Deciphering Related Languages
نویسندگان
چکیده
We present a method for translating texts between close language pairs. The method does not require parallel data, and it does not require the languages to be written in the same script. We show results for six language pairs: Afrikaans/Dutch, Bosnian/Serbian, Danish/Swedish, Macedonian/Bulgarian, Malaysian/Indonesian, and Polish/Belorussian. We report BLEU scores showing our method to outperform others that do not use parallel data.
منابع مشابه
Deciphering Methods as a Means of Linguistic Research
Methods of linguistic deciphering may be regarded as a set of procedures aimed at the recognition of linguistic objects in a text whose language is not known to the investigator. They combine many advantages of the formal approach to language. Assuming that each deciphering procedure may serve as a definition of the respective linguistic object we may view the set of such procedures as a certai...
متن کاملOptimization algorithms of deciphering as the elements of a linguistic theory
This paper presents an outline of the linguistic theory which may be identified with the partially ordered set of optimization algorithms of deciphering. An algorith~L of deciphering is the operational definition of a given linguistic phenomenon which ha~, the following three components: a set of admissible solutions, an objective function and a proaodure which finds out the mini,4~m or the max...
متن کاملIdentity and Representation through Language in Ghana: The Postcolonial Self and the Other
Research related to colonialism and post colonialism shows how the identities of indigenous people were constructed and how these identities are reconstructed in our contemporary world. The thrust of this paper is that colonialism brought a shift in the linguistic structure of Ghana with the introduction of the use of English among Ghanaians. The coexistence of both Ghanaian languages and Engli...
متن کاملDuplicate Detection for Symbolically Compressed Documents
A new family of symbolic compression algorithms has recently been developed that includes the ongoing JBIG2 standardization effort as well as related commercial products. These techniques are specifically designed for binary document images. They cluster individual blobs in a document and store the sequence of occurrence of blobs and representative blob templates, hence the name symbolic compre...
متن کاملSome Properties of Codes with Infinite Deciphering Delay
In 2013, Tommi Lehtinen and Alexander Okhotin proved that if X is a code, then it has infinite deciphering delay if and only if there exist + ∈ A z y x , , with * , , , X zy yz xy x ∈ and * , X z y ∉ . In this paper, we give a sufficient and necessary condition for codes with infinite deciphering delay. Then, we construct two kinds of three-element codes with infinite deciphering delay.
متن کامل