【正文】
Shouxun Lin. 2020. Treetostring alignment template for statistical machine translation. In ColingACL 2020: Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics。討論 ? 參與了兩個(gè)單元的評測 ? 試圖在 SMT系統(tǒng)中結(jié)合句法知識 ? 試圖在詞對齊中結(jié)合 ITG約束 ? 在模型訓(xùn)練及解碼過程中結(jié)合 ITG約束和句法分析樹知識 ? 結(jié)果不同 ? 在中 英新聞任務(wù)中,采用同構(gòu)模型提高了翻譯質(zhì)量, ? 在英 中科技任務(wù)中,同構(gòu)模型的采用產(chǎn)生了負(fù)面影響,具體的原因我們將在后續(xù)進(jìn)一步研究 計(jì)算機(jī)學(xué)院 17 主要參考文獻(xiàn) ? Franz Joseph Och and Hermann Ney. 2020. A Systematic Comparison of Various Statistical Alignment Models. Computational Linguistics, 29(1):19–52. ? Deyi Xiong, Qun Liu and Shouxun Lin. 2020. Maximum Entropy Based Phrase Reordering Model for Statistical Machine Translation. In Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the ACL, pages521528. ? Peter F. Brown, Stephen A. Della Pietra, Vincent J. Della Pietra, amp。 9 : F o r k = i to j 1 d o / / 尋找一個(gè)分割點(diǎn) 1 0 : F oreach cand A in cands[i,k] a n d e a c h c a n d B in cands[ k+1 , j ] 1 1 : 分別計(jì)算 A 和 B 的正向和反向輸入,添加到