#436The 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,ak
performance
</term>
( typically ,
<term>
word or
semantic
error rate
</term>
) from a list of
<term>
#1091The 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,ak
hypotheses ( SRH )
</term>
in terms of their
<term>
semantic
coherence
</term>
. We conducted an
<term>
#2477We apply our system to the task of scoring alternative speech recognition hypotheses (SRH) in terms of theirsemantic coherence.
other,10-1-P03-1009,ak
<term>
clustering
</term>
in inducing
<term>
semantic
verb classes
</term>
from undisambiguated
#3895Previous research has demonstrated the utility of clustering in inducingsemantic verb classes from undisambiguated corpus data.
other,6-2-P03-1068,ak
backbone of the
<term>
annotation
</term>
are
<term>
semantic
roles
</term>
in the
<term>
frame semantics
#4971The backbone of the annotation aresemantic roles in the frame semantics paradigm.
tech,13-4-P03-1068,ak
</term>
and
<term>
ambiguity
</term>
in
<term>
semantic
annotation
</term>
. We investigate the
<term>
#5006On this basis, we discuss the problems of vagueness and ambiguity insemantic annotation.
model,15-2-I05-4007,ak
wordnets
</term>
, we must rely on
<term>
lexical
semantic
relation ( LSR ) mappings
</term>
to ensure
#7089Since there is no homomorphism between pairs of monolingual wordnets, we must rely on lexical semantic relation (LSR) mappings to ensure conceptual cohesion.
model,23-3-I05-4007,ak
</term>
and a set of
<term>
cross-lingual lexical
semantic
relations
</term>
. In particular , we propose
#7125In this paper, we propose and implement a model for bootstrapping parallel wordnets based on one monolingual wordnet and a set of cross-lingual lexical semantic relations.
tech,16-1-I05-5003,ak
related to the task of
<term>
sentence-level
semantic
equivalence classification
</term>
. This
#7383The task of machine translation (MT) evaluation is closely related to the task of sentence-level semantic equivalence classification.
other,25-2-I05-5003,ak
<term>
classifiers
</term>
to predict
<term>
semantic
equivalence
</term>
and
<term>
entailment
</term>
#7412This paper investigates the utility of applying standard MT evaluation methods (BLEU, NIST, WER and PER) to building classifiers to predictsemantic equivalence and entailment.
other,1-1-P05-1053,ak
MT architectures
</term>
. Extracting
<term>
semantic
relationships
</term>
between
<term>
entities
#9266Extractingsemantic relationships between entities is challenging.
other,7-2-P05-1053,ak
of diverse
<term>
lexical , syntactic and
semantic
knowledge
</term>
in
<term>
feature-based relation
#9284This paper investigates the incorporation of diverse lexical, syntactic and semantic knowledge in feature-based relation extraction using SVM.
other,4-5-P05-1053,ak
chunking
</term>
. We also demonstrate how
<term>
semantic
information
</term>
such as
<term>
WordNet
</term>
#9357We also demonstrate howsemantic information such as WordNet and Name List, can be used in feature-based relation extraction to further improve the performance.
tech,6-1-P05-1073,ak
Despite much recent progress on accurate
<term>
semantic
role labeling
</term>
, previous work has
#10040Despite much recent progress on accuratesemantic role labeling, previous work has largely used independent classifiers, possibly combined with separate label sequence models via Viterbi decoding.
model,13-1-P06-1052,ak
problem
</term>
: Given an
<term>
underspecified
semantic
representation ( USR )
</term>
of a
<term>
#12069We 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.
model,6-1-T78-1031,ak
performing
<term>
inference
</term>
in
<term>
semantic
networks
</term>
are presented and compared
#12993Two styles of performing inference insemantic networks are presented and compared.
model,8-5-T78-1031,ak
rules
</term>
can be constructed in a
<term>
semantic
network
</term>
using a variant of a
<term>
#13074Node-based inference rules can be constructed in asemantic network using a variant of a predicate calculus notation.
model,6-1-P81-1032,ak
interpretation
</term>
requires strong
<term>
semantic
domain models
</term>
,
<term>
fail-soft recovery
#13732Robust natural language interpretation requires strongsemantic domain models, fail-soft recovery heuristics, and very flexible control structures.
other,1-4-P82-1035,ak
being described . These
<term>
syntactic and
semantic
expectations
</term>
can be used to figure
#14347These 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 (ellipsis), and resolve referents (anaphora).
tech,23-2-E83-1029,ak
Procedural Systemic Grammar
</term>
, the
<term>
semantic
analyzer
</term>
relying on the
<term>
Conceptual
#14602Specifically, the following components of the system are described: the syntactic analyzer, based on a Procedural Systemic Grammar, thesemantic analyzer relying on the Conceptual Dependency Theory, and the dictionary.