Paper Info
Title
Automated essay scoring based on finite state transducer: towards ASR transcription of oral English speech
Abstract
Conventional Automated Essay Scoring (AES) measures may cause severe problems when directly applied in scoring Automatic Speech Recognition (ASR) transcription as they are error sensitive and unsuitable for the characteristic of ASR transcription. Therefore, we introduce a framework of Finite State Transducer (FST) to avoid the shortcomings. Compared with the Latent Semantic Analysis with Support Vector Regression (LSA-SVR) method (stands for the conventional measures), our FST method shows better performance especially towards the ASR transcription. In addition, we apply the synonyms similarity to expand the FST model. The final scoring performance reaches an acceptable level of 0.80 which is only 0.07 lower than the correlation (0.87) between human raters.
Year
Venue
Keywords
2012
ACL
oral english speech,fst method,support vector regression,scoring automatic speech recognition,latent semantic analysis,asr transcription,finite state transducer,final scoring performance,conventional automated essay scoring,automated essay,better performance,fst model
Field
DocType
Volume
Computer science,Support vector machine,Automated essay scoring,Speech recognition,Correlation,Artificial intelligence,Natural language processing,Latent semantic analysis,Finite state transducer
Conference
P12-1
Citations 
PageRank 
References 
0
0.34
15
Authors
3
Name
Order
Citations
PageRank
Xingyuan Peng141.46
Dengfeng Ke2134.13
Bo Xu324136.59