问一道题：NO.PZ2015120204000045 [ CFA II ]

NO.PZ2015120204000045 问题如下 Steele anSchultz then scuss how to preprocess the rtext tSteele tells Schultz ththe process ccompletein the following three steps:Step 1 Cleanse the rtext ta.Step 2 Split the cleanseta into a collection of wor for them to normalizeStep 3 Normalize the collection of wor from Step 2 ancreate a stinset of tokens from the normalizewor. With respeto Step 1, Steele tells Schultz: “I believe I shoulremove all html tags, punctuations, numbers, anextra white spaces from the ta before normalizing them.Is Steele’s statement regarng Step 1 of the preprocessing of rtext ta correct? A.Yes B.No, because her suggestetreatment of punctuation is incorrect. C.No, because her suggestetreatment of extra white spaces is incorrect. B is correct. Although most punctuations are not necessary for text analysis anshoulremove some punctuations (e.g., percentage signs, currensymbols, anquestion marks) museful for ML mol training. Supunctuations shoulsubstitutewith annotations (e.g., /percentSign/, /llarSign/, an/questionMark/) to preserve their grammaticmeaning in the text. Suannotations preserve the semantic meaning of important characters in the text for further text processing ananalysis stages. 如题