|
</term>
from
<term>
structured data
</term>
(
|
based
|
on a
<term>
typing-algorithm
</term>
and
<term>
|
#1983
Our logical definition leads to a neat relation to categorial grammar, (yielding a treatment of Montague semantics), a parsing-as-deduction in a resource sensitive logic, and a learning algorithm from structured data ( based on a typing-algorithm and type-unification). |
|
approach to question answering
</term>
which is
|
based
|
on combining the results from different
|
#2336
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 answers in multiple corpora. |
|
implementation of the
<term>
model
</term>
|
based
|
on
<term>
finite-state models
</term>
, demonstrate
|
#2751
We present an implementation of the modelbased on finite-state models, demonstrate the model's ability to significantly reduce character and word error rate, and provide evaluation results involving automatic extraction of translation lexicons from printed text. |
|
translation quality
</term>
of
<term>
EBMT
</term>
|
based
|
on a small-sized
<term>
bilingual corpus
</term>
|
#3088
In order to boost the translation quality of EBMTbased 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. |
|
on
<term>
block selection criteria
</term>
|
based
|
on
<term>
unigram
</term>
counts and
<term>
phrase
|
#3469
We show experimental results on block selection criteriabased on unigram counts and phrase length. |
|
<term>
dialogue system
</term>
. We build this
|
based
|
on both
<term>
Finite State Model ( FSM )
|
#3499
We build this based on both Finite State Model (FSM) and Statistical Learning Model (SLM). |
|
central to our
<term>
IE paradigm
</term>
. It is
|
based
|
on : ( 1 ) an extended set of
<term>
features
|
#3752
It is based on: (1) an extended set of features; and (2) inductive decision tree learning. |
tech,3-1-P03-1022,bq |
data
</term>
. We apply a
<term>
decision tree
|
based
|
approach
</term>
to
<term>
pronoun resolution
|
#3978
We apply a decision tree based approach to pronoun resolution in spoken dialogue. |
|
to understand
<term>
user utterances
</term>
|
based
|
on the
<term>
context
</term>
of a
<term>
dialogue
|
#4147
This process enables the system to understand user utterancesbased on the context of a dialogue. |
|
dimensions .
<term>
Dialogue strategies
</term>
|
based
|
on the
<term>
user modeling
</term>
are implemented
|
#4382
Dialogue strategiesbased on the user modeling are implemented in Kyoto city bus information system that has been developed at our laboratory. |
|
</term>
. The
<term>
stemming model
</term>
is
|
based
|
on
<term>
statistical machine translation
|
#4450
The stemming model is based on statistical machine translation and it uses an English stemmer and a small (10K sentences) parallel corpus as its sole training resources. |
|
built a
<term>
generation algorithm
</term>
|
based
|
on the results . The evaluation using another
|
#5706
We conducted psychological experiments with 42 subjects to collect referring expressions in such situations, and built a generation algorithmbased on the results. |
tech,3-5-C04-1112,bq |
model
</term>
. Also , the
<term>
WSD system
|
based
|
on lemmas
</term>
is smaller and more robust
|
#6083
Also, the WSD system based on lemmas is smaller and more robust. |
|
finding
<term>
synonymous expressions
</term>
|
based
|
on the
<term>
distributional hypothesis
</term>
|
#6102
We present a text mining method for finding synonymous expressionsbased on the distributional hypothesis in a set of coherent corpora. |
|
We show that various
<term>
features
</term>
|
based
|
on the structure of
<term>
email-threads
</term>
|
#6287
We show that various featuresbased on the structure of email-threads can be used to improve upon lexical similarity of discourse segments for question-answer pairing. |
|
for
<term>
word sense disambiguation
</term>
|
based
|
on
<term>
parallel corpora
</term>
. The method
|
#6445
The paper presents a method for word sense disambiguationbased on parallel corpora. |
|
<term>
features
</term>
of
<term>
sentences
</term>
|
based
|
on
<term>
semantic similarity measures
</term>
|
#6696
This system identifies features of sentencesbased on semantic similarity measures and discourse structure. |
|
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. |