tech,25-2-H01-1041,bq |
The
<term>
CCLINC Korean-to-English translation system
</term>
consists of two
<term>
core modules
</term>
,
<term>
language understanding and generation modules
</term>
mediated by a
<term>
language neutral meaning representation
</term>
called a
<term>
semantic
frame
</term>
.
|
#436
The CCLINC Korean-to-English translation system consists of two core modules, language understanding and generation modules mediated by a language neutral meaning representation called asemantic frame. |
measure(ment),19-3-H01-1058,bq |
The
<term>
oracle
</term>
knows the
<term>
reference word string
</term>
and selects the
<term>
word string
</term>
with the best
<term>
performance
</term>
( typically ,
<term>
word or
semantic
error rate
</term>
) from a list of
<term>
word strings
</term>
, where each
<term>
word string
</term>
has been obtained by using a different
<term>
LM
</term>
.
|
#1091
The 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. |
other,20-2-N03-1012,bq |
We apply our
<term>
system
</term>
to the task of
<term>
scoring
</term>
alternative
<term>
speech recognition hypotheses ( SRH )
</term>
in terms of their
<term>
semantic
coherence
</term>
.
|
#2476
We apply our system to the task of scoring alternative speech recognition hypotheses (SRH) in terms of theirsemantic coherence. |
other,10-1-P03-1009,bq |
Previous research has demonstrated the utility of
<term>
clustering
</term>
in inducing
<term>
semantic
verb classes
</term>
from undisambiguated
<term>
corpus data
</term>
.
|
#3894
Previous research has demonstrated the utility of clustering in inducingsemantic verb classes from undisambiguated corpus data. |
other,6-2-P03-1068,bq |
The backbone of the
<term>
annotation
</term>
are
<term>
semantic
roles
</term>
in the
<term>
frame semantics paradigm
</term>
.
|
#4969
The backbone of the annotation aresemantic roles in the frame semantics paradigm. |
tech,13-4-P03-1068,bq |
On this basis , we discuss the problems of
<term>
vagueness
</term>
and
<term>
ambiguity
</term>
in
<term>
semantic
annotation
</term>
.
|
#5004
On this basis, we discuss the problems of vagueness and ambiguity insemantic annotation. |
|
Motivated by this
semantic
criterion we analyze the empirical quality of
<term>
distributional word feature vectors
</term>
and its impact on
<term>
word similarity
</term>
results , proposing an objective
<term>
measure
</term>
for evaluating
<term>
feature vector
</term>
quality .
|
#5326
Motivated by this semantic criterion we analyze the empirical quality of distributional word feature vectors and its impact on word similarity results, proposing an objective measure for evaluating feature vector quality. |
other,8-3-N04-1024,bq |
This system identifies
<term>
features
</term>
of
<term>
sentences
</term>
based on
<term>
semantic
similarity measures
</term>
and
<term>
discourse structure
</term>
.
|
#6698
This system identifies features of sentences based onsemantic similarity measures and discourse structure. |
tech,16-1-I05-5003,bq |
The task of
<term>
machine translation ( MT ) evaluation
</term>
is closely related to the task of
<term>
sentence-level
semantic
equivalence classification
</term>
.
|
#8333
The task of machine translation (MT) evaluation is closely related to the task of sentence-level semantic equivalence classification. |
other,25-2-I05-5003,bq |
This paper investigates the utility of applying standard
<term>
MT evaluation methods ( BLEU , NIST , WER and PER )
</term>
to building
<term>
classifiers
</term>
to predict
<term>
semantic
equivalence
</term>
and
<term>
entailment
</term>
.
|
#8362
This paper investigates the utility of applying standard MT evaluation methods (BLEU, NIST, WER and PER) to building classifiers to predictsemantic equivalence and entailment. |
other,13-1-P06-1052,bq |
We present an efficient algorithm for the
<term>
redundancy elimination problem
</term>
: Given an
<term>
underspecified
semantic
representation ( USR )
</term>
of a
<term>
scope ambiguity
</term>
, compute an
<term>
USR
</term>
with fewer mutually
<term>
equivalent readings
</term>
.
