Penut Chen
    • Create new note
    • Create a note from template
      • Sharing URL Link copied
      • /edit
      • View mode
        • Edit mode
        • View mode
        • Book mode
        • Slide mode
        Edit mode View mode Book mode Slide mode
      • Customize slides
      • Note Permission
      • Read
        • Only me
        • Signed-in users
        • Everyone
        Only me Signed-in users Everyone
      • Write
        • Only me
        • Signed-in users
        • Everyone
        Only me Signed-in users Everyone
      • Engagement control Commenting, Suggest edit, Emoji Reply
    • Invite by email
      Invitee

      This note has no invitees

    • Publish Note

      Share your work with the world Congratulations! 🎉 Your note is out in the world Publish Note No publishing access yet

      Your note will be visible on your profile and discoverable by anyone.
      Your note is now live.
      This note is visible on your profile and discoverable online.
      Everyone on the web can find and read all notes of this public team.

      Your account was recently created. Publishing will be available soon, allowing you to share notes on your public page and in search results.

      Your team account was recently created. Publishing will be available soon, allowing you to share notes on your public page and in search results.

      Explore these features while you wait
      Complete general settings
      Bookmark and like published notes
      Write a few more notes
      Complete general settings
      Write a few more notes
      See published notes
      Unpublish note
      Please check the box to agree to the Community Guidelines.
      View profile
    • Commenting
      Permission
      Disabled Forbidden Owners Signed-in users Everyone
    • Enable
    • Permission
      • Forbidden
      • Owners
      • Signed-in users
      • Everyone
    • Suggest edit
      Permission
      Disabled Forbidden Owners Signed-in users Everyone
    • Enable
    • Permission
      • Forbidden
      • Owners
      • Signed-in users
    • Emoji Reply
    • Enable
    • Versions and GitHub Sync
    • Note settings
    • Note Insights New
    • Engagement control
    • Make a copy
    • Transfer ownership
    • Delete this note
    • Save as template
    • Insert from template
    • Import from
      • Dropbox
      • Google Drive
      • Gist
      • Clipboard
    • Export to
      • Dropbox
      • Google Drive
      • Gist
    • Download
      • Markdown
      • HTML
      • Raw HTML
Menu Note settings Note Insights Versions and GitHub Sync Sharing URL Create Help
Create Create new note Create a note from template
Menu
Options
Engagement control Make a copy Transfer ownership Delete this note
Import from
Dropbox Google Drive Gist Clipboard
Export to
Dropbox Google Drive Gist
Download
Markdown HTML Raw HTML
Back
Sharing URL Link copied
/edit
View mode
  • Edit mode
  • View mode
  • Book mode
  • Slide mode
Edit mode View mode Book mode Slide mode
Customize slides
Note Permission
Read
Only me
  • Only me
  • Signed-in users
  • Everyone
Only me Signed-in users Everyone
Write
Only me
  • Only me
  • Signed-in users
  • Everyone
Only me Signed-in users Everyone
Engagement control Commenting, Suggest edit, Emoji Reply
  • Invite by email
    Invitee

    This note has no invitees

  • Publish Note

    Share your work with the world Congratulations! 🎉 Your note is out in the world Publish Note No publishing access yet

    Your note will be visible on your profile and discoverable by anyone.
    Your note is now live.
    This note is visible on your profile and discoverable online.
    Everyone on the web can find and read all notes of this public team.

    Your account was recently created. Publishing will be available soon, allowing you to share notes on your public page and in search results.

    Your team account was recently created. Publishing will be available soon, allowing you to share notes on your public page and in search results.

