#792Listen-Communicate-Show (LCS) is a new paradigm for human interaction with data sources.
lr,8-6-N01-1003,ak
automatically learned from
<term>
training
data
</term>
. We show that the trained
<term>
SPR
#1431The SPR uses ranking rules automatically learned from training data.
over both character - and word-segmented
data
, in combination with a range of
<term>
local
#1511We take a selection of both bag-of-words and segment order-sensitive string comparison methods, and run each over both character- and word-segmented data, in combination with a range of local segment contiguity models (in the form of N-grams).
other,34-2-P01-1047,ak
learning algorithm
</term>
from
<term>
structured
data
</term>
( based on a
<term>
typing-algorithm
#1982Our 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).
lr,15-1-N03-1001,ak
manual transcription
</term>
of
<term>
training
data
</term>
. The method combines
<term>
domain
#2222This paper describes a method for utterance classification that does not require manual transcription of training data.
lr,7-4-N03-1012,ak
<term>
system
</term>
against the
<term>
annotated
data
</term>
shows that , it successfully classifies
#2510An 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%).
lr,2-1-N03-2003,ak
result
</term>
. Sources of
<term>
training
data
</term>
suitable for
<term>
language modeling
#3018Sources of training data suitable for language modeling of conversational speech are limited.
lr,7-2-N03-2003,ak
In this paper , we show how
<term>
training
data
</term>
can be supplemented with
<term>
text
#3037In this paper, we show how training data can be supplemented with text from the web filtered to match the style and/or topic of the target recognition task, but also that it is possible to get bigger performance gains from the data by using class-dependent interpolation of N-grams.
lr,43-2-N03-2003,ak
bigger performance gains from the
<term>
data
</term>
by using
<term>
class-dependent interpolation
#3072In this paper, we show how training data can be supplemented with text from the web filtered to match the style and/or topic of the target recognition task, but also that it is possible to get bigger performance gains from thedata by using class-dependent interpolation of N-grams.
large inflow of multilingual , multimedia
data
. It gives users the ability to spend their
#3603The TAP-XL Automated Analyst's Assistant is an application designed to help an English-speaking analyst write a topical report, culling information from a large inflow of multilingual, multimedia data.
ability to spend their time finding more
data
relevant to their task , and gives them
#3616It gives users the ability to spend their time finding more data relevant to their task, and gives them translingual reach into other languages by leveraging human language technology.
other,15-3-N03-4010,ak
browsing the
<term>
repository
</term>
of
<term>
data
objects
</term>
created by the
<term>
system
#3700The operation of the system will be explained in depth through browsing the repository ofdata objects created by the system during each question answering session.
other,13-1-P03-1005,ak
</term>
for
<term>
structured natural language
data
</term>
. The
<term>
HDAG Kernel
</term>
directly
#3806This paper proposes the Hierarchical Directed Acyclic Graph (HDAG) Kernel for structured natural language data.
other,15-1-P03-1009,ak
classes
</term>
from undisambiguated
<term>
corpus
data
</term>
. We describe a new approach which
#3901Previous research has demonstrated the utility of clustering in inducing semantic verb classes from undisambiguated corpus data.
#3972A novel evaluation scheme is proposed which accounts for the effect of polysemy on the clusters, offering us a good insight into the potential and limitations of semantically classifying undisambiguated SCF data.
lr,13-4-P03-1033,ak
learning
</term>
using real
<term>
dialogue
data
</term>
collected by the
<term>
system
</term>
#4367Moreover, the models are automatically derived by decision tree learning using real dialogue data collected by the system.
lr,14-1-P03-1058,ak
is the lack of
<term>
manually sense-tagged
data
</term>
required for
<term>
supervised learning
#4817A central problem of word sense disambiguation (WSD) is the lack of manually sense-tagged data required for supervised learning.
lr,11-2-P03-1058,ak
automatically acquire
<term>
sense-tagged training
data
</term>
from
<term>
English-Chinese parallel
#4836In 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.
lr,8-3-P03-1058,ak
this method of acquiring
<term>
sense-tagged
data
</term>
is promising . On a subset of the
#4867Our investigation reveals that this method of acquiring sense-tagged data is promising.
lr,37-4-P03-1058,ak
advantage that
<term>
manually sense-tagged
data
</term>
have in their sense coverage . Our
#4910On a subset of the most difficult SENSEVAL-2 nouns, the accuracy difference between the two approaches is only 14.0%, and the difference could narrow further to 6.5% if we disregard the advantage that manually sense-tagged data have in their sense coverage.