# 讀書筆記: stanford cs 224n # stanford cs 224n: assignment #4 ## Q2 Analyzing NMT Systems (30 points) (a) (12 points) Here we present a series of errors we found in the outputs of our NMT model (which is the same as the one you just trained). For each example of a Spanish source sentence, reference (i.e., ‘gold’) English translation, and NMT (i.e., ‘model’) English translation, please: CS 224n Assignment 4 Page 5 of 7 **1.Identify the error in the NMT translation. 2.Provide a reason why the model may have made the error (either due to a specific linguistic construct or specific model limitations). 3.Describe one possible way we might alter the NMT system to fix the observed error.** Below are the translations that you should analyze as described above. Note that out-of-vocabulary words are underlined. 1. **(2 points) Source Sentence: Aqu´ı otro de mis favoritos, “La noche estrellada”.** Reference Translation: So another one of my favorites, “The Starry Night”. NMT Translation: Here’s another favorite of my favorites, “The Starry Night”. #### ANS: error: 重複字(favorite of my favorite) reason: RNN常出現,可能把one不知道要指向誰 possible solution:在training或是decoding的時候對重複字加入penalty? 1. **(2 points) Source Sentence: Ustedes saben que lo que yo hago es escribir para los ni˜nos, y,de hecho, probablemente soy el autor para ni˜nos, ms ledo en los EEUU.** Reference Translation: You know, what I do is write for children, and I’m probably America’s most widely read children’s author, in fact. NMT Translation: You know what I do is write for children, and in fact, I’m probably the author for children, more reading in the U.S. #### ANS: error: 語序不順 reason:對long-term dependencies無法處理? possible solution: 3. **(2 points) Source Sentence: Un amigo me hizo eso – Richard Bolingbroke.** Reference Translation: A friend of mine did that – Richard Bolingbroke. NMT Translation: A friend of mine did that – Richard <unk> #### ANS: error:<unk> reason: 遇到特殊字?人名? possible solution: 加入training或是學習對特殊字做處理 4. **(2 points) Source Sentence: Solo tienes que dar vuelta a la manzana para verlo como unaepifan´ıa.** Reference Translation: You’ve just got to go around the block to see it as an epiphany. NMT Translation: You just have to go back to the apple to see it as a epiphany. #### ANS: error: manzana有兩種意思 reason: 選了出現頻率高的? possible solution:Word Sense Disambiguation (WSD) ?? 1. **(2 points) Source Sentence: Ella salv´o mi vida al permitirme entrar al ba˜no de la sala de profesores.** Reference Translation: She saved my life by letting me go to the bathroom in the teachers’ lounge. NMT Translation: She saved my life by letting me go to the bathroom in the women’s room. #### ANS: error:profesor == women! reason:profesore大多是女性,故產生bias possible solution: 1. **(2 points) Source Sentence: Eso es m´as de 100,000 hect´areas.** Reference Translation: That’s more than 250 thousand acres. NMT Translation: That’s over 100,000 acres. #### ANS: error: 數字一樣單位不同?? reason:沒看過hectareas possible solution: 確定hectareas在訓練及,或是將單位的概念放在訓練及中