    Explore these features while you wait
    Complete general settings
    Bookmark and like published notes
    Write a few more notes
    Complete general settings
    Write a few more notes
    See published notes
    Unpublish note
    Please check the box to agree to the Community Guidelines.
    View profile
    Engagement control
    Commenting
    Permission
    Disabled Forbidden Owners Signed-in users Everyone
    Enable
    Permission
    • Forbidden
    • Owners
    • Signed-in users
    • Everyone
    Suggest edit
    Permission
    Disabled Forbidden Owners Signed-in users Everyone
    Enable
    Permission
    • Forbidden
    • Owners
    • Signed-in users
    Emoji Reply
    Enable
    Import from Dropbox Google Drive Gist Clipboard
       Owned this note    Owned this note      
    Published Linked with GitHub
    1
    • Any changes
      Be notified of any changes
    • Mention me
      Be notified of mention me
    • Unsubscribe
    # NLP Note :::info + 課程名稱:自然語言處理 Natural Language Processing + 授課老師:[name=林川傑 Chuan-Jie Lin] + 開課學期:1071 ::: [TOC] ## 1001 Lexicon 合法詞彙的集合 ## 1008 ### Morphology 英文變形 + Inflectional 名詞動詞的變形 Ex: dog, dogs, dog's Ex: go, went, gone + Derivational 衍生出來的詞 英文詞分成兩部份 Stem 枝幹 Affixes 修飾 Ex: international Stem: nation Affixes: inter- (prefix), -al (suffix) 有些語言也有 infix + Verb/Adj to Noun -ation computerize Linguistics 語言的 翻譯比較不需要還原 搜尋引擎會比較需要用到變形還原 Maximum Likelihood 就是直接算出來的統計機率方法 N-gram用來放在語音辨識,確認辨識出來的這句話合不合理常不常見 ## 1015 只要 a > b, 則 log(a) > log(b) bigram 可能無從判斷不存在的詞是否為真的不存在 → 會讓機率的估算變成 0 ∴ 改用 Smoothing Method ### Smoothing Method 使用一個近似 0 但不是 0 的數 機率模型有個很重要的原則:所有的事件總和要是 1 方法一、Discounting 把所有事件打個九折,剩下 10% 分給未出現的詞 方法二、Model Combination 結合 Unigram, Bigram 之類的G#XFKUUTG%TG$F ## 1022 + Article 冠詞 a, the + 量詞,英文就沒有 + Function Words + 通常沒什麼資訊 + 而且集合固定,沒什麼變 + Content Words + 有很多資訊 + 而且常常冒出新的詞 ## 1029 如何做詞性標記 + 詞性集 + 辭典紀錄每個詞有幾種詞性 Project念成專案跟投射時讀音不同 Google小姐能分的清楚 Rule Base的方法太耗人力、過時、錯誤率高 詞性標記的機率模型可能有0機率的出現 如果是0,可能真的是0 通常可以相信真的是0 就算要做Smoothing那個值也是超小 不需要太複雜的Smoothing Method 大部分的機率模型大多都是監督式學習 ### Context Sensitive Grammar a S b → a NP + VP b 因為S前面是a,後面是b,所以變成後面那樣 ### Context Free Grammar 不需要根據前後文就可以剖析成某種語法 S → NP + VP 大多用Syntax,也是語法的意思,Grammar比較像是文法 在做翻譯、問答,需要語法剖析才能知道例如主詞在哪 語法差異例如:A of B → B的A Ex: You can view these great rules as analysis and synthesis machine. 介系詞開頭的都是PP 動詞接NP是VP VP + PP > VP 最後NP + VP變成S ## 1105 NP 名詞詞組 VP 動詞詞組 ### Parsing (Ch 9 P.38) 有個假設,Right hand side只有兩個子節點 + Top-Down Parsing + 把 Left hand side 做一個分群 + Bottom-Up Parsing + 把 Right hand side 的第一個做分群 可能有 Ambiguity 1. PP Attachment Ex: I observed the boy with a telescope. + 望遠鏡到底是我的還是男孩的 2. 