| model,11-5-A94-1017,ak | example-retrieval ( ER ) </term> , i.e. , retrieving <term> | examples | </term> most similar to an <term> input expression | #26164 In TDMT, example-retrieval (ER), i.e., retrievingexamples most similar to an input expression, is the most dominant part of the total processing time. | |
| model,19-3-A94-1017,ak | translates a <term> sentence </term> utilizing <term> | examples | </term> effectively and performs accurate | #26132 We have already proposed a model, TDMT (Transfer-Driven Machine Translation), that translates a sentence utilizingexamples effectively and performs accurate structural disambiguation and target word selection. | |
| other,10-8-A94-1017,ak | between <term> APs </term> demonstrates the <term> | scalability | </term> against <term> vocabulary size </term> | #26226 Moreover, a study on communications between APs demonstrates thescalability against vocabulary size by extrapolation. | |
| other,12-8-A94-1017,ak | the <term> scalability </term> against <term> | vocabulary size | </term> by <term> extrapolation </term> . Thus | #26228 Moreover, a study on communications between APs demonstrates the scalability againstvocabulary size by extrapolation. | |
| other,13-6-A94-1017,ak | to implement the <term> ER </term> for <term> | expressions | </term> including a <term> frequent word </term> | #26196 Our study has concluded that we only need to implement the ER forexpressions including a frequent word on APs. | |
| other,16-5-A94-1017,ak | <term> examples </term> most similar to an <term> | input expression | </term> , is the most dominant part of the | #26169 In TDMT, example-retrieval (ER), i.e., retrieving examples most similar to aninput expression, is the most dominant part of the total processing time. | |
| other,16-6-A94-1017,ak | <term> expressions </term> including a <term> | frequent word | </term> on <term> APs </term> . Experimental | #26199 Our study has concluded that we only need to implement the ER for expressions including afrequent word on APs. | |
| other,17-3-A94-1017,ak | Translation ) </term> , that translates a <term> | sentence | </term> utilizing <term> examples </term> effectively | #26130 We have already proposed a model, TDMT (Transfer-Driven Machine Translation), that translates asentence utilizing examples effectively and performs accurate structural disambiguation and target word selection. | |
| tech,0-2-A94-1017,ak | spoken language translation </term> . <term> | Spoken language translation | </term> requires ( 1 ) an accurate <term> translation | #26095 This paper proposes a model using associative processors (APs) for real-time spoken language translation.Spoken language translation requires (1) an accurate translation and (2) a real-time response. | |
| tech,1-5-A94-1017,ak | concentrate on the second requirement . In <term> | TDMT | </term> , <term> example-retrieval ( ER ) </term> | #26154 InTDMT, example-retrieval (ER), i.e., retrieving examples most similar to an input expression, is the most dominant part of the total processing time. | |
| tech,11-6-A94-1017,ak | that we only need to implement the <term> | ER | </term> for <term> expressions </term> including | #26194 Our study has concluded that we only need to implement theER for expressions including a frequent word on APs. | |
| tech,12-1-A94-1017,ak | associative processors ( APs ) </term> for <term> | real-time spoken language translation | </term> . <term> Spoken language translation | #26090 This paper proposes a model using associative processors (APs) forreal-time spoken language translation. | |
| tech,14-9-A94-1017,ak | </term> , meets the vital requirements of <term> | spoken language translation | </term> . <term> Japanese texts </term> frequently | #26247 Thus, our model, TDMT on APs, meets the vital requirements ofspoken language translation. | |
| tech,15-8-A94-1017,ak | against <term> vocabulary size </term> by <term> | extrapolation | </term> . Thus , our model , <term> TDMT </term> | #26231 Moreover, a study on communications between APs demonstrates the scalability against vocabulary size byextrapolation. | |
| tech,19-6-A94-1017,ak | including a <term> frequent word </term> on <term> | APs | </term> . Experimental results show that | #26202 Our study has concluded that we only need to implement the ER for expressions including a frequent word onAPs. | |
| tech,24-3-A94-1017,ak | </term> effectively and performs accurate <term> | structural disambiguation | </term> and <term> target word selection </term> | #26137 We have already proposed a model, TDMT (Transfer-Driven Machine Translation), that translates a sentence utilizing examples effectively and performs accuratestructural disambiguation and target word selection. | |
| tech,27-3-A94-1017,ak | structural disambiguation </term> and <term> | target word selection | </term> . This paper will concentrate on | #26140 We have already proposed a model, TDMT (Transfer-Driven Machine Translation), that translates a sentence utilizing examples effectively and performs accurate structural disambiguation andtarget word selection. | |
| tech,3-5-A94-1017,ak | requirement . In <term> TDMT </term> , <term> | example-retrieval ( ER ) | </term> , i.e. , retrieving <term> examples | #26156 In TDMT,example-retrieval ( ER ), i.e., retrieving examples most similar to an input expression, is the most dominant part of the total processing time. | |
| tech,5-7-A94-1017,ak | Experimental results show that the <term> | ER | </term> can be drastically speeded up . Moreover | #26209 Experimental results show that theER can be drastically speeded up. | |
| tech,5-9-A94-1017,ak | extrapolation </term> . Thus , our model , <term> | TDMT | </term> on <term> APs </term> , meets the vital | #26238 Thus, our model,TDMT on APs, meets the vital requirements of spoken language translation. |
