</term>
. A novel
<term>
|
#3281
The results show that it can provide a significant improvement in alignment quality. |
|
<term>
natural language understanding
</term>
|
in
|
a
<term>
dialogue system
</term>
. We build
|
#3491
In this paper, we propose a novel Cooperative Model for natural language understandingin a dialogue system. |