同義字 Ex: I walk to the bank. + 到底是走去銀行還是走去河岸 3. P and Q or R + P and (Q or R) + (P and Q) or R + 可能用語音的停頓點來表示 4. NN-Compound + 兒童 新聞主播 + 兒童新聞 主播 5. Movement Which flight do you want me to have the travel agent book? ## 1126 ### Feature (Ch 11) + Number, case, gender... | | 單數 Singular | 複數 Plural | | :-----------: | ------------ | ------------ | | First Person | I, me, mine | we, us, ours | | Second Person | you, yours | you, yours | | Third Person | he, she, its | they, them | + Feature 的使用 + 語法檢查 (Ex: Office Word) + 解決 PP-attachment + 有些語法有陰性、陽性和中性,展開就會有18種 ### Feature Matching + `S -> NP VP` + 確認數量與人稱要相等 + `<NP NUM> == <VP NUM>` + `<NP PERSON> == <VP PERSON>` + `NP -> dog` + `<NP NUM> = sing. // 單數` + `<NP PERSON> = 3 // 第三人稱` + `NP -> dogs` + `<NP NUM> = plur. // 複數` + `<NP PERSON> = 3 // 第三人稱` ### Representing Meaning (Ch 14) + 一開始從 Word 到 Syntax + 現在要來研究語意 Meaning + 人類透過一連串的聲音與一堆符號來進行溝通 + 我們用一種 Representation 來教電腦何謂語意 ### First Order Predicate Calculus (FOPC) + 雖然不是最完美的表達法 + 但其他表達法有更多嚴重的限制與問題 + Predicate 述語 + Ex: 我吃了一個紅蘋果 1. 動詞 + `吃(x, y): x 吃 y` 2. 形容詞 + `紅(x): x 是紅的` 3. 名詞 + `蘋果(x): x 是蘋果` 4. 介係詞 + `吃(我, e) & 蘋果(e) & 紅(e)` + Mary giving a list to John + Mary 是**語意**上的主詞 + John was given a list from Mary + John 是**語法**上的主詞,但 John 不是主動 + 所以乾脆寫成: ``` Giving(x) & Giver(Mary, x) & Given(y, x) & Givee(John, x) & Isa(y, List) ``` ### Semantic Analysis (Ch 15) + Mass-Noun 集合名詞 + Proper-Noun 專有名詞 ## 1203 ### Review Predicate + 述語式邏輯 + Giving(Mary, John, List) + Mary giving John a list + Predicate 其實很少使用 + 但 State of the Art 的 QA System 就有使用 ### Compositional Analysis + Serving-Server-Served + $Isa(e, Serving)\land Server(e, y)\land Served(e, x)$ + #### Ex: I told Harry to go to Maharani. + Telling-Teller-Tellee + Going-Goer + To + -ee 結尾是被...的人 1. $\lambda x\lambda y\exists e, telling(e) \land teller(e, x) \land tellee(e, y)$ 2. $\lambda t\lambda k\exists z, going(z)\land goer(z, k)$ 3. $\lambda a\lambda b, to(a, b)$ + 2 跟 3 可以直接 $\land$ 在一起 + 從語法樹的葉子不斷 Parse 上來就可以完成一個 Compositional Logic ### Logic Problem + 這世界上有甜西瓜 + $\exists x, 西瓜(x)\land甜(x)$ + 這世界上的西瓜都是甜的 + $\forall x, 西瓜(x)\to甜(x)$ + #### Who Love Who + $\exists x\exists y, love(x,y)$ + 至少有個 x 愛著 y + 也有可能是同一個人愛自己 + $\forall x\forall y, love(x,y)$ + 所有人都愛所有人 + 這世界充滿了愛 + $\exists x\forall y, love(x,y)$ + 有個人愛著所有人 + $\forall x\exists y, love(x,y)$ + 所有人都愛著一個人 + $\exists y\forall x, love(x, y)$ + 有個人被所有人愛 + 若集合裡面不只有人(可能有摩天輪) + $\exists x\forall y, People(x)\land People(y)\to love(x,y)$ + 出現 $\forall$ 就要用 $\to$ ### Non-Compositionality (Ch15 P36) + Idioms + Kick the bucket + Buy the farm + Bite the bullet + Run the show + Bury the hatchet + 以上都是講人去世了 + The Tip of the Iceberg + 冰山一角 + The tip of 1000-page iceberg. + 一千頁裡面的冰山一角 + 語意的轉換上會直接轉成它直接的意思 + Jokes + Irony + Sarcasm + Metaphor + Metonymy + Indirect Requests ### Information Extraction + 跟 IR 可能比較沒有關係 + 例如:要找一個跟恐怖攻擊有關的事情 + 會有發生時間、發生地點、攻擊者是誰等等 + 需要做一些日期時間的解析 + 例如:上星期三轉成實際的日期 + 有些地名等等 + 可以查表 + 但恐怖組織,可能需要專有名詞辨識 + 組織名:Bridgestone Sport Co. + 國家名:Taiwan, Japan + 時間:Friday, January 1990 + 數量:20 million new Taiwan dollars, 20,000 ## 1210 ### Lexical Semantics + 分成三個層面 + 整篇文章在講啥 + 每句話在講啥 + 每個詞在講啥 + 接下來探討詞的意思 + Paradigmatic + 兩個詞之間的關係 + 同義詞、反義詞、上下義詞 + Syntagmatic + 討論構詞的結構 + Ex: 好喝、難聽 + 在中文比較常討論 + What's a word + 詞的單位 Lexeme + 同一個 Entry + Lexicon + Lexeme 的集合 + 單純的詞列表 + 與 Dictionary 不一樣 ### Homonymy 同名詞 + 指兩個詞很像 + Phonological 同音詞 + Homophony + Threw/Through, Deer/Dear + 意義、異議、意譯 + 造成語音辨識上的困擾 + Orthographic 形近詞 + Homographic + Tear (眼淚或撕裂) + Minute (Time/Tiny) + 空(ㄎㄨㄥ/ㄎㄨㄥˋ) + 造成語音合成的問題 + Both + Bat (球棒/蝙蝠) + 讀音跟字形都一樣 ### Polysemy 多義詞 + Bank 河岸、銀行 + Interest 興趣、利息 + 如果有大量閱讀經驗,可以解決歧義問題 ### Synonyms 同義詞 + 同義詞其實沒有很同義 + 其實同義詞很少 + 開心 & 快樂 + 但快樂可以當抽象名詞 + 詞的發明就是為了分辨更細微的差異 + 如果真的同義就不會被發明出來 + Big/Large + Big sister (O) + Large sister (X) + Small/Tiny + Tiny 是 Small 的狹義詞 + 如果兩個詞是反義詞,則他們的下義詞都互相是反義詞 ### Hyponymy 上下義詞 + Hypernym 上義詞 + Hyponym 下義詞 + Ex: Dog is an animal + Hypernym: Animal + Hyponym: Dog + 工作身份則不是語意的問題 + 比較像 Attribute,可以變的 + 上義詞有的特性,下義詞都有 + 人會說話,所以男人女人都會說話 + WordNet 由普林斯頓大學認識科學實驗室建立的 | Category | Unique Strings | Synsets | Total Word-Sense Pairs | |:---------:|:--------------:|:-------:|:----------------------:| | Noun | 117097 | 81426 | 145104 | | Verb | 11488 | 13650 | 24890 | | Adjective | 22141 | 18877 | 31302 | | Adverb | 4601 | 3644 | 5720 | + Synset 是語意 + 動詞雖然只有 11488 個,但語意卻有 13650 個 + 名詞雖然有 117097 個,但語意只有 81426 個 + WordNet vs Word2Vec + WordNet 是專家系統 + Word2Vec 是機器學習 + 以白宮為例: + 語句中可能以白宮代表美國政權 + 但 WordNet 裡面就是定義成那棟建築 + 因為人類用詞不像專家那樣精準 + 所以情感上 Word2Vec 好像準一點 ## 1217 ### Wordnet Relation (Ch.16 P.21) + 上下義 + Hypernym + Hyponym + 團體:團體中的一員 + Has-Member + Member-Of + 部件:彼此之間的差異可能有點大 + Has-Part + Part-Of + 反義詞 + Antonym + 在 Wordnet 裡面只有 Holonym/Meronym + 包含 Group/Member & Whole/Part ### Inside Verbs + Agents of the actions + Takers, givers + Thematic Role (P.28) + Agent + Experiencer + Force + Theme + 做事情的時候就在的 + Result + 做完事情才會長出來的東西 + Content + Instrument + Beneficiary + Source + 例如起點 + Goal + 例如目的地 + Sally gave Harry a book. + $Giver(Sally)\land Givee(Harry)\land Given(book)$ + $Agent(Sally)\land Goal(Harry)\land