| tech,23-1-P01-1004,bq | <term> retrieval performance </term> of a <term> | translation | memory system </term> . We take a selection | #1484 In this paper, we compare the relative effects of segment order, segmentation and segment contiguity on the retrieval performance of atranslation memory system. |
| other,9-2-A94-1017,bq | translation </term> requires ( 1 ) an accurate <term> | translation | </term> and ( 2 ) a <term> real-time response | #20219 Spoken language translation requires (1) an accuratetranslation and (2) a real-time response. |
| tech,4-3-P01-1007,bq | complexity </term> . For example , after <term> | translation | </term> into an equivalent <term> RCG </term> | #1659 For example, aftertranslation into an equivalent RCG, any tree adjoining grammar can be parsed in O(n6) time. |
| tech,14-5-P05-1069,bq | </term> on a standard <term> Arabic-English | translation | task </term> . Previous work has used <term> | #9651 The best system obtains a 18.6% improvement over the baseline on a standard Arabic-English translation task. |
| other,34-1-C90-3045,bq | semantic interpretation </term> or <term> automatic | translation | of natural language </term> . We present | #16460 The unique properties of tree-adjoining grammars (TAG) present a challenge for the application of TAGs beyond the limited confines of syntax, for instance, to the task of semantic interpretation or automatic translation of natural language. |
| measure(ment),31-3-P05-1048,bq | does not yield significantly better <term> | translation | quality </term> than the <term> statistical | #9378 Using a state-of-the-art Chinese word sense disambiguation model to choose translation candidates for a typical IBM statistical MT system, we find that word sense disambiguation does not yield significantly bettertranslation quality than the statistical machine translation system alone. |
| measure(ment),17-8-P05-1067,bq | the <term> IBM models </term> in both <term> | translation | speed and quality </term> . In this paper | #9544 The result shows that our system outperforms the baseline system based on the IBM models in bothtranslation speed and quality. |
| tech,6-3-I05-2048,bq | particularly important when building <term> | translation | systems </term> for new <term> language pairs | #8047 This is particularly important when buildingtranslation systems for new language pairs or new domains. |
| other,10-4-N04-1022,bq | decoders </term> on a <term> Chinese-to-English | translation | task </term> . Our results show that <term> | #6623 We report the performance of the MBR decoders on a Chinese-to-English translation task. |
| other,10-3-P05-1048,bq | disambiguation model </term> to choose <term> | translation | candidates </term> for a typical <term> IBM | #9357 Using a state-of-the-art Chinese word sense disambiguation model to choosetranslation candidates for a typical IBM statistical MT system, we find that word sense disambiguation does not yield significantly better translation quality than the statistical machine translation system alone. |
| this approach is that knowledge concerning | translation | equivalence of expressions may be directly | #15073 The principle advantage of this approach is that knowledge concerning translation equivalence of expressions may be directly exploited, obviating the need for answers to semantic questions that we do not yet have. | |
| tech,16-1-C90-1013,bq | generation </term> , developed for a <term> dialogue | translation | system </term> . The <term> system </term> utilizes | #16227 This article introduces a bidirectional grammar generation system called feature structure-directed generation, developed for a dialogue translation system. |
| other,19-9-H01-1042,bq | sample output to be an <term> expert human | translation | </term> or a <term> machine translation </term> | #733 The subjects were given three minutes per extract to determine whether they believed the sample output to be an expert human translation or a machine translation. |
| measure(ment),20-3-P05-1032,bq | orders of magnitude with no loss in <term> | translation | quality </term> . We describe a novel <term> | #9198 We show how sampling can be used to reduce the retrieval time by orders of magnitude with no loss intranslation quality. |
| lr,9-1-H05-2007,bq | systematic <term> patterns </term> in <term> | translation | data </term> using <term> part-of-speech tag | #7637 We describe a method for identifying systematic patterns intranslation data using part-of-speech tag sequences. |
| tech,1-3-P84-1034,bq | important roles . For <term> Japanese-English | translation | </term> , the <term> semantics directed approach | #13257 For Japanese-English translation, the semantics directed approach is powerful where the Conceptual Dependency Diagram (CDD) and the Augmented Case Marker System (which is a kind of Semantic Role System) play essential roles. |
| tool,1-2-H01-1041,bq | </term> . The <term> CCLINC Korean-to-English | translation | system </term> consists of two <term> core | #414 The CCLINC Korean-to-English translation system consists of two core modules, language understanding and generation modules mediated by a language neutral meaning representation called a semantic frame. |
| other,0-2-A94-1017,bq | translation </term> . <term> Spoken language | translation | </term> requires ( 1 ) an accurate <term> translation | #20212 Spoken language translation requires (1) an accurate translation and (2) a real-time response. |
| other,14-9-A94-1017,bq | vital requirements of <term> spoken language | translation | </term> . <term> Japanese texts </term> frequently | #20364 Thus, our model, TDMT on APs, meets the vital requirements of spoken language translation. |
| other,12-1-A94-1017,bq | </term> for <term> real-time spoken language | translation | </term> . <term> Spoken language translation | #20208 This paper proposes a model using associative processors (APs) for real-time spoken language translation. |
