|
<term>
hidden Markov models ( HMM )
</term>
,
|
which
|
uses a large amount of
<term>
speech
</term>
|
#17009
First, we present a new paradigm for speaker-independent (SI) training of hidden Markov models (HMM), which uses a large amount of speech from a few speakers instead of the traditional practice of using a little speech from many speakers. |
|
Document Understanding System )
</term>
,
|
which
|
creates the data for a
<term>
text retrieval
|
#21406
Our document understanding technology is implemented in a system called IDUS (Intelligent Document Understanding System), which creates the data for a text retrieval application and the automatic generation of hypertext links. |
|
traditional
<term>
statistical approaches
</term>
,
|
which
|
resolve
<term>
ambiguities
</term>
by indirectly
|
#17842
Owing to the problem of insufficient training data and approximation error introduced by the language model, traditional statistical approaches, which resolve ambiguities by indirectly and implicitly using maximum likelihood method, fail to achieve high performance in real applications. |
|
<term>
concordancer
</term>
,
<term>
CARE
</term>
,
|
which
|
exploits the
<term>
move-tagged abstracts
|
#11768
We also present a prototype concordancer, CARE, which exploits the move-tagged abstracts for digital learning. |
|
<term>
LRE project SmTA double check
</term>
,
|
which
|
is creating a
<term>
PC based tool
</term>
|
#20177
This paper reports on work done for the LRE project SmTA double check, which is creating a PC based tool to be used in the technical abstracting industry. |
|
with a single
<term>
Intel i860 chip
</term>
,
|
which
|
provides a factor of 5 speed-up over a
<term>
|
#16932
The speech-search algorithm is implemented on a board with a single Intel i860 chip, which provides a factor of 5 speed-up over a SUN 4 for straight C code. |
|
English-Chinese parallel corpora
</term>
,
|
which
|
are then used for disambiguating the
<term>
|
#4840
In this paper, we evaluate an approach to automatically acquire sense-tagged training data from English-Chinese parallel corpora, which are then used for disambiguating the nouns in the SENSEVAL-2 English lexical sample task. |
|
a calculus of
<term>
equivalences
</term>
,
|
which
|
can be used to simplify
<term>
formulas
</term>
|
#14781
This logical model yields a calculus of equivalences, which can be used to simplify formulas. |
|
judge three types of the
<term>
errors
</term>
,
|
which
|
are characters wrongly substituted , deleted
|
#20651
In order to judge three types of the errors, which are characters wrongly substituted, deleted or inserted in a Japanese bunsetsu and an English word, and to correct these errors, this paper proposes new methods using m-th order Markov chain model for Japanese kanji-kana characters and English alphabets, assuming that Markov probability of a correct chain of syllables or kanji-kana characters is greater than that of erroneous chains. |
|
an impediment to progress in the field ,
|
which
|
we address with this work . Experiments
|
#7588
The lack of automatic methods for scoring system output is an impediment to progress in the field, which we address with this work. |
|
propose a
<term>
logical formalism
</term>
,
|
which
|
, among other things , is suitable for
|
#13890
In this paper we propose a logical formalism, which, among other things, is suitable for representing determiners without forcing a particular interpretation when their meaning is still not clear. |
|
argumentation system
</term>
by Konolige ,
|
which
|
is a
<term>
formalization
</term>
of
<term>
defeasible
|
#16586
This paper proposes that sentence analysis should be treated as defeasible reasoning, and presents such a treatment for Japanese sentence analyses using an argumentation system by Konolige, which is a formalization of defeasible reasoning, that includes arguments and defeat rules that capture defeasibility. |
|
probabilistic model of natural language
</term>
,
|
which
|
we call
<term>
HBG
</term>
, that takes advantage
|
#18903
We describe a generative probabilistic model of natural language, which we call HBG, that takes advantage of detailed linguistic information to resolve ambiguity. |
|
</term>
called
<term>
alternative markers
</term>
,
|
which
|
includes
<term>
other ( than )
</term>
,
<term>
|
#1831
This paper presents a formal analysis for a large class of words called alternative markers, which includes other (than), such (as), and besides. |
|
coordinate structure analysis model
</term>
,
|
which
|
provides
<term>
top-down scope information
|
#19794
This paper presents an English coordinate structure analysis model, which provides top-down scope information of the correct syntactic structure by taking advantage of the symmetric patterns of the parallelism. |
|
<term>
probabilistic parsing models
</term>
,
|
which
|
we call
<term>
P-CFG
</term>
, the
<term>
HBG
|
#19021
In head-to-head tests against one of the best existing robust probabilistic parsing models, which we call P-CFG, the HBG model significantly outperforms P-CFG, increasing the parsing accuracy rate from 60% to 75%, a 37% reduction in error. |
|
comparison with previous
<term>
models
</term>
,
|
which
|
either use arbitrary
<term>
windows
</term>
|
#6356
In comparison with previous models, which either use arbitrary windows to compute similarity between words or use lexical affinity to create sequential models, in this paper we focus on models intended to capture the co-occurrence patterns of any pair of words or phrases at any distance in the corpus. |
|
WH-questions
</term>
. These
<term>
models
</term>
,
|
which
|
are built from
<term>
shallow linguistic
|
#2146
These models, which are built from shallow linguistic features of questions, are employed to predict target variables which represent a user's informational goals. |
|
program
</term>
called
<term>
NOMAD
</term>
,
|
which
|
understands
<term>
scruffy texts
</term>
in
|
#13122
This method of using expectations to aid the understanding of scruffy texts has been incorporated into a working computer program called NOMAD, which understands scruffy texts in the domain of Navy messages. |
|
selection function
</term>
is presented ,
|
which
|
yields superior
<term>
feature vectors
</term>
|
#5368
Finally, a novel feature weighting and selection function is presented, which yields superior feature vectors and better word similarity performance. |