Semantically Governed Machine Translation of BE-clauses with Adverbs and Prepositional Phrases. Demonstration of a Ring-Model for German/English, English/German including Analysis-Synthesis, Transformation, Transition, and Generation
نویسنده
چکیده
Research in methods of lexicalization, classification, analysis-synthesis, transformation, transition, and generation, which has been carried on independently in the German and English sections at LIMAS, has recently been consolidated for the purpose of constructing a Ring-Translation-Model This model has to meet the following requirements: I. It must;produce a translation which is identical in meaning to the original and stylistically acceptable. 2. Some Of the difficulties which have heretofore appeared in machine translation must be resolved. The starting point (Figure I) is a German adverbial phrase, which is to be analyzed and then converted into a factor formula by means of a morpho-nomo-transformation. An explicative homo-homo-transformation together with prepositional governing factors then expand the factor formula for the adverbial expression into a formula for a prepositional phrase, which in turn becomes ex-pressible through a nomo-morpho-transformation. The factor formula for the German prepositional phrase is converted into an English factor formula according to the coordinator's system of maximum agreement. This takes place through a nomo-nomo-transition if the identical factor formula is present in English, otherwise through a nomo-~omme~ra~afQ~mation. A nomo-morpho-tr&nsformation then creates an expressible English prepositional phrase which is semantically equivalent to the German. The factor formula for an English adverbial phrase is made possible by a reductive nomo-homo-transformation plus a nomo-morpho-transformation. The last step of the cycle again takes place in the coordinator. The factor formula for the English adverbial phrase is converted into the corresponding formula for the German adverbial phrase by means of transition or a homo-homo-transformation. The morphological realization of this factor formula is identical to that of the initial German adverbial phrase. The automatic reversible process of the ring model is determined by several association lists and function matrices. At first a-I
منابع مشابه
مدل ترجمه عبارت-مرزی با استفاده از برچسبهای کمعمق نحوی
Phrase-boundary model for statistical machine translation labels the rules with classes of boundary words on the target side phrases of training corpus. In this paper, we extend the phrase-boundary model using shallow syntactic labels including POS tags and chunk labels. With the priority of chunk labels, the proposed model names non-terminals with shallow syntactic labels on the boundaries of ...
متن کاملVIRTEX - A German-Russlan Translation Experiment
Machine Translation from German into Russian did not gain the attention it deserves so far. Especially such typical Russian phenomena like the aspect of verbs complicate the translation process. The known MT approaches do not deal with such problems in a satisfactory way. To overcome this lack, we started the German.Russian translation experiment VIRTEX. We focussed our attention on the crucial...
متن کاملVIRTEX - a German-Russian Translation Experiment
Machine Translation from German into Russian did not gain the attention it deserves so far. Especially such typical Russian phenomena like the aspect of verbs complicate the translation process. The known MT approaches do not deal with such problems in a satisfactory way. To overcome this lack, we started the German.Russian translation experiment VIRTEX. We focussed our attention on the crucial...
متن کاملPredicting Target Language CCG Supertags Improves Neural Machine Translation
Neural machine translation (NMT) models are able to partially learn syntactic information from sequential lexical information. Still, some complex syntactic phenomena such as prepositional phrase attachment are poorly modeled. This work aims to answer two questions: 1) Does explicitly modeling target language syntax help NMT? 2) Is tight integration of words and syntax better than multitask tra...
متن کاملSyntax-aware Neural Machine Translation Using CCG
Neural machine translation (NMT) models are able to partially learn syntactic information from sequential lexical information. Still, some complex syntactic phenomena such as prepositional phrase attachment are poorly modeled. This work aims to answer two questions: 1) Does explicitly modeling target language syntax help NMT? 2) Is tight integration of words and syntax better than multitask tra...
متن کامل