Theme(book)$ + 語意角色在機器翻譯扮演重要的角色 ### Supervised & Unsupervised Learning + 訓練的過程有沒有用到標準答案 ### Bound on Performance + Upper Bound + 人類的 Performance + Lower Bound + 最簡單演算法的 Performance + Baseline + Random Method + Majority Method + 選最常出現的 + Other Model + 選別人家的系統 ### WSD Tags + Wordnet的分類太細了 + 光 bass 就有八種解釋 + 有時候可能沒必要分太細 + Collocational + 用前後幾個詞的搭配來判斷 + Ex: [guitar, NN, and, CJC, player, NN, stand, VVB] + Co-Occurrence + 只標示有沒有出現,看不出順序的 + Ex: [0, 0, 0, 1, 0, 0, 1, 0, ..., 0] ### Classifiers + Naive Bayes + 貝氏定理寫出來的機器學習分類器 + Decision Lists + 比較像規則式 + 機器學習寫出來的規則式 + Decision Trees + Neural Nets + 強調只餵 raw text + Support Vector Machines, SVM + Nearest Neighbor Methods ### Bootstrapping + 從小型語料庫選擇 100% 正確的規則出來 + 用這 100% 正確的規則去分析大型語料庫 + 因此獲得大量訓練資料 ### One Sense per Discourse + Discourse 篇章、文章 + 假設在一篇文章中同一個詞都是一樣的語意 ### One Sense per Collocation + 附近的詞加強本身的語意 ### Unsupervised Disambiguation + EM Algorithm + 先執行 E-Step 再執行 M-Step + 不斷執行這兩個步驟直到收斂為止 + 若要判斷不同的詞,就要分別訓練不同的模型 > Maximum Likelihood > 直接計算最大值 ## Pragmatic Level ## 1224 ### Discourse (Ch.18) + 有點像是一整個篇章主題的呈現 + 整篇文章的 Discourse 要一致 + Discourse coherent 主題連貫性 + Rhetorical Structure + 修辭的結構 + 討論兩句話是否有因果、舉例、假設等 + Nucleus/Satellite + 補充 Elaboration + Features + Exlicit markers: because, however, therefore, then + 可以窮舉這些連接詞 + 順序、時態、聲音 + RST Problem + 即便有訓練過的標記者,標記的一致性可能還是很低 + Discourse/Topic Structure + Referring Expressions + Co-refernence 同指涉 + 指涉字串:例如經常用代名詞來講話 + 需要解決同指涉現象就要找出候選詞 + Candidcate 候選詞 + 所有的代名詞 vs. Full NP + Definite vs. Indefinite NPs + Definite NPs + the ... + 專有名詞 + Indefinite NPs + a ... + Common vs. Proper Noun + Modified vs. Bare head NP + 代名詞解析分兩大派 + 人稱代名詞、非人 + More NP types + Inferrables + Ex: Sally bought a used car. **The tires** need to be replaced. + The tires 代表車子的部件 + Discontinuous Sets + Ex: John has known Bill for many years now. **They** often go hiking together. + They 指涉 John & Bill + Anaphora 往前指涉 + 最常見的指涉現象 + 前面提過的名詞,後面用代名詞表示 + Zero Anaphora 零指涉 + 指涉一個省略的代名詞 + Co-reference between named entities + 用 the White House 指涉 The US government + 借代修辭 + Co-reference between noun phrases + Ex: I stayed in Grand Hotel yesrerday. **The hotel** was ... + The hotel 指涉 Grand Hotel ### Dialogue (Ch.19) + [Reference](https://www.slideshare.net/tw_dsconf/ss-75294430) + Basic Model + NLU -> DM -> NLG -> Loop + Language Understanding (LU) + Dialogue Management (DM) + State Tracking + 這部份也要負責確認人沒有講清楚的部份 + Natural Language Generation (NLG) + Dialogue vs. Monologue + Dialogue + Turn-Talking + 確認誰要說話 + Grounding + 達成共識 + Detecting & Repairing Misunderstanding + Initiative & Confirmation Strategies + 人類常常在講一些不合語意的話 + 口語化、哈哈笑之類的 + Utterances + 講話被中斷 + 可以用語句間的暫停、語氣聲調來解決 + Turn Talking + 誰該講 + 何時該講 + 如何判斷講話的人 + 放棄這個回合 + Holding the floor + 可被中斷的 + 如何判斷我必須講話 + Simple Turn-Talking Rule + Ch.19 P.8 + Turn Taking Scripts + Greeting/Greeting + Question/Answer + Compliment/Downplayer + 稱讚/感謝之類的 + Request/Grant or Not + 明顯的沉默是不好的 + Initiative + System Initiative + 總是讓系統起頭 + 穩定 + 但是不友善 + Mixed Initiative + 比較多是這種 + User 講多少算多少 + 沒講到的系統再問 + User Initiative + Grounding + 參與者雙方是否 Establish common ground + 瞭解我們是否具有共同的背景知識 + NLG + Template-Based NLG + 透過設計 Pattern 來產生文句 + 也可以透過 ML 來學習句型 + Evaluation + 能不能完成任務 + 花費多少時間完成任務 + 花費多少成本建構系統 ## **Homework 4 WordNet** + Wu & Palmer Similarity + $Sim_{wp} = \frac{2N}{N1+N2}$ + 計算兩個詞之間的相似度最高的那個 + 可以使用 NLTK + 只要算名詞的語意就好 ## Final Project + 幫某個已知的系統加上某個 NLP 技術替它增加一個新的 Feature + 常見的 NLP 技術 + 斷詞、詞頻統計 + 抽取關鍵詞 + 翻譯 + 意見探勘 + 情緒偵測 + 光學文字辨識、字幕 + 語音辨識與合成 + 文句生成 + FAQ系統、問答系統、閱讀測驗 + 專有名詞辨識 + 資訊擷取 + 自動摘要 + 文章相似度比對、資訊含量的比對 + NE 關聯性、Ontology + 不同的專有名詞之間的關聯性為何 + 找出所有的關聯性之後就能建立一個 Ontology + 例如: + 學校有個學術單位叫電資學院 + 學校有個行政單位叫做教務處 + 文句蘊含 + 告訴我兩個句子 $t_1, t_2$ + $t_1$ 成立的時候 $t_2$ 成不成立 + Paraphrase 換句話說 + 美國反對北韓發展核武 + 白宮不支持金正恩擁有核武 + 報告五項 + 哪些已經有惹 + 哪些沒有der + 提供四個新功能 + 或者提供五個新功能 ## Additional + Linguistic + Lexical (Word) + Syntactic (Syntax) + Semantic (Semantics) + Pragmatic (Pragmatics 語用) + Ambiguity 歧義性 + Ex: 土地公有政策略有感覺 + Surface information + Character 字元 + Letter 字母 + Word 詞 + Matching + String Matching + Pattern Matching + Lexical Level (Word) + Terminology + Lexicon 辭典、詞條 + Word + Inflection(變形、單複數、三態變化、比較級) + Lemmatization:還原成原形 + Lemma:原形 + Stemming: + taking -> tak + takes -> tak + teeth -> teeth + earlier -> earli + Word segmentation 斷詞 + Morphological analysis(還原日文動詞變化) + Tokenization + Token, Term, Word, String + Syntactic Level (Syntax) + Part-of-Speech 詞性標記 + POS Tagger + Phrase 詞組、Sentence 句子 + Syntax 語法、Grammar 文法 + Syntactic Label 語法角色(主詞、受詞) + Parsing 語法剖析 + Parsing Tree, Syntax Tree 語法樹 + Structural + Bracket Tree + Head 中心語 如果是人名就取姓 + Modifier 修飾語 + Dependency Tree 語法相依樹 + Dependency Relation + Semantic Level + Resource + WordNet + 中文 WordNet + 同義詞詞林(擴展版) + 廣義知網 E-Hownet + Synonyms 同義詞 + Hyponym 下義詞、狹義詞 + Hypernym 上義詞、廣義詞 + Progmatic Level + Context 上下文 + Contextual Information + Content 內容,主角的 + Ellipsis 省略現象 + Co-reference 同指涉 + Anaphora 代名詞指涉 + Experiment & Evaluation + Training + Tuning + Testing + Dataset + Machine Learning + Classifier 分類器 + Features 特徵 + Object + Classes + N-Fold Cross-Validation + Evaluate System Performance + Accuracy + Precision + Recall + F-Measure + Utterance 對話中的句子,不一定是完整或者語法完備的句子

