other,16-7-P03-1050,bq |
average precision
</term>
over
<term>
unstemmed
|
text
|
</term>
, and 96 % of the performance of
|
#4586
Task-based evaluation using Arabic information retrieval indicates an improvement of 22-38% in average precision over unstemmed text, and 96% of the performance of the proprietary stemmer above. |
other,14-4-C92-4207,bq |
spatial constraints
</term>
from the
<term>
|
text
|
</term>
, and represent them as the
<term>
|
#18468
To reconstruct the model, the authors extract the qualitative spatial constraints from thetext, and represent them as the numerical constraints on the spatial attributes of the entities. |
lr,26-6-P03-1050,bq |
affix lists
</term>
, and
<term>
human annotated
|
text
|
</term>
, in addition to an
<term>
unsupervised
|
#4560
Our resource-frugal approach results in 87.5% agreement with a state of the art, proprietary Arabic stemmer built using rules, affix lists, and human annotated text, in addition to an unsupervised component. |
other,12-4-P06-1013,bq |
are derived automatically from
<term>
raw
|
text
|
</term>
. Experiments using the
<term>
SemCor
|
#11022
Our combination methods rely on predominant senses which are derived automatically from raw text. |
other,17-1-A94-1026,bq |
conversion
</term>
needed to input the
<term>
|
text
|
</term>
. It is critical , therefore , for
|
#20383
Japanese texts frequently suffer from the homophone errors caused by the KANA-KANJI conversion needed to input thetext. |
other,20-2-P01-1008,bq |
translations
</term>
of the same
<term>
source
|
text
|
</term>
. Our approach yields
<term>
phrasal
|
#1798
We present an unsupervised learning algorithm for identification of paraphrases from a corpus of multiple English translations of the same source text. |
other,11-7-H01-1042,bq |
six extracts of
<term>
translated newswire
|
text
|
</term>
. Some of the extracts were
<term>
|
#695
Subjects were given a set of up to six extracts of translated newswire text. |
other,24-1-N03-4010,bq |
answering capability
</term>
on
<term>
free
|
text
|
</term>
. The demonstration will focus on
|
#3660
The JAVELIN system integrates a flexible, planning-based architecture with a variety of language processing modules to provide an open-domain question answering capability on free text. |
other,37-3-N03-1018,bq |
translation lexicons
</term>
from
<term>
printed
|
text
|
</term>
. We present an application of
<term>
|
#2782
We present an implementation of the model based 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. |
|
aggregation system
</term>
using each author 's
|
text
|
as a coherent
<term>
corpus
</term>
. Our approach
|
#6133
This paper proposes a new methodology to improve the accuracy of a term aggregation system using each author's text as a coherent corpus. |
other,26-4-P04-2005,bq |
exploits the large amount of
<term>
Chinese
|
text
|
</term>
available in
<term>
corpora
</term>
and
|
#6985
Our method takes advantage of the different way in which word senses are lexicalised in English and Chinese, and also exploits the large amount of Chinese text available in corpora and on the Web. |
tech,36-1-H01-1040,bq |
text collections
</term>
via a standard
<term>
|
text
|
browser
</term>
. We describe how this information
|
#310
In this paper we show how two standard outputs from information extraction (IE) systems - named entity annotations and scenario templates - can be used to enhance access to text collections via a standardtext browser. |
tech,38-3-H01-1040,bq |
increased potential of
<term>
IE-enhanced
|
text
|
browsers
</term>
. At MIT Lincoln Laboratory
|
#383
We also report results of a preliminary, qualitative user evaluation of the system, which while broadly positive indicates further work needs to be done on the interface to make users aware of the increased potential of IE-enhanced text browsers. |
lr,11-4-P04-2010,bq |
<term>
pronouns
</term>
in
<term>
unannotated
|
text
|
</term>
by using a fully automatic sequence
|
#7081
Furthermore, we present a standalone system that resolves pronouns in unannotated text by using a fully automatic sequence of preprocessing modules that mimics the manual annotation process. |
lr,0-4-P03-1050,bq |
phase
</term>
.
<term>
Monolingual , unannotated
|
text
|
</term>
can be used to further improve the
|
#4489
Monolingual, unannotated text can be used to further improve the stemmer by allowing it to adapt to a desired domain or genre. |
lr,20-3-I05-4010,bq |
an authoritative and comprehensive
<term>
|
text
|
collection
</term>
covering the specific
|
#8272
The resultant bilingual corpus, 10.4M English words and 18.3M Chinese characters, is an authoritative and comprehensivetext collection covering the specific and special domain of HK laws. |
other,31-1-H01-1040,bq |
- can be used to enhance access to
<term>
|
text
|
collections
</term>
via a standard
<term>
text
|
#305
In this paper we show how two standard outputs from information extraction (IE) systems - named entity annotations and scenario templates - can be used to enhance access totext collections via a standard text browser. |
lr,19-2-N03-4010,bq |
answer candidates
</term>
from the given
<term>
|
text
|
corpus
</term>
. The operation of the
<term>
|
#3681
The demonstration will focus on how JAVELIN processes questions and retrieves the most likely answer candidates from the giventext corpus. |
lr-prod,15-3-H94-1014,bq |
<term>
word
</term><term>
Wall Street Journal
|
text
|
corpus
</term>
. Using the
<term>
BU recognition
|
#21260
The models were constructed using a 5K vocabulary and trained using a 76 million word Wall Street Journal text corpus. |
other,13-2-N03-2003,bq |
data
</term>
can be supplemented with
<term>
|
text
|
</term>
from the
<term>
web
</term>
filtered
|
#3041
In this paper, we show how training data can be supplemented withtext 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. |