a
<term>
machine translation
</term>
. Additionally
#734The subjects were given three minutes per extract to determine whether they believed the sample output to be an expert human translationor a machine translation.
other,14-4-H01-1049,ak
logistics system to place a
<term>
supply
or
information request
</term>
. The
<term>
request
#843Using LCS-Marine, tactical personnel can converse with their logistics system to place a supply or information request.
the status of a
<term>
request
</term>
changes
or
when a
<term>
request
</term>
is complete .
#880Requestors can also instruct the system to notify them when the status of a request changes or when a request is complete.
measure(ment),19-3-H01-1058,ak
performance
</term>
( typically ,
<term>
word
or
semantic error rate
</term>
) from a list
#1090The oracle knows the reference word string and selects the word string with the best performance (typically, word or semantic error rate) from a list of word strings, where each word string has been obtained by using a different LM.
</term>
using a
<term>
neural network
</term>
or
a
<term>
decision tree
</term>
. The method
#1167We suggest a method that mimics the behavior of the oracle using a neural networkor a decision tree.
decision of how to combine them into one
or
more
<term>
sentences
</term>
. In this paper
#1331Sentence planning is a set of inter-related but distinct tasks, one of which is sentence scoping, i.e. the choice of syntactic structure for elementary speech acts and the decision of how to combine them into one or more sentences.
tech,16-1-P01-1008,ak
</term>
, current systems use
<term>
manual
or
semi-automatic methods
</term>
to collect
#1771While paraphrasing is critical both for interpretation and generation of natural language, current systems use manual or semi-automatic methods to collect paraphrases.
tech,32-1-P01-1056,ak
compete with
<term>
hand-crafted template-based
or
rule-based approaches
</term>
. In this paper
#2047Techniques for automatically training modules of a natural language generator have recently been proposed, but a fundamental concern is whether the quality of utterances produced with trainable components can compete with hand-crafted template-based or rule-based approaches.
2.284
<term>
SRHs
</term>
as either coherent
or
incoherent ( given a
<term>
baseline
</term>
#2529An 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%).
model,7-2-N03-2025,ak
approach only requires a few common
<term>
noun
or
pronoun seeds
</term>
that correspond to
#3314This approach only requires a few common noun or pronoun seeds that correspond to the concept for the targeted NE, e.g. he/she/man/woman for PERSON NE.
that focus on
<term>
user 's knowledge
</term>
or
typical kinds of
<term>
users
</term>
, the
#4309Unlike previous studies that focus on user's knowledgeor typical kinds of users, the user model we propose is more comprehensive.
to adapt to a desired
<term>
domain
</term>
or
<term>
genre
</term>
. Examples and results
#4509Monolingual, unannotated text can be used to further improve the stemmer by allowing it to adapt to a desired domainor genre.
prefix * - stem-suffix * ( * denotes zero
or
more occurrences of a
<term>
morpheme
</term>
#4632We approximate Arabic's rich morphology by a model that a word consists of a sequence of morphemes in the pattern prefix*-stem-suffix* (* denotes zero or more occurrences of a morpheme).
items
</term>
to
<term>
word clusters
</term>
or
<term>
word senses
</term>
. The
<term>
model
#5466We make use of a conditional log-linear model, with hidden variables representing the assignment of lexical items to word clustersor word senses.
with
<term>
tag
</term>
[ ANA ] for anaphoric
or
[ IMP ] for impersonal or expletive . This
#6121We present a tool, called ILIMP, which takes as input a raw text in French and produces as output the same text in which every occurrence of the pronoun il is tagged either with tag [ANA] for anaphoric or [IMP] for impersonal or expletive.
for anaphoric or [ IMP ] for impersonal
or
expletive . This tool is therefore designed
#6127We present a tool, called ILIMP, which takes as input a raw text in French and produces as output the same text in which every occurrence of the pronoun il is tagged either with tag [ANA] for anaphoric or [IMP] for impersonal or expletive.
systems
</term>
, such as
<term>
BLEU
</term>
or
<term>
NIST
</term>
, are now well established
#6235Automatic evaluation metrics for Machine Translation (MT) systems, such as BLEUor NIST, are now well established.
language pairs
</term>
like English-Chinese
or
English-Japanese , because of the
<term>
#6257Yet, they are scarcely used for the assessment of language pairs like English-Chinese or English-Japanese, because of the word segmentation problem.
<term>
dependents
</term>
on its left , right
or
on both sides . The
<term>
ambiguity resolution
#6626In the Chinese language, a verb may have its dependents on its left, right or on both sides.
parsing
</term>
of
<term>
sentences
</term>
with two
or
more
<term>
verbs
</term>
. Previous works
#6646The ambiguity resolution of right-side dependencies is essential for dependency parsing of sentences with two or more verbs.