other,2-2-H92-1026,bq |
</term>
incorporates
<term>
lexical , syntactic ,
|
semantic
|
, and structural information
</term>
from
|
#18925
HBG incorporates lexical, syntactic, semantic, and structural information from the parse tree into the disambiguation process in a novel way. |
tech,13-4-P03-1068,bq |
</term>
and
<term>
ambiguity
</term>
in
<term>
|
semantic
|
annotation
</term>
. We investigate the
<term>
|
#5004
On this basis, we discuss the problems of vagueness and ambiguity insemantic annotation. |
other,17-6-A94-1026,bq |
component places some restrictions on the
<term>
|
semantic
|
categories
</term>
of the
<term>
adjoining
|
#20477
The basic idea of this method is that a compound noun component places some restrictions on thesemantic categories of the adjoining words. |
other,20-2-N03-1012,bq |
hypotheses ( SRH )
</term>
in terms of their
<term>
|
semantic
|
coherence
</term>
. We conducted an
<term>
|
#2476
We apply our system to the task of scoring alternative speech recognition hypotheses (SRH) in terms of theirsemantic coherence. |
other,8-3-C90-3063,bq |
these
<term>
statistics
</term>
reflect
<term>
|
semantic
|
constraints
</term>
and thus are used to
|
#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 |
statistics
</term>
indeed reflect the
<term>
|
semantic
|
constraints
</term>
and thus provide a basis
|
#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. |
other,3-1-C90-3063,bq |
defeasibility
</term>
. Manual acquisition of
<term>
|
semantic
|
constraints
</term>
in broad domains is very
|
#16607
Manual acquisition ofsemantic constraints in broad domains is very expensive. |
|
human agreement
</term>
. Motivated by this
|
semantic
|
criterion we analyze the empirical 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,6-3-C94-1052,bq |
experiments , corresponding to rather
<term>
closed
|
semantic
|
domains
</term>
, have been developed in
|
#20796
Several experiments, corresponding to rather closed semantic domains, have been developed in order to generate lexical cross-relations between English and Spanish. |
other,25-2-I05-5003,bq |
<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. |
tech,16-1-I05-5003,bq |
related to the task of
<term>
sentence-level
|
semantic
|
equivalence classification
</term>
. This
|
#8333
The task of machine translation (MT) evaluation is closely related to the task of sentence-level semantic equivalence classification. |
measure(ment),19-3-H01-1058,bq |
performance
</term>
( typically ,
<term>
word or
|
semantic
|
error rate
</term>
) from a list of
<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,1-4-P82-1035,bq |
being described . These
<term>
syntactic and
|
semantic
|
expectations
</term>
can be used to figure
|
#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). |
tech,25-2-H01-1041,bq |
meaning representation
</term>
called a
<term>
|
semantic
|
frame
</term>
. The key features of the
<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. |
other,39-3-H92-1060,bq |
gluing them together to obtain a single
<term>
|
semantic
|
frame
</term>
encoding the full
<term>
meaning
|
#19425
Robust parsing is applied only after a full analysis has failed, and it involves the two stages of 1) parsing a set of phrases and clauses, and 2) gluing them together to obtain a singlesemantic frame encoding the full meaning of the sentence. |
other,1-3-P84-1047,bq |
</term>
are grouped together . Like
<term>
|
semantic
|
grammar
</term>
, this allows easy exploitation
|
#13351
Likesemantic grammar, this allows easy exploitation of limited domain semantics. |
other,42-6-A92-1027,bq |
only
<term>
edges
</term>
with a valid
<term>
|
semantic
|
</term>
interpretation are ever introduced
|
#17745
A further reduction in the search space is achieved by using semantic rather than syntactic categories on the terminal and non-terminal edges, thereby reducing the amount of ambiguity and thus the number of edges, since only edges with a validsemantic interpretation are ever introduced. |
other,31-1-C90-3045,bq |
</term>
, for instance , to the task of
<term>
|
semantic
|
interpretation
</term>
or
<term>
automatic
|
#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,8-5-T78-1031,bq |
rules
</term>
can be constructed in a
<term>
|
semantic
|
network
</term>
using a variant of a
<term>
|
#12137
Node-based inference rules can be constructed in asemantic network using a variant of a predicate calculus notation. |
other,6-1-T78-1031,bq |
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. |