model,11-6-P01-1007,bq |
<term>
method
</term>
on a
<term>
wide coverage
|
English
|
grammar
</term>
are given . While
<term>
paraphrasing
|
#1748
The results of a practical evaluation of this method on a wide coverage English grammar are given. |
lr,12-2-P01-1008,bq |
paraphrases
</term>
from a
<term>
corpus of multiple
|
English
|
translations
</term>
of the same
<term>
source
|
#1792
We present an unsupervised learning algorithm for identification of paraphrases from a corpus of multiple English translations of the same source text. |
other,3-2-N03-2017,bq |
constraint
</term>
. It requires disjoint
<term>
|
English
|
phrases
</term>
to be mapped to non-overlapping
|
#3246
It requires disjointEnglish phrases to be mapped to non-overlapping intervals in the French sentence. |
tech,13-2-P03-1050,bq |
machine translation
</term>
and it uses an
<term>
|
English
|
stemmer
</term>
and a small ( 10K sentences
|
#4459
The stemming model is based on statistical machine translation and it uses anEnglish stemmer and a small (10K sentences) parallel corpus as its sole training resources. |
other,29-2-P03-1058,bq |
<term>
nouns
</term>
in the
<term>
SENSEVAL-2
|
English
|
lexical sample task
</term>
. Our investigation
|
#4851
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. |
other,8-1-P04-2005,bq |
approach for automatically acquiring
<term>
|
English
|
topic signatures
</term>
. Given a particular
|
#6901
We present a novel approach for automatically acquiringEnglish topic signatures. |
other,15-4-P04-2005,bq |
word senses
</term>
are lexicalised in
<term>
|
English
|
</term>
and
<term>
Chinese
</term>
, and also
|
#6973
Our method takes advantage of the different way in which word senses are lexicalised inEnglish and Chinese, and also exploits the large amount of Chinese text available in corpora and on the Web. |
other,22-2-H05-1005,bq |
the output
<term>
summary
</term>
is in
<term>
|
English
|
</term>
. Typically , information that makes
|
#7174
We consider the case of multi-document summarization, where the input documents are in Arabic, and the output summary is inEnglish. |
other,22-4-H05-1005,bq |
realize that
<term>
information
</term>
in
<term>
|
English
|
</term>
. We demonstrate how errors in the
|
#7218
Further, the use of multiple machine translation systems provides yet more redundancy, yielding different ways to realize that information inEnglish. |
other,7-3-I05-4010,bq |
<term>
bilingual corpus
</term>
, 10.4 M
<term>
|
English
|
words
</term>
and 18.3 M
<term>
Chinese characters
|
#8259
The resultant bilingual corpus, 10.4MEnglish words and 18.3M Chinese characters, is an authoritative and comprehensive text collection covering the specific and special domain of HK laws. |
lr,10-3-J05-4003,bq |
</term>
from large
<term>
Chinese , Arabic , and
|
English
|
non-parallel newspaper corpora
</term>
.
|
#9040
Using this approach, we extract parallel data from large Chinese, Arabic, and English non-parallel newspaper corpora. |
|
the needs of a publication of papers in
|
English
|
, many systems to run off texts have been
|
#12224
In order to meet the needs of a publication of papers in English, many systems to run off texts have been developed. |
other,14-4-J82-3002,bq |
</term>
,
<term>
Chat-80
</term>
translates
<term>
|
English
|
questions
</term>
into the
<term>
Prolog
</term>
|
#12900
With the aid of a logic-based grammar formalism called extraposition grammars, Chat-80 translatesEnglish questions into the Prolog subset of logic. |
other,17-3-P82-1035,bq |
based both on knowledge of
<term>
surface
|
English
|
</term>
and on
<term>
world knowledge
</term>
|
#13044
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. |
other,10-4-P84-1034,bq |
Japanese sentence structure
</term>
and
<term>
|
English
|
sentence structure
</term>
, which is vital
|
#13303
Some examples of the difference between Japanese sentence structure andEnglish sentence structure, which is vital to machine translation are also discussed together with various interesting ambiguities. |
tech,16-1-A88-1003,bq |
</term>
of
<term>
Lucy
</term>
, a portable
<term>
|
English
|
understanding system
</term>
. The design
|
#14934
In this paper, we describe the pronominal anaphora resolution module of Lucy, a portableEnglish understanding system. |
other,14-1-C88-1044,bq |
demonstrative expressions
</term>
in
<term>
|
English
|
</term>
and discusses implications for current
|
#15183
This paper presents necessary and sufficient conditions for the use of demonstrative expressions inEnglish and discusses implications for current discourse processing algorithms. |
other,11-3-C90-3072,bq |
little
<term>
inflection
</term>
such as
<term>
|
English
|
</term>
, but fails for
<term>
highly inflective
|
#16768
This approach is sufficient for languages with little inflection such asEnglish, but fails for highly inflective languages such as Czech, Russian, Slovak or other Slavonic languages. |
other,18-5-C90-3072,bq |
existing
<term>
spelling-checkers
</term>
for
<term>
|
English
|
</term>
and the main
<term>
dictionary
</term>
|
#16825
The speed of the resulting program lies somewhere in the middle of the scale of existing spelling-checkers forEnglish and the main dictionary fits into the standard 360K floppy, whereas the number of recognized word forms exceeds 6 million (for Czech). |
other,7-1-A94-1007,bq |
authors propose a model for analyzing
<term>
|
English
|
sentences
</term>
including
<term>
coordinate
|
#19682
The authors propose a model for analyzingEnglish sentences including coordinate conjunctions such as and, or, but and the equivalent words. |