mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 01:16:28 +03:00
Update tokenization 101 and add illustration
This commit is contained in:
ines
parent
b03fb2d7b0
commit
db116cbeda
123
website/assets/img/docs/tokenization.svg
Normal file
123
website/assets/img/docs/tokenization.svg
Normal file
|
|
@ -0,0 +1,123 @@
|
|||
<svg class="o-svg" xmlns="http://www.w3.org/2000/svg" width="600" height="380" viewBox="-20 -10 550 400">
|
||||
<style>
|
||||
.svg__tokenization__text { fill: #1a1e23; font: 18px "Source Sans Pro" }
|
||||
.svg__tokenization__text-small { fill: #fff; font: 600 13px "Source Code Pro" }
|
||||
</style>
|
||||
<path fill="none" stroke="#c00" stroke-width="2" stroke-miterlimit="10" d="M71 39v12H16v11M71 39v12h20v11"/>
|
||||
<path fill="#f8cecc" stroke="#c00" stroke-width="2" d="M1 1h140v38.2H1z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" width="43" height="19" transform="translate(48.5 9.5)">“Let’s</text>
|
||||
<path fill="none" stroke="#666" stroke-width="2" stroke-miterlimit="10" d="M175 39v23"/>
|
||||
<path fill="#f5f5f5" stroke="#666" stroke-width="2" d="M150 1h50v38.2h-50z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(164.5 9.5)" width="19" height="19">go</text>
|
||||
<path fill="none" stroke="#666" stroke-width="2" stroke-miterlimit="10" d="M235 39v23"/>
|
||||
<path fill="#f5f5f5" stroke="#666" stroke-width="2" d="M210 1h50v38.2h-50z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(226.5 9.5)" width="15" height="19">to</text>
|
||||
<path fill="none" stroke="#666" stroke-width="2" stroke-miterlimit="10" d="M341 39v23"/>
|
||||
<path fill="#f5f5f5" stroke="#666" stroke-width="2" d="M270 1h141v38.2H270z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(320.5 9.5)" width="38" height="19">N.Y.!”</text>
|
||||
<path fill="none" stroke="#82b366" stroke-width="2" stroke-miterlimit="10" d="M16 100v20"/>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M1 62h30v38.2H1z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(11.5 70.5)" width="7" height="19">“</text>
|
||||
<path fill="none" stroke="#c00" stroke-width="2" stroke-miterlimit="10" d="M91 100v11H66v9M91 100v11h29v9"/>
|
||||
<path fill="#f8cecc" stroke="#c00" stroke-width="2" d="M41 62h100v38.2H41z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(72.5 70.5)" width="35" height="19">Let’s</text>
|
||||
<path fill="none" stroke="#666" stroke-width="2" stroke-miterlimit="10" d="M175 100v20"/>
|
||||
<path fill="#f5f5f5" stroke="#666" stroke-width="2" d="M150 62h50v38.2h-50z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(164.5 70.5)" width="19" height="19">go</text>
|
||||
<path fill="none" stroke="#666" stroke-width="2" stroke-miterlimit="10" d="M235 100v20"/>
|
||||
<path fill="#f5f5f5" stroke="#666" stroke-width="2" d="M210 62h50v38.2h-50z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(226.5 70.5)" width="15" height="19">to</text>
|
||||
<path fill="none" stroke="#666" stroke-width="2" stroke-miterlimit="10" d="M341 100v20"/>
|
||||
<path fill="#f5f5f5" stroke="#666" stroke-width="2" d="M270 62h141v38.2H270z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(320.5 70.5)" width="38" height="19">N.Y.!”</text>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M1 120h30v38H1z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(11.5 128.5)" width="7" height="19">“</text>
|
||||
<path fill="none" stroke="#82b366" stroke-width="2" stroke-miterlimit="10" d="M66 158v24"/>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M41 120h50v38H41z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(53.5 128.5)" width="23" height="19">Let</text>
|
||||
<path fill="none" stroke="#82b366" stroke-width="2" stroke-miterlimit="10" d="M175 158v24"/>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M150 120h50v38h-50z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(164.5 128.5)" width="19" height="19">go</text>
|
||||
<path fill="none" stroke="#82b366" stroke-width="2" stroke-miterlimit="10" d="M235 158v24"/>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M210 120h50v38h-50z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(226.5 128.5)" width="15" height="19">to</text>
|
||||
<path fill="none" stroke="#c00" stroke-width="2" stroke-miterlimit="10" d="M341 158v13h-20v11M341 158v13h55v11"/>
|
||||
<path fill="#f8cecc" stroke="#c00" stroke-width="2" d="M270 120h141v38H270z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(320.5 128.5)" width="38" height="19">N.Y.!”</text>
|
||||
<path fill="none" stroke="#82b366" stroke-width="2" stroke-miterlimit="10" d="M120 158v24"/>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M100 120h40v38h-40z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(113.5 128.5)" width="11" height="19">’s</text>
|
||||
<path fill="none" stroke="#82b366" stroke-width="2" stroke-miterlimit="10" d="M16 220v23"/>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M1 181.8h30V220H1z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(11.5 190.5)" width="7" height="19">“</text>
