Supervised and unsupervised stemming reduced Telugu broadcast news ASR word error rate from 18.69% to 17.93% and 16.97%, respectively, with Kneser-Ney smoothing.
https://www.iitm.ac.in/donlab/tts/downloads/cls/cls_v2.1.6.pdf
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Unsupervised Stemming based Language Model for Telugu Broadcast News Transcription
Supervised and unsupervised stemming reduced Telugu broadcast news ASR word error rate from 18.69% to 17.93% and 16.97%, respectively, with Kneser-Ney smoothing.