English Machine Translation Model Based on an Improved Self-Attention Technology

<table class="table-group" id="tab4"><tr><td><table class="table"><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr class="thead"><td class="align_left">Alignment and reorganization method</td><td class="align_center">BLEU</td></tr><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td class="align_left">Grow-diag-final-and</td><td class="align_center">0.40</td></tr><tr><td class="align_left">Grow-diag-final</td><td class="align_center">0.42</td></tr><tr><td class="align_left">Grow-diag</td><td class="align_center">0.36</td></tr><tr><td class="align_left">Grow</td><td class="align_center">0.34</td></tr><tr><td class="align_left">Intersect</td><td class="align_center">0.32</td></tr><tr><td class="align_left">Union</td><td class="align_center">0.26</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>BLEU scores for nonstrict phrase extraction in <i>n</i>-best alignment.</div>

Scientific Programming

tab4

Table 4

Table 4: English Machine Translation Model Based on an Improved Self-Attention Technology 