|
information extraction system
</term>
we evaluate is
|
based
|
on a
<term>
linear-chain conditional random
|
#6818
The information extraction system we evaluate is based on a linear-chain conditional random field (CRF), a probabilistic model which has performed well on information extraction tasks because of its ability to capture arbitrary, overlapping features of the input in a Markov model. |
|
algorithm
</term>
for
<term>
Arabic-English
</term>
|
based
|
on
<term>
supervised training data
</term>
|
#7260
This paper presents a maximum entropy word alignment algorithm for Arabic-Englishbased on supervised training data. |
|
statistical machine translation method
</term>
,
|
based
|
on
<term>
non-contiguous phrases
</term>
,
|
#7347
This paper presents a phrase-based statistical machine translation method, based on non-contiguous phrases, i.e. phrases with gaps. |
|
as well as a
<term>
training method
</term>
|
based
|
on the maximization of
<term>
translation
|
#7388
A statistical translation model is also presented that deals such phrases, as well as a training methodbased on the maximization of translation accuracy, as measured with the NIST evaluation metric. |
tech,7-10-I05-2048,bq |
coupled with
<term>
rule-based and example
|
based
|
machine translation modules
</term>
to build
|
#8178
It has also successfully been coupled with rule-based and example based machine translation modules to build a multi engine machine translation system. |
|
novel
<term>
classification method
</term>
|
based
|
on
<term>
PER
</term>
which leverages
<term>
|
#8374
We also introduce a novel classification methodbased on PER which leverages part of speech information of the words contributing to the word matches and non-matches in the sentence. |
|
</term>
for the
<term>
reranking task
</term>
,
|
based
|
on the
<term>
boosting approach
</term>
to
<term>
|
#8769
We introduce a new method for the reranking task, based on the boosting approach to ranking problems described in Freund et al. (1998). |
|
statistical machine translation system
</term>
|
based
|
on a
<term>
probabilistic synchronous dependency
|
#9436
In this paper, we present a syntax-based statistical machine translation systembased on a probabilistic synchronous dependency insertion grammar. |
|
outperforms the
<term>
baseline system
</term>
|
based
|
on the
<term>
IBM models
</term>
in both
<term>
|
#9537
The result shows that our system outperforms the baseline systembased on the IBM models in both translation speed and quality. |
|
) as well as
<term>
binary features
</term>
|
based
|
on the
<term>
block
</term>
identities themselves
|
#9614
We use a maximum likelihood criterion to train a log-linear block bigram model which uses real-valued features (e.g. a language model score) as well as binary featuresbased on the block identities themselves, e.g. block bigram features. |
|
<term>
dialogue act
</term>
can be predicted
|
based
|
on
<term>
gaze
</term>
,
<term>
utterance
</term>
|
#10268
First, we investigate how well the addressee of a dialogue act can be predicted based on gaze, utterance and conversational context features. |
tech,8-3-P06-2012,bq |
</term>
show that this
<term>
spectral clustering
|
based
|
approach
</term>
outperforms the other
<term>
|
#11384
Experiment results on ACE corpora show that this spectral clustering based approach outperforms the other clustering methods. |
|
<term>
method of analyzing metaphors
</term>
|
based
|
on the existence of a small number of
<term>
|
#12463
This paper discusses a method of analyzing metaphorsbased on the existence of a small number of generalized metaphor mappings. |
|
The paper proposes
<term>
interfaces
</term>
|
based
|
on a judicious mixture of these techniques
|
#12646
The paper proposes interfacesbased on a judicious mixture of these techniques and the still valuable methods of more traditional natural language interfaces. |
|
</term>
, a
<term>
programming language
</term>
|
based
|
on
<term>
logic
</term>
. With the aid of a
|
#12882
The system is implemented entirely in Prolog, a programming languagebased on logic. |
|
to make use of
<term>
expectations
</term>
,
|
based
|
both on knowledge of
<term>
surface English
|
#13038
Our solution to these problems is to make use of expectations, based both on knowledge of surface English and on world knowledge of the situation being described. |
|
reasoning with dispositions
</term>
which is
|
based
|
on the concept of a
<term>
fuzzy syllogism
|
#13675
The paper closes with a description of an approach to reasoning with dispositions which is based on the concept of a fuzzy syllogism. |
|
interactive disambiguation scheme
</term>
|
based
|
on the
<term>
paraphrasing
</term>
of a
<term>
|
#15717
This paper presents a new interactive disambiguation schemebased on the paraphrasing of a parser's multiple output. |
|
of processing prevails they are usually
|
based
|
on
<term>
dictionaries of word forms
</term>
|
#16747
From different reasons among which the speed of processing prevails they are usually based on dictionaries of word forms instead of words. |
|
of
<term>
phrase boundary heuristics
</term>
|
based
|
on the placement of
<term>
function words
|
#17675
This is facilitated through the use of phrase boundary heuristicsbased on the placement of function words, and by heuristic rules that permit certain kinds of phrases to be deduced despite the presence of unknown words. |