|
||||
<path fill="none" stroke="#82b366" stroke-width="2" stroke-miterlimit="10" d="M66 220v23"/>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M41 181.8h50V220H41z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(53.5 190.5)" width="23" height="19">Let</text>
|
||||
<path fill="none" stroke="#82b366" stroke-width="2" stroke-miterlimit="10" d="M175 220v23"/>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M150 181.8h50V220h-50z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(164.5 190.5)" width="19" height="19">go</text>
|
||||
<path fill="none" stroke="#82b366" stroke-width="2" stroke-miterlimit="10" d="M235 220v23"/>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M210 181.8h50V220h-50z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(226.5 190.5)" width="15" height="19">to</text>
|
||||
<path fill="none" stroke="#c00" stroke-width="2" stroke-miterlimit="10" d="M321 220v11h-20v12M321 220v11h34v12"/>
|
||||
<path fill="#f8cecc" stroke="#c00" stroke-width="2" d="M270 181.8h101V220H270z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(304.5 190.5)" width="30" height="19">N.Y.!</text>
|
||||
<path fill="none" stroke="#82b366" stroke-width="2" stroke-miterlimit="10" d="M120 220v23"/>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M100 181.8h40V220h-40z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(113.5 190.5)" width="11" height="19">’s</text>
|
||||
<path fill="none" stroke="#82b366" stroke-width="2" stroke-miterlimit="10" d="M396 220v23"/>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M381 181.8h30V220h-30z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(391.5 190.5)" width="7" height="19">”</text>
|
||||
<path fill="none" stroke="#82b366" stroke-width="2" stroke-miterlimit="10" d="M16 281v23"/>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M1 242.7h30V281H1z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(11.5 251.5)" width="7" height="19">“</text>
|
||||
<path fill="none" stroke="#82b366" stroke-width="2" stroke-miterlimit="10" d="M66 281v23"/>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M41 242.7h50V281H41z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(53.5 251.5)" width="23" height="19">Let</text>
|
||||
<path fill="none" stroke="#82b366" stroke-width="2" stroke-miterlimit="10" d="M175 281v20-17 20"/>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M150 242.7h50V281h-50z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(164.5 251.5)" width="19" height="19">go</text>
|
||||
<path fill="none" stroke="#82b366" stroke-width="2" stroke-miterlimit="10" d="M235 281v23"/>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M210 242.7h50V281h-50z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(226.5 251.5)" width="15" height="19">to</text>
|
||||
<path fill="none" stroke="#c00" stroke-width="2" stroke-miterlimit="10" d="M301 281v23"/>
|
||||
<path fill="#f8cecc" stroke="#b85450" stroke-width="2" d="M270 242.7h61V281h-61z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(286.5 251.5)" width="26" height="19">N.Y.</text>
|
||||
<path fill="none" stroke="#82b366" stroke-width="2" stroke-miterlimit="10" d="M120 281v23"/>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M100 242.7h40V281h-40z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(113.5 251.5)" width="11" height="19">’s</text>
|
||||
<path fill="none" stroke="#82b366" stroke-width="2" stroke-miterlimit="10" d="M396 281v23"/>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M381 242.7h30V281h-30z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(391.5 251.5)" width="7" height="19">”</text>
|
||||
<path fill="none" stroke="#82b366" stroke-width="2" stroke-miterlimit="10" d="M355 281v23"/>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M340 242.7h30V281h-30z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(351.5 251.5)" width="5" height="19">!</text>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M1 304h30v38H1z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(11.5 312.5)" width="7" height="19">“</text>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M41 304h50v38H41z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(53.5 312.5)" width="23" height="19">Let</text>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M150 304h50v38h-50z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(164.5 312.5)" width="19" height="19">go</text>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M210 304h50v38h-50z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(226.5 312.5)" width="15" height="19">to</text>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M270 304h61v38h-61z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(286.5 312.5)" width="26" height="19">N.Y.</text>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M100 304h40v38h-40z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(113.5 312.5)" width="11" height="19">’s</text>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M381 304h30v38h-30z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(391.5 312.5)" width="7" height="19">”</text>
