Repairing Incorrect Translation with Examples
نویسندگان
چکیده
This paper proposes an example driven approach to improve the quality of MT system outputs. Specifically, We extend the system combination method in SMT to combine the examples by two strategies: 1) estimating the confidence of examples by the similarity between source input and the source part of examples; 2) approximating target word posterior probability by the word alignments of the bilingual examples. Experimental results show a significant improvement of 0.64 BLEU score as compared to one online translation service (Google Translate).
منابع مشابه
Kyoto-U: Syntactical EBMT System for NTCIR-7 Patent Translation Task
This paper describes “Kyoto-U” MT system that attended the patent translation task at NTCIR-7. Example-based machine translation is applied in this system to integrate our study on both structural NLP and machine translation. In the alignment step, consistency criteria are applied to solve the alignment ambiguities and to discard incorrect alignment candidates. In the translation step, translat...
متن کاملThe Problem of Accuracy as an Evaluation Criterion
In this position paper, I argue that for a particular class of problems, the widely adopted evaluation criterion, accuracy, is an incorrect measure. I describe the general characteristics of this class of problems and why accuracy is not a suitable evaluation method, using examples from computer vision, machine translation and music information processing.
متن کاملA Pattern-Learning Based, Hybrid Model for the Syntactic Analysis of Structural Relationships among Japanese Clauses
This paper presents a model for analyzing Japanese compound sentences by taking advantage of user's examples. Syntactic analysis of the Japanese compound sentences is one of the most difficult problems for machine translation (MT) systems. One particularly difficult problem is selecting, from all possible candidates, the correct global structure of an individual sentence, i.e. recognizing the s...
متن کاملGenerate and Repair Machine Translation
We propose Generate and Repair Machine Translation (GRMT), a constraint-based approach to machine translation that focuses on accurate translation output. GRMT performs the translation by generating a Translation Candidate (TC), verifying the syntax and semantics of the TC and repairing the TC when required. GRMT comprises three modules: Analysis Lite Machine Translation (ALMT), Translation Can...
متن کاملRepairing Syntax Errors in LR-based Parsers
When a compiler encounters a syntax error, it usually attempts to restart parsing to check the remainder of the input for any further errors. One common method of recovering from syntax errors is to repair the incorrect input string, allowing parsing to continue. This research presents a language independent method for repairing the input string to an LALR(1) parser. The method results in much ...
متن کامل