Adaptation Guided Retrieval: Approaching EBMT with Caution
نویسندگان
چکیده
Many translation memory tools rely on the assumption that source language constructions correspond more or less isomorphically to their target language counterparts. Cross-linguistic divergences and non-linguistic factors such as translator stylistics clearly make the assumption false, so there is a need for sub-sentential linkage between any two languages. The strength of these links determines how adaptable a particular translation is in the context of a given problem sentence, and we use this as our main selection criterion. Our cautious approach to EBMT is inspired by current adaptationguided methodologies shown to be successful in other case based reasoning domains.
منابع مشابه
Adaptation Guided Retrieval in EBMT: A Case-Based Approach to Machine Translation
In this paper we describe a methodological analysis of EBMT (Examplebased Machine Translation) based on a CBR (Case-Based Reasoning) perspective. This analysis focuses on adaptation. We argue that, just as in CBR, the overall power of an EBMT system is its ability to adapt examples retrieved to suit the new problem translation. Here we describe a technique whereby reusability is a function of t...
متن کاملAn Example-based Approach to Machine Translation
In this paper we describe a methodological analysis of EBMT (Example-Based Machine Translation) based on a CBR (Case-Based Reasoning) perspective. This analysis focuses on adaptation. We argue that, just as in CBR, the overall power of an EBMT system is its ability to adapt examples retrieved to suit the new problem translation. Here we describe a technique whereby reusability is a function of ...
متن کاملIdentification of Divergence for English to Hindi EBMT
Divergence is a key aspect of translation between two languages. Divergence occurs when structurally similar sentences of the source language do not translate into sentences that are similar in structures in the target language. Divergence assumes special significance in the domain of Example-Based Machine Translation (EBMT). An EBMT system generates translation of a given sentence by retrievin...
متن کاملAn Ensemble Approach to Adaptation-Guided Retrieval
Instance-based learning methods predict the solution of a case from the solutions of similar cases. However, solutions can be generated from less similar cases as well, provided appropriate “case adaptation” rules are available to adjust the prior solutions to account for dissimilarities. In fact, case-based reasoning research on adaptation-guided retrieval (AGR) shows that it may be beneficial...
متن کاملAdaptation-Guided Retrieval Using Adaptation Knowledge to Guide the Retrieval of Adaptable Cases
Adaptation-guided retrieval is a case retrieval technique that uses “adaptability” as its core selection criterion. This means that cases are chosen for reuse according to how readily they can be adapted to fit the target problem requirements. This makes a change from traditional retrieval methods, which have concentrated on estimating adaptability in terms of semantic similarity. Unfortunately...
متن کامل