#6409At the same time, the recent improvements in theBLEU scores of statistical machine translation (SMT) suggests that SMT models are good at predicting the right translation of the words in source language sentences.
model,18-1-I05-2021,ak
claim , by evaluating a representative
<term>
Chinese-to-English SMT model
</term>
directly on
<term>
word sense disambiguation
#6347We present the first known empirical test of an increasingly common speculative claim, by evaluating a representativeChinese-to-English SMT model directly on word sense disambiguation performance, using standard WSD evaluation methodology and datasets from the Senseval-3 Chinese lexical sample task.
other,22-2-I05-2021,ak
models
</term>
, in particular with the
<term>
Senseval series of workshops
</term>
. At the same time , the recent improvements
#6394Much effort has been put in designing and evaluating dedicated word sense disambiguation (WSD) models, in particular with theSenseval series of workshops.
other,37-1-I05-2021,ak
methodology
</term>
and datasets from the
<term>
Senseval-3 Chinese lexical sample task
</term>
. Much effort has been put in designing
#6366We present the first known empirical test of an increasingly common speculative claim, by evaluating a representative Chinese-to-English SMT model directly on word sense disambiguation performance, using standard WSD evaluation methodology and datasets from theSenseval-3 Chinese lexical sample task.
tech,30-6-I05-2021,ak
dedicated
<term>
WSD models
</term>
, and that
<term>
SMT
</term>
should benefit from the better predictions
#6517This tends to support the view that despite recent speculative claims to the contrary, current SMT models do have limitations in comparison with dedicated WSD models, and thatSMT should benefit from the better predictions made by the WSD models.
model,11-5-I05-2021,ak
accuracy
</term>
of current typical
<term>
SMT models
</term>
to be significantly lower than that
#6471We present controlled experiments showing the WSD accuracy of current typicalSMT models to be significantly lower than that of all the dedicated WSD models considered.
model,16-6-I05-2021,ak
speculative claims to the contrary , current
<term>
SMT models
</term>
do have limitations in comparison
#6503This tends to support the view that despite recent speculative claims to the contrary, currentSMT models do have limitations in comparison with dedicated WSD models, and that SMT should benefit from the better predictions made by the WSD models.
model,21-3-I05-2021,ak
translation ( SMT )
</term>
suggests that
<term>
SMT models
</term>
are good at predicting the right
<term>
#6420At the same time, the recent improvements in the BLEU scores of statistical machine translation (SMT) suggests thatSMT models are good at predicting the right translation of the words in source language sentences.
model,7-4-I05-2021,ak
however , the
<term>
WSD accuracy
</term>
of
<term>
SMT models
</term>
has never been evaluated and compared
#6444Surprisingly however, the WSD accuracy ofSMT models has never been evaluated and compared with that of the dedicated WSD models.
other,34-3-I05-2021,ak
<term>
translation
</term>
of the words in
<term>
source language sentences
</term>
. Surprisingly however , the
<term>
#6433At the same time, the recent improvements in the BLEU scores of statistical machine translation (SMT) suggests that SMT models are good at predicting the right translation of the words insource language sentences.
tech,13-3-I05-2021,ak
improvements in the
<term>
BLEU scores
</term>
of
<term>
statistical machine translation ( SMT )
</term>
suggests that
<term>
SMT models
</term>
#6412At the same time, the recent improvements in the BLEU scores ofstatistical machine translation ( SMT ) suggests that SMT models are good at predicting the right translation of the words in source language sentences.
other,29-3-I05-2021,ak
</term>
are good at predicting the right
<term>
translation
</term>
of the words in
<term>
source language
#6428At the same time, the recent improvements in the BLEU scores of statistical machine translation (SMT) suggests that SMT models are good at predicting the righttranslation of the words in source language sentences.
model,10-2-I05-2021,ak
designing and evaluating dedicated
<term>
word sense disambiguation ( WSD ) models
</term>
, in particular with the
<term>
Senseval
#6382Much effort has been put in designing and evaluating dedicatedword sense disambiguation ( WSD ) models, in particular with the Senseval series of workshops.
measure(ment),23-1-I05-2021,ak
Chinese-to-English SMT model
</term>
directly on
<term>
word sense disambiguation performance
</term>
, using standard
<term>
WSD evaluation
#6352We present the first known empirical test of an increasingly common speculative claim, by evaluating a representative Chinese-to-English SMT model directly onword sense disambiguation performance, using standard WSD evaluation methodology and datasets from the Senseval-3 Chinese lexical sample task.
measure(ment),4-4-I05-2021,ak
</term>
. Surprisingly however , the
<term>
WSD accuracy
</term>
of
<term>
SMT models
</term>
has never
#6441Surprisingly however, theWSD accuracy of SMT models has never been evaluated and compared with that of the dedicated WSD models.
measure(ment),6-5-I05-2021,ak
controlled experiments showing the
<term>
WSD accuracy
</term>
of current typical
<term>
SMT models
#6466We present controlled experiments showing theWSD accuracy of current typical SMT models to be significantly lower than that of all the dedicated WSD models considered.
tech,30-1-I05-2021,ak
performance
</term>
, using standard
<term>
WSD evaluation methodology
</term>
and datasets from the
<term>
Senseval-3
#6359We present the first known empirical test of an increasingly common speculative claim, by evaluating a representative Chinese-to-English SMT model directly on word sense disambiguation performance, using standardWSD evaluation methodology and datasets from the Senseval-3 Chinese lexical sample task.
model,20-4-I05-2021,ak
compared with that of the dedicated
<term>
WSD models
</term>
. We present controlled experiments
#6457Surprisingly however, the WSD accuracy of SMT models has never been evaluated and compared with that of the dedicatedWSD models.
model,23-5-I05-2021,ak
lower than that of all the dedicated
<term>
WSD models
</term>
considered . This tends to support
#6483We present controlled experiments showing the WSD accuracy of current typical SMT models to be significantly lower than that of all the dedicatedWSD models considered.
model,25-6-I05-2021,ak
limitations in comparison with dedicated
<term>
WSD models
</term>
, and that
<term>
SMT
</term>
should
#6512This tends to support the view that despite recent speculative claims to the contrary, current SMT models do have limitations in comparison with dedicatedWSD models, and that SMT should benefit from the better predictions made by the WSD models.