|
||||
<path fill="#d5e8d4" stroke="#82b366" stroke-width="2" d="M340 304h30v38h-30z"/>
|
||||
<text class="svg__tokenization__text" dy="1em" transform="translate(351.5 312.5)" width="5" height="19">!</text>
|
||||
<rect width="104" height="19" x="437" y="72" fill="#c00" stroke="#c00" stroke-width="2" rx="2.9" ry="2.9"/>
|
||||
<text class="svg__tokenization__text-small" dy="0.9em" transform="translate(455.5 74.5)" width="65" height="12">EXCEPTION</text>
|
||||
<rect width="104" height="19" x="437" y="11" fill="#c00" stroke="#c00" stroke-width="2" rx="2.9" ry="2.9"/>
|
||||
<text class="svg__tokenization__text-small" dy="0.9em" transform="translate(466.5 13.5)" width="43" height="12">PREFIX</text>
|
||||
<rect width="104" height="19" x="437" y="130" fill="#c00" stroke="#c00" stroke-width="2" rx="2.9" ry="2.9"/>
|
||||
<text class="svg__tokenization__text-small" dy="0.9em" transform="translate(466.5 132.5)" width="43" height="12">SUFFIX</text>
|
||||
<rect width="104" height="19" x="437" y="191" fill="#c00" stroke="#c00" stroke-width="2" rx="2.9" ry="2.9"/>
|
||||
<text class="svg__tokenization__text-small" dy="0.9em" transform="translate(466.5 193.5)" width="43" height="12">SUFFIX</text>
|
||||
<rect width="104" height="19" x="437" y="252" fill="#c00" stroke="#c00" stroke-width="2" rx="2.9" ry="2.9"/>
|
||||
<text class="svg__tokenization__text-small" dy="0.9em" transform="translate(455.5 254.5)" width="65" height="12">EXCEPTION</text>
|
||||
<rect width="104" height="19" x="437" y="313" fill="#82b366" stroke="#82b366" stroke-width="2" rx="2.9" ry="2.9"/>
|
||||
<text class="svg__tokenization__text-small" dy="0.9em" transform="translate(473.5 315.5)" width="29" height="12">DONE</text>
|
||||
</svg>
|
||||
|
After Width: | Height: | Size: 12 KiB |
|
|
@ -16,3 +16,47 @@ p
|
|||
+row
|
||||
for cell in ["Apple", "is", "looking", "at", "buying", "U.K.", "startup", "for", "$", "1", "billion"]
|
||||
+cell=cell
|
||||
|
||||
p
|
||||
| Fist, the raw text is split on whitespace characters, similar to
|
||||
| #[code text.split(' ')]. Then, the tokenizer processes the text from
|
||||
| left to right. On each substring, it performs two checks:
|
||||
|
||||
+list("numbers")
|
||||
+item
|
||||
| #[strong Does the substring match a tokenizer exception rule?] For
|
||||
| example, "don't" does not contain whitespace, but should be split
|
||||
| into two tokens, "do" and "n't", while "U.K." should always
|
||||
| remain one token.
|
||||
+item
|
||||
| #[strong Can a prefix, suffix or infixes be split off?]. For example
|
||||
| punctuation like commas, periods, hyphens or quotes.
|
||||
|
||||
p
|
||||
| If there's a match, the rule is applied and the tokenizer continues its
|
||||
| loop, starting with the newly split substrings. This way, spaCy can split
|
||||
| #[strong complex, nested tokens] like combinations of abbreviations and
|
||||
| multiple punctuation marks.
|
||||
|
||||
+aside
|
||||
| #[strong Tokenizer exception:] Special-case rule to split a string into
|
||||
| several tokens or prevent a token from being split when punctuation rules
|
||||
| are applied.#[br]
|
||||
| #[strong Prefix:] Character(s) at the beginning, e.g.
|
||||
| #[code $], #[code (], #[code “], #[code ¿].#[br]
|
||||
| #[strong Suffix:] Character(s) at the end, e.g.
|
||||
| #[code km], #[code )], #[code ”], #[code !].#[br]
|
||||
| #[strong Infix:] Character(s) in between, e.g.
|
||||
| #[code -], #[code --], #[code /], #[code …].#[br]
|
||||
|
||||
+image
|
||||
include ../../../assets/img/docs/tokenization.svg
|
||||
.u-text-right
|
||||
+button("/assets/img/docs/tokenization.svg", false, "secondary").u-text-tag View large graphic
|
||||
|
||||
p
|
||||
| While punctuation rules are usually pretty general, tokenizer exceptions
|
||||
| strongly depend on the specifics of the individual language. This is
|
||||
| why each #[+a("/docs/api/language-models") available language] has its
|
||||
| own subclass like #[code English] or #[code German], that loads in lists
|
||||
| of hard-coded data and exception rules.
|
||||
|
|
|
|||
|
|
@ -94,9 +94,10 @@ p
|
|||
include _spacy-101/_tokenization
|
||||
|
||||
+infobox
|
||||
| To learn more about how spaCy's tokenizer and its rules work in detail,
|
||||
| how to #[strong customise] it and how to #[strong add your own tokenizer]
|
||||
| to a processing pipeline, see the usage guide on
|
||||
| To learn more about how spaCy's tokenization rules work in detail,
|
||||
| how to #[strong customise and replace] the default tokenizer and how to
|
||||
| #[strong add language-specific data], see the usage guides on
|
||||
| #[+a("/docs/usage/adding-languages") adding languages] and
|
||||
| #[+a("/docs/usage/customizing-tokenizer") customising the tokenizer].
|
||||
|
||||
+h(3, "annotations-pos-deps") Part-of-speech tags and dependencies
|
||||
|
|
|
|||
Loading…
Reference in New Issue
Block a user