A comparative evaluation of data-driven models in translation selection of machine translation

Citations Over TimeTop 18% of 2002 papers

Abstract

We present a comparative evaluation of two data-driven models used in translation selection of English-Korean machine translation. Latent semantic analysis(LSA) and probabilistic latent semantic analysis (PLSA) are applied for the purpose of implementation of data-driven models in particular. These models are able to represent complex semantic structures of given contexts, like text passages. Grammatical relationships, stored in dictionaries, are utilized in translation selection essentially. We have used k-nearest neighbor (k-NN) learning to select an appropriate translation of the unseen instances in the dictionary. The distance of instances in k-NN is computed by estimating the similarity measured by LSA and PLSA. For experiments, we used TREC data(AP news in 1988) for constructing latent semantic spaces of two models and Wall Street Journal corpus for evaluating the translation accuracy in each model. PLSA selected relatively more accurate translations than LSA in the experiment, irrespective of the value of k and the types of grammatical relationship.

Related Papers

• → Automatic essay grading with probabilistic latent semantic analysis(2005)57 cited
• Comparison of Latent Semantic Analysis and Probabilistic Latent Semantic Analysis for Documents Clustering(2015)
• → Feasible settings for the adaptive latent semantic analysis: Hk-LSA model(2017)2 cited
• → Comparing the Performance of Latent Semantic Analysis and Probability Latent Semantic Analysis Models on Autoscoring Essay Tasks(2017)1 cited
• → Latent Semantic Analysis(2023)