Bulgarian-English and English-Bulgarian Machine Translation: System Design and Evaluation
نویسندگان
چکیده
The paper presents a deep factored machine translation (MT) system between English and Bulgarian languages in both directions. The MT system is hybrid. It consists of three main steps: (1) the source-language text is linguistically annotated, (2) it is translated to the target language with the Moses system, and (3) translation is postprocessed with the help of the transferred linguistic annotation from the source text. Besides automatic evaluation we performed manual evaluation over a domain test suite of sentences demonstrating certain phenomena like imperatives, questions, etc.
منابع مشابه
Towards Semantic-based Hybrid Machine Translation between Bulgarian and English
The paper focuses on the creation of a semantic-based hybrid Machine Translation system between Bulgarian and English in the domain of Information Technology. The preprocessing strategies are presented. A method for the substitution of English word forms with the synsets or Bulgarian representative lemmas is discussed. Finally, the creation of a factored model in the Moses system is described.
متن کاملLinguistically-Augmented Bulgarian-to-English Statistical Machine Translation Model
In this paper, we present our linguisticallyaugmented statistical machine translation model from Bulgarian to English, which combines a statistical machine translation (SMT) system (as backbone) with deep linguistic features (as factors). The motivation is to take advantages of the robustness of the SMT system and the linguistic knowledge of morphological analysis and the hand-crafted grammar t...
متن کاملLinguistically-Enriched Models for Bulgarian-to-English Machine Translation
In this paper, we present our linguisticallyenriched Bulgarian-to-English statistical machine translation model, which takes a statistical machine translation (SMT) system as backbone various linguistic features as factors. The motivation is to take advantages of both the robustness of the SMT system and the rich linguistic knowledge from morphological analysis as well as the hand-crafted gramm...
متن کاملFactored Models for Deep Machine Translation
In this paper, we present some preliminary results on Statistical Machine Translation from Bulgarian-to-English and English-to-Bulgarian. Linguistic knowledge has been added gradually as factors in the MOSES system. The tests were performed on the QTLeap corpus data in IT domain for Pilot 1. The training was done on news parallel data as well as on IT domain data. The BLEU scores show that the ...
متن کاملBulgarian-English Question Answering: Adaptation of Language Resources
This paper describes the Bulgarian part of a Bulgarian–English question answering system. The Bulgarian modules are implemented as a question analysis procedure within a Bulgarian question answering system — BulQA. The paper presents the available language resources and corresponding technology which is used for the analysis of the questions in Bulgarian and their translation into English forma...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2017