... obtaining a complete syntactic analysis of an input, with no signifi- cant semantic analysis; (3) translation proceeds after obtaining a complete semantic analysis of an input. The definition ... (INTO (IN) PREP (GC A)) (IN (IN) PREP (GC O)) Figure 2 Transfer Entries for the German Preposition " ;in& quot; The German PREPosition " ;in& quot; (in parentheses) may trans- late into ... semantic type, and case information (see Figure ]). Transfer lexical entries indicate how and under what conditions words or idioms in one language translate into words or idioms in another (see...
... translator Translation No. 5: a machinetranslation (Machine Program A) Translation No. 7: a machinetranslation (Machine Program B, 2d Pass) Translation No. 9: a machinetranslation (Machine Program ... significantly inferior to human translations 1 and 4, and machine transla- tion 9 is significantly inferior to machine translations 5 and 7. However, human translations 1 and 4 are in no case ... monolinguals’ mean in- telligibility ratings of the 144 sentences in each of six trans- lations. Translations 1, 4, and 2 are human translations; Translations 7, 5, and 9 are machine translations....
... References (2006) Garzanti francese : francese-italiano, italiano-francese. I grandi dizionari Garzanti. Milano, Gar-zanti Linguistica. Amiot, D. (2005) Between compounding and deriva-tion: elements ... im-plementing lexical morphology principles in a machine translation system in order to solve unknown words. Multilingual symbolic treat-ment of word-formation is seducing but re-quires an in- depth ... explain why implementing morphology in the context of ma-chine translation (MT) is a real challenge and what kind of aspects need to be taken into ac-count (section 4), and we show that translating...
... of Germany ABSTRACT There have been various attempts at using the sublanguage notion for disambi- guation and the selection of target language equivalents inmachine translation. In this ... the sublanguage notion for solving some of the notorious problems inmachinetranslation (MT) such as disambiguation and selection of target language equivalents. In the following, I shall ... Zimmermann (1991). Computer-Aided and Machi- ne Translation. Practical Applicati- ons and Applied Research. Saar- briicken: AQ-Verlag Quinlan, E. (1989). Sublanguage and the re- levance...
... the domain of interest is thekey resource when training a statistical ma-chine translation (SMT) system for a specificpurpose. Since ad-hoc manual translation canrepresent a significant investment ... Testing for Statis-tical Machine Translation: Controlling for OptimizerInstability. In Proceedings of the 49th Annual Meet-ing of the Association for Computational Linguistics:Human Language ... online:http://www.itl.nist.gov/div898/handbook/.George Foster and Roland Kuhn. 2009. StabilizingMinimum Error Rate Training. In Proceedings of theFourth Workshop on Statistical Machine Translation, pages...
... ABSTRACT In this paper we provide an abstract characterisation of different kinds of robust processing inMachineTranslation and Natural Language Processing systems in terms of the kinds of ... MACHINETRANSLATION This paper is an attempt to provide part of the basis for a general theory of robust processing inMachineTranslation (MT) with relevance to other areas of Natural Language ... processing, and for which we know of no existing solutions. We discuss two possible approaches to this, emphasising the need to correct or repair processing malfunctions. ROBUST PROCESSING IN MACHINE...
... paper is one in a series which describes the methods now in use for research on machine trans- lation (MT) at The RAND Corporation. Postediting follows mechanical partial translationin the research ... articles a and an are not distinguished. Connections: of, to, by, with, than, as, in, on. English connecting words must be inserted in the absence of a Russian equivalent, in two kinds of context ... adverb. In constructions utilizing a modal (e.g., можно, легко) plus an infinitive, the infinitive is considered the main element in the clause and is said to govern the modal. In such constructions,...
... generally tackled in the translation into Bulgarian, since it is a language usually providing a series of forms for a verb: transitive, intransitive, and transitive /in- transitive, which are ... automatic analysis and synthesis). Scientific and Technical In- formation, Moscow, No.5, 1967. (in Russian). Penchev, J. and V. Perlcllev. 1982. On meaning in theoretical and computational semantics. ... semantics. In: COLING-82, Abstracts, Prague, 1982. Penchev, J. and V. Perlcliev. 1984. On meaning in theoretical and computational semantics. Bulgarian Language, Sofia, No.4, 1984. (in Bulgarian)....
... judgments in its rankings of five Chinese-to-English machine translation systems, and in its ability to distinguishbetween human and machine translations. Bleu’scorrelation with human judgments has ... illustrated in the 2005 NIST Machine Translation Evaluation and our experi-ment manually evaluating Systran and SMT trans-lations.What conclusions can we draw from this?Should we give up on using ... automatic evalu-ation metrics work is to compare the output of a machine translation system against reference hu-man translations. Machinetranslation evaluationmetrics differ from other metrics that...
... phrase-based machinetranslation system. In In Proceedings of the ACL Worskhop on Buildingand Using Parallel Texts, Ann Arbor. ACL.Baskaran Sankaran, Majid Razmara, and Anoop Sarkar.2012. Kriya an end-to-end ... to penalize misleading training instances fromOUT and assign more weight to IN- like instancesthan OUT instances. Foster et al. (2010) propose asimilar method for machinetranslation that uses ... May.NAACL.Yang Liu, Haitao Mi, Yang Feng, and Qun Liu. 2009.Joint decoding with multiple translation models. In Proceedings of the Joint Conference of the 47th An- nual Meeting of the ACL and the 4th InternationalJoint...