SMT Errors Requiring Grammatical Knowledge for Prevention
نویسنده
چکیده
This paper introduces three types of Statistical Machine Translation (SMT) output errors that would require grammatical knowledge for prevention. The first type is due to words that are negative in meaning but not in form. Problems arise when the negative forms are obligatory in target languages. The second type of errors is derived from the rigidity of pattern phrases or correlatives which do not allow for intervening elements. The third type is caused by ellipses in input sentences which must be reinstated for output sentences when so required by rules of omission in target languages or the difference in Head-Complement order between source and target languages.
منابع مشابه
The Effect of Learner Corpus Size in Grammatical Error Correction of ESL Writings
English as a Second Language (ESL) learners’ writings contain various grammatical errors. Previous research on automatic error correction for ESL learners’ grammatical errors deals with restricted types of learners’ errors. Some types of errors can be corrected by rules using heuristics, while others are difficult to correct without statistical models using native corpora and/or learner corpora...
متن کاملUsing Parallel Features in Parsing of Machine-Translated Sentences for Correction of Grammatical Errors
In this paper, we present two dependency parser training methods appropriate for parsing outputs of statistical machine translation (SMT), which pose problems to standard parsers due to their frequent ungrammaticality. We adapt the MST parser by exploiting additional features from the source language, and by introducing artificial grammatical errors in the parser training data, so that the trai...
متن کاملDiscriminative Reranking for Grammatical Error Correction with Statistical Machine Translation
Research on grammatical error correction has received considerable attention. For dealing with all types of errors, grammatical error correction methods that employ statistical machine translation (SMT) have been proposed in recent years. An SMT system generates candidates with scores for all candidates and selects the sentence with the highest score as the correction result. However, the 1-bes...
متن کاملA Neural Network Architecture for Detecting Grammatical Errors in Statistical Machine Translation
In this paper we present a Neural Network (NN) architecture for detecting grammatical errors in Statistical Machine Translation (SMT) using monolingual morpho-syntactic word representations in combination with surface and syntactic context windows. We test our approach on two language pairs and two tasks, namely detecting grammatical errors and predicting overall post-editing effort. Our result...
متن کاملNTCIR-7 Patent Translation Experiments at Hitachi
Statistical Machine Translation (SMT) is a new paradigm in machine translation, which enables highquality translation. However, many translation errors occur in the translation of complex and compound sentences because of the lack of grammatical knowledge about the global structure of a sentence. We adopt the pre-editing method, which divides sentences into clauses, and translate these clauses ...
متن کامل