    Import from clipboard

    Paste your markdown or webpage here...

    Advanced permission required

    Your current role can only read. Ask the system administrator to acquire write and comment permission.

    This team is disabled

    Sorry, this team is disabled. You can't edit this note.

    This note is locked

    Sorry, only owner can edit this note.

    Reach the limit

    Sorry, you've reached the max length this note can be.
    Please reduce the content or divide it to more notes, thank you!

    Import from Gist

    Import from Snippet

    or

    Export to Snippet

    Are you sure?

    Do you really want to delete this note?
    All users will lose their connection.

    Create a note from template

    Create a note from template

    Oops...
    This template has been removed or transferred.
    Upgrade
    All
    • All
    • Team
    No template.

    Create a template

    Upgrade

    Delete template

    Do you really want to delete this template?
    Turn this template into a regular note and keep its content, versions, and comments.

    This page need refresh

    You have an incompatible client version.
    Refresh to update.
    New version available!
    See releases notes here
    Refresh to enjoy new features.
    Your user state has changed.
    Refresh to load new user state.

    Sign in

    Forgot password
    or
    Sign in via Facebook Sign in via X(Twitter) Sign in via GitHub Sign in via Dropbox Sign in with Wallet
    Wallet ( )
    Connect another wallet

    New to HackMD? Sign up

    By signing in, you agree to our terms of service.

    Help

    • English
    • 中文
    • Français
    • Deutsch
    • 日本語
    • Español
    • Català
    • Ελληνικά
    • Português
    • italiano
    • Türkçe
    • Русский
    • Nederlands
    • hrvatski jezik
    • język polski
    • Українська
    • हिन्दी
    • svenska
    • Esperanto
    • dansk

    Documents

    Help & Tutorial

    How to use Book mode

    Slide Example

    API Docs

    Edit in VSCode

    Install browser extension

    Contacts

    Feedback

    Discord

    Send us email

    Resources

    Releases

    Pricing

    Blog

    Policy

    Terms

    Privacy

    Cheatsheet

    Syntax Example Reference
    # Header Header 基本排版
    - Unordered List
    • Unordered List
    1. Ordered List
    1. Ordered List
    - [ ] Todo List
    • Todo List
    > Blockquote
    Blockquote
    **Bold font** Bold font
    *Italics font* Italics font
    ~~Strikethrough~~ Strikethrough
    19^th^ 19th
    H~2~O H2O
    ++Inserted text++ Inserted text
    ==Marked text== Marked text
    [link text](https:// "title") Link
    ![image alt](https:// "title") Image
    `Code` Code 在筆記中貼入程式碼
    ```javascript
    var i = 0;
    ```
    var i = 0;
    :smile: :smile: Emoji list
    {%youtube youtube_id %} Externals
    $L^aT_eX$ LaTeX
    :::info
    This is a alert area.
    :::

    This is a alert area.

    Versions and GitHub Sync
    Get Full History Access

    • Edit version name
    • Delete

    revision author avatar     named on  

    More Less

    Note content is identical to the latest version.
    Compare
      Choose a version
      No search result
      Version not found
    Sign in to link this note to GitHub
    Learn more
    This note is not linked with GitHub
     

    Feedback

    Submission failed, please try again

    Thanks for your support.

    On a scale of 0-10, how likely is it that you would recommend HackMD to your friends, family or business associates?

    Please give us some advice and help us improve HackMD.

     

    Thanks for your feedback

    Remove version name

    Do you want to remove this version name and description?

    Transfer ownership

    Transfer to
      Warning: is a public team. If you transfer note to this team, everyone on the web can find and read this note.

        Link with GitHub

        Please authorize HackMD on GitHub
        • Please sign in to GitHub and install the HackMD app on your GitHub repo.
        • HackMD links with GitHub through a GitHub App. You can choose which repo to install our App.
        Learn more  Sign in to GitHub

        Push the note to GitHub Push to GitHub Pull a file from GitHub

          Authorize again
         

        Choose which file to push to

        Select repo
        Refresh Authorize more repos
        Select branch
        Select file
        Select branch
        Choose version(s) to push
        • Save a new version and push
        • Choose from existing versions
        Include title and tags
        Available push count

        Pull from GitHub

         
        File from GitHub
        File from HackMD

        GitHub Link Settings

        File linked

        Linked by
        File path
        Last synced branch
        Available push count

        Danger Zone

        Unlink
        You will no longer receive notification when GitHub file changes after unlink.

        Syncing

        Push failed

        Push successfully