| P03-1057 | exploration of several measures for | feedback cleaning | remains an interesting future |
| P03-1057 | Evaluation Methods The idea of | feedback cleaning | is independent of BLEU . Some |
| P03-1057 | these methods . The effects of | feedback cleaning | depend on the characteristics |
| P03-1057 | observe the characteristics of | feedback cleaning | , cleaning of the base rule set |
| P03-1057 | . 4 . Simple Feedback Cleaning | Feedback cleaning | was carried out using the evaluation |
| P03-1057 | k2 ≥ 3.841 ) . 4 . Simple | Feedback Cleaning | Feedback cleaning was carried |
| P03-1057 | , in the same way used for the | feedback cleaning | . A total of 510 sentences from |
| P03-1057 | introduce the proposed method , called | feedback cleaning | . This method is carried out |
| P03-1057 | this section , the effects of | feedback cleaning | are evaluated by using English-to-Japanese |
| P03-1057 | output scores are applicable to | feedback cleaning | . The characteristics common |
| P03-1057 | is applied to the cleaning . 4 | Feedback Cleaning | In this section , we introduce |
| P03-1057 | base rule set . 4 . Apply the | feedback cleaning | algorithm to each of the N pairs |
| P03-1057 | evaluation corpus and carry out | feedback cleaning | , the rule set will be adapted |
| P03-1057 | In this paper , we proposed a | feedback cleaning | method that utilizes automatic |
| P03-1057 | sentences requires a high cost . The | feedback cleaning | proposed in this paper can be |
| P03-1057 | the proposed methods ( simple | feedback cleaning | and cross-cleaning ) are considerably |
| P03-1057 | ( AQUAINT ) Program . <title> | Feedback Cleaning | of Machine Translation Rules |
| P03-1057 | ( 1 ) # of test sentences 6.2 | Feedback Cleaning | Using Evaluation Corpus In order |
| W11-0814 | investigating two solutions . One is | feedback cleaning | , where we investigate the impact |
| P03-1057 | rules , the rule set of the simple | feedback cleaning | is clearly a locally optimal |
