other,15-4-C04-1036,bq |
presented , which yields superior
<term>
|
feature vectors
|
</term>
and better
<term>
word similarity
</term>
|
#5371
Finally, a novel feature weighting and selection function is presented, which yields superiorfeature vectors and better word similarity performance. |
other,29-3-C04-1036,bq |
<term>
measure
</term>
for evaluating
<term>
|
feature vector
|
</term>
quality . Finally , a novel
<term>
|
#5352
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 evaluatingfeature vector quality. |
other,30-2-C04-1036,bq |
application
</term>
) at a good level of
<term>
|
human agreement
|
</term>
. Motivated by this semantic criterion
|
#5320
The new criterion - meaning-entailing substitutability - fits the needs of semantic-oriented NLP applications and can be evaluated directly (independent of an application) at a good level ofhuman agreement. |
other,9-1-C04-1036,bq |
goal and evaluation criterion for
<term>
|
word similarity measures
|
</term>
. The new criterion -
<term>
meaning-entailing
|
#5286
We suggest a new goal and evaluation criterion forword similarity measures. |
tech,11-2-C04-1036,bq |
substitutability
</term>
- fits the needs of
<term>
|
semantic-oriented NLP applications
|
</term>
and can be evaluated directly ( independent
|
#5301
The new criterion - meaning-entailing substitutability - fits the needs ofsemantic-oriented NLP applications and can be evaluated directly (independent of an application) at a good level of human agreement. |
tech,4-4-C04-1036,bq |
</term>
quality . Finally , a novel
<term>
|
feature weighting and selection function
|
</term>
is presented , which yields superior
|
#5360
Finally, a novelfeature weighting and selection function is presented, which yields superior feature vectors and better word similarity performance. |
other,19-4-C04-1036,bq |
<term>
feature vectors
</term>
and better
<term>
|
word similarity
|
</term>
performance . The work presented
|
#5375
Finally, a novel feature weighting and selection function is presented, which yields superior feature vectors and betterword similarity performance. |
other,11-3-C04-1036,bq |
we analyze the empirical quality of
<term>
|
distributional word feature vectors
|
</term>
and its impact on
<term>
word similarity
|
#5334
Motivated by this semantic criterion we analyze the empirical quality ofdistributional word feature vectors and its impact on word similarity results, proposing an objective measure for evaluating feature vector quality. |
measure(ment),26-3-C04-1036,bq |
</term>
results , proposing an objective
<term>
|
measure
|
</term>
for evaluating
<term>
feature vector
|
#5349
Motivated by this semantic criterion we analyze the empirical quality of distributional word feature vectors and its impact on word similarity results, proposing an objectivemeasure for evaluating feature vector quality. |
measure(ment),4-2-C04-1036,bq |
measures
</term>
. The new criterion -
<term>
|
meaning-entailing substitutability
|
</term>
- fits the needs of
<term>
semantic-oriented
|
#5294
The new criterion -meaning-entailing substitutability - fits the needs of semantic-oriented NLP applications and can be evaluated directly (independent of an application) at a good level of human agreement. |
other,23-2-C04-1036,bq |
evaluated directly ( independent of an
<term>
|
application
|
</term>
) at a good level of
<term>
human agreement
|
#5313
The new criterion - meaning-entailing substitutability - fits the needs of semantic-oriented NLP applications and can be evaluated directly (independent of anapplication) at a good level of human agreement. |
other,19-3-C04-1036,bq |
feature vectors
</term>
and its impact on
<term>
|
word similarity
|
</term>
results , proposing an objective
<term>
|
#5342
Motivated by this semantic criterion we analyze the empirical quality of distributional word feature vectors and its impact onword similarity results, proposing an objective measure for evaluating feature vector quality. |