zzx_mt系統(tǒng)評測報告-資料下載頁
2025-10-08 21:43本頁面
【導(dǎo)讀】中英SMT系統(tǒng)中的兩個問題。詞對齊中引入啟發(fā)式規(guī)則，加入ITG約束。重定序模型中結(jié)合ITG和句法知識。中-英詞序差別大。為每個源短語創(chuàng)建的翻譯選項列表。分詞：中文ICTCLAS，英文WMT05的Tokenizer工具。英文的詞根化處理：詞對齊過程中使用。同構(gòu)模型對于翻譯結(jié)果產(chǎn)生的積極的影響，各個指標(biāo)均比兩。方向偏好產(chǎn)生了負(fù)面的影響，原因可能有：。具有解釋能力，反而影響了模型的穩(wěn)定性；CWMT08提供的科技語料作為訓(xùn)練集。采用類似的預(yù)處理后，共：616597個句對。參與了兩個單元的評測。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
【正文】 etra, Vincent J. Della Pietra, amp。 Robert L. Mercer. 1993. The mathematics of statistical machine translation: parameter estimation. Computational Linguistics 19 (2), pp. 263311. ? Kenji Yamada and Kevin Knight. 2020. A Syntaxbased Statistical Translation Model. In Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics, pp. 523–530. ? Yang Liu, Qun Liu, amp。 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。 . ? Dekai Wu. 1997. Stochastic Inversion Transduction Grammars and Bilingual Parsing of Parallel Corpora. Computational Linguistics, 23(3):374. ? WenHan Chao and ZhouJun Li. 2020. Incorporating Constituent Structure Constraint into Discriminative Word Alignment”, In proceedings of MT Summit XI, Copenhagen, Denmark, September 1014, 2020. ? A. Stolcke. 2020. SRILM – An extensible language modeling toolkit. In Proceedings of the International Conference on Spoken Language Processing, pp. 901–904 謝謝
教學(xué)課件相關(guān)推薦
鄂ICP備17016276號-1