The String-to-String Correction Problem
Journal of the ACM (JACM)
Automatic scoring of pronunciation quality
Speech Communication
A vector space model for automatic indexing
Communications of the ACM
A tutorial on support vector regression
Statistics and Computing
Automated Japanese Essay Scoring System: Jess
DEXA '04 Proceedings of the Database and Expert Systems Applications, 15th International Workshop
Automated rating of ESL essays
HLT-NAACL-EDUC '03 Proceedings of the HLT-NAACL 03 workshop on Building educational applications using natural language processing - Volume 2
WordNet: similarity - measuring the relatedness of concepts
AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Automatic essay grading with probabilistic latent semantic analysis
EdAppsNLP 05 Proceedings of the second workshop on Building Educational Applications Using NLP
OpenFst: a general and efficient weighted finite-state transducer library
CIAA'07 Proceedings of the 12th international conference on Implementation and application of automata
Using entity-based features to model coherence in student essays
HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Modeling organization in student essays
EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
An Unsupervised Automated Essay Scoring System
IEEE Intelligent Systems
LIBSVM: A library for support vector machines
ACM Transactions on Intelligent Systems and Technology (TIST)
A new dataset and method for automatically grading ESOL texts
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
| Hi-index | 0.00 |
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.