|
#11132
We present an efficient algorithm for the redundancy elimination problem: Given an underspecified semantic representation (USR) of a scope ambiguity, compute an USR with fewer mutually equivalent readings. |
other,6-1-T78-1031,bq |
Two styles of performing
<term>
inference
</term>
in
<term>
semantic
networks
</term>
are presented and compared .
|
#12056
Two styles of performing inference insemantic networks are presented and compared. |
other,8-5-T78-1031,bq |
<term>
Node-based inference rules
</term>
can be constructed in a
<term>
semantic
network
</term>
using a variant of a
<term>
predicate calculus notation
</term>
.
|
#12137
Node-based inference rules can be constructed in asemantic network using a variant of a predicate calculus notation. |
other,1-4-P82-1035,bq |
These
<term>
syntactic and
semantic
expectations
</term>
can be used to figure out
<term>
unknown words
</term>
from
<term>
context
</term>
, constrain the possible
<term>
word-senses
</term>
of
<term>
words with multiple meanings
</term>
(
<term>
ambiguity
</term>
) , fill in
<term>
missing words
</term>
(
<term>
elllpsis
</term>
) , and resolve
<term>
referents
</term>
(
<term>
anaphora
</term>
) .
|
#13058
These syntactic and semantic expectations can be used to figure out unknown words from context, constrain the possible word-senses of words with multiple meanings (ambiguity), fill in missing words (elllpsis), and resolve referents (anaphora). |
other,1-3-P84-1047,bq |
Like
<term>
semantic
grammar
</term>
, this allows easy exploitation of
<term>
limited domain semantics
</term>
.
|
#13351
Likesemantic grammar, this allows easy exploitation of limited domain semantics. |
other,25-3-C88-1007,bq |
The principle advantage of this approach is that knowledge concerning translation equivalence of expressions may be directly exploited , obviating the need for answers to
<term>
semantic
questions
</term>
that we do not yet have .
|
#15088
The principle advantage of this approach is that knowledge concerning translation equivalence of expressions may be directly exploited, obviating the need for answers tosemantic questions that we do not yet have. |
other,31-1-C90-3045,bq |
The unique properties of
<term>
tree-adjoining grammars ( TAG )
</term>
present a challenge for the application of
<term>
TAGs
</term>
beyond the limited confines of
<term>
syntax
</term>
, for instance , to the task of
<term>
semantic
interpretation
</term>
or
<term>
automatic translation of natural language
</term>
.
|
#16456
The unique properties of tree-adjoining grammars (TAG) present a challenge for the application of TAGs beyond the limited confines of syntax, for instance, to the task ofsemantic interpretation or automatic translation of natural language. |
other,3-1-C90-3063,bq |
Manual acquisition of
<term>
semantic
constraints
</term>
in broad domains is very expensive .
|
#16607
Manual acquisition ofsemantic constraints in broad domains is very expensive. |
other,8-3-C90-3063,bq |
To a large extent , these
<term>
statistics
</term>
reflect
<term>
semantic
constraints
</term>
and thus are used to disambiguate
<term>
anaphora references
</term>
and
<term>
syntactic ambiguities
</term>
.
|
#16641
To a large extent, these statistics reflectsemantic constraints and thus are used to disambiguate anaphora references and syntactic ambiguities. |
other,18-6-C90-3063,bq |
The results of the experiment show that in most of the cases the
<term>
cooccurrence statistics
</term>
indeed reflect the
<term>
semantic
constraints
</term>
and thus provide a basis for a useful
<term>
disambiguation tool
</term>
.
|
#16709
The results of the experiment show that in most of the cases the cooccurrence statistics indeed reflect thesemantic constraints and thus provide a basis for a useful disambiguation tool. |