| lr,14-3-P05-1058,ak | word alignment models </term> with the <term> | large-scale out-of-domain corpus | </term> and the <term> small-scale in-domain | #9731 In this paper, we first train two statistical word alignment models with thelarge-scale out-of-domain corpus and the small-scale in-domain corpus respectively, and then interpolate these two models to improve the domain-specific word alignment. | |
| lr,19-3-P05-1058,ak | out-of-domain corpus </term> and the <term> | small-scale in-domain corpus | </term> respectively , and then interpolate | #9736 In this paper, we first train two statistical word alignment models with the large-scale out-of-domain corpus and thesmall-scale in-domain corpus respectively, and then interpolate these two models to improve the domain-specific word alignment. | |
| lr,9-2-P05-1058,ak | alignment adaptation </term> is to use <term> | out-of-domain corpus | </term> to improve <term> in-domain word alignment | #9708 The basic idea of alignment adaptation is to useout-of-domain corpus to improve in-domain word alignment results. | |
| measure(ment),14-4-P05-1058,ak | word alignment </term> in terms of both <term> | precision | </term> and <term> recall </term> , achieving | #9768 Experimental results show that our approach improves domain-specific word alignment in terms of bothprecision and recall, achieving a relative error rate reduction of 6.56% as compared with the state-of-the-art technologies. | |
| measure(ment),16-4-P05-1058,ak | terms of both <term> precision </term> and <term> | recall | </term> , achieving a <term> relative error | #9770 Experimental results show that our approach improves domain-specific word alignment in terms of both precision andrecall, achieving a relative error rate reduction of 6.56% as compared with the state-of-the-art technologies. | |
| measure(ment),20-4-P05-1058,ak | and <term> recall </term> , achieving a <term> | relative error rate reduction | </term> of 6.56 % as compared with the state-of-the-art | #9774 Experimental results show that our approach improves domain-specific word alignment in terms of both precision and recall, achieving arelative error rate reduction of 6.56% as compared with the state-of-the-art technologies. | |
| model,29-3-P05-1058,ak | respectively , and then interpolate these two <term> | models | </term> to improve the <term> domain-specific | #9746 In this paper, we first train two statistical word alignment models with the large-scale out-of-domain corpus and the small-scale in-domain corpus respectively, and then interpolate these twomodels to improve the domain-specific word alignment. | |
| model,8-3-P05-1058,ak | In this paper , we first train two <term> | statistical word alignment models | </term> with the <term> large-scale out-of-domain | #9725 In this paper, we first train twostatistical word alignment models with the large-scale out-of-domain corpus and the small-scale in-domain corpus respectively, and then interpolate these two models to improve the domain-specific word alignment. | |
| other,13-2-P05-1058,ak | out-of-domain corpus </term> to improve <term> | in-domain word alignment results | </term> . In this paper , we first train | #9712 The basic idea of alignment adaptation is to use out-of-domain corpus to improvein-domain word alignment results. | |
| tech,33-3-P05-1058,ak | two <term> models </term> to improve the <term> | domain-specific word alignment | </term> . Experimental results show that | #9750 In this paper, we first train two statistical word alignment models with the large-scale out-of-domain corpus and the small-scale in-domain corpus respectively, and then interpolate these two models to improve thedomain-specific word alignment. | |
| tech,4-1-P05-1058,ak | models </term> . This paper proposes an <term> | alignment adaptation approach | </term> to improve <term> domain-specific ( | #9687 This paper proposes analignment adaptation approach to improve domain-specific (in-domain) word alignment. | |
| tech,4-2-P05-1058,ak | alignment </term> . The basic idea of <term> | alignment adaptation | </term> is to use <term> out-of-domain corpus | #9703 The basic idea ofalignment adaptation is to use out-of-domain corpus to improve in-domain word alignment results. | |
| tech,7-4-P05-1058,ak | results show that our approach improves <term> | domain-specific word alignment | </term> in terms of both <term> precision </term> | #9761 Experimental results show that our approach improvesdomain-specific word alignment in terms of both precision and recall, achieving a relative error rate reduction of 6.56% as compared with the state-of-the-art technologies. | |
| tech,9-1-P05-1058,ak | adaptation approach </term> to improve <term> | domain-specific ( in-domain ) word alignment | </term> . The basic idea of <term> alignment | #9692 This paper proposes an alignment adaptation approach to improvedomain-specific ( in-domain ) word alignment. |
