tech,11-2-C04-1080,bq |
first comprehensive comparison of
<term>
|
unsupervised methods for part-of-speech tagging
|
</term>
, noting that published results to
|
#5537
Along the way, we present the first comprehensive comparison ofunsupervised methods for part-of-speech tagging, noting that published results to date have not been comparable across corpora or lexicons. |
tech,17-3-C04-1080,bq |
</term>
that can be achieved by the
<term>
|
algorithms
|
</term>
, we present a method of
<term>
HMM
|
#5575
Observing that the quality of the lexicon greatly impacts the accuracy that can be achieved by thealgorithms, we present a method of HMM training that improves accuracy when training of lexical probabilities is unstable. |
other,25-1-C04-1080,bq |
tagged , and evaluate it in both the
<term>
|
unsupervised and supervised case
|
</term>
. Along the way , we present the
|
#5521
We present a new HMM tagger that exploits context on both sides of a word to be tagged, and evaluate it in both theunsupervised and supervised case. |
lr,30-2-C04-1080,bq |
comparable across
<term>
corpora
</term>
or
<term>
|
lexicons
|
</term>
. Observing that the quality of the
|
#5556
Along the way, we present the first comprehensive comparison of unsupervised methods for part-of-speech tagging, noting that published results to date have not been comparable across corpora orlexicons. |
tech,13-4-C04-1080,bq |
achieves state-of-the-art results in a
<term>
|
supervised , non-training intensive framework
|
</term>
. Past work of
<term>
generating referring
|
#5608
Finally, we show how this new tagger achieves state-of-the-art results in asupervised , non-training intensive framework. |
tech,7-4-C04-1080,bq |
unstable . Finally , we show how this new
<term>
|
tagger
|
</term>
achieves state-of-the-art results
|
#5602
Finally, we show how this newtagger achieves state-of-the-art results in a supervised, non-training intensive framework. |
lr,6-3-C04-1080,bq |
Observing that the quality of the
<term>
|
lexicon
|
</term>
greatly impacts the
<term>
accuracy
|
#5564
Observing that the quality of thelexicon greatly impacts the accuracy that can be achieved by the algorithms, we present a method of HMM training that improves accuracy when training of lexical probabilities is unstable. |
other,32-3-C04-1080,bq |
<term>
accuracy
</term>
when training of
<term>
|
lexical probabilities
|
</term>
is unstable . Finally , we show how
|
#5590
Observing that the quality of the lexicon greatly impacts the accuracy that can be achieved by the algorithms, we present a method of HMM training that improves accuracy when training oflexical probabilities is unstable. |
other,8-1-C04-1080,bq |
<term>
HMM tagger
</term>
that exploits
<term>
|
context
|
</term>
on both sides of a
<term>
word
</term>
|
#5504
We present a new HMM tagger that exploitscontext on both sides of a word to be tagged, and evaluate it in both the unsupervised and supervised case. |
lr,28-2-C04-1080,bq |
date have not been comparable across
<term>
|
corpora
|
</term>
or
<term>
lexicons
</term>
. Observing
|
#5554
Along the way, we present the first comprehensive comparison of unsupervised methods for part-of-speech tagging, noting that published results to date have not been comparable acrosscorpora or lexicons. |
measure(ment),10-3-C04-1080,bq |
<term>
lexicon
</term>
greatly impacts the
<term>
|
accuracy
|
</term>
that can be achieved by the
<term>
|
#5568
Observing that the quality of the lexicon greatly impacts theaccuracy that can be achieved by the algorithms, we present a method of HMM training that improves accuracy when training of lexical probabilities is unstable. |
tech,4-1-C04-1080,bq |
effect on both tasks . We present a new
<term>
|
HMM tagger
|
</term>
that exploits
<term>
context
</term>
|
#5500
We present a newHMM tagger that exploits context on both sides of a word to be tagged, and evaluate it in both the unsupervised and supervised case. |
tech,24-3-C04-1080,bq |
algorithms
</term>
, we present a method of
<term>
|
HMM training
|
</term>
that improves
<term>
accuracy
</term>
|
#5582
Observing that the quality of the lexicon greatly impacts the accuracy that can be achieved by the algorithms, we present a method ofHMM training that improves accuracy when training of lexical probabilities is unstable. |
other,14-1-C04-1080,bq |
<term>
context
</term>
on both sides of a
<term>
|
word
|
</term>
to be tagged , and evaluate it in
|
#5510
We present a new HMM tagger that exploits context on both sides of aword to be tagged, and evaluate it in both the unsupervised and supervised case. |
measure(ment),28-3-C04-1080,bq |
<term>
HMM training
</term>
that improves
<term>
|
accuracy
|
</term>
when training of
<term>
lexical probabilities
|
#5586
Observing that the quality of the lexicon greatly impacts the accuracy that can be achieved by the algorithms, we present a method of HMM training that improvesaccuracy when training of lexical probabilities is unstable. |