Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Dataset:[Natural_Questions_HTML_reduced_all](https://huggingface.co/datasets/SaulLu/Natural_Questions_HTML_reduced_all)
|
| 2 |
+
|
| 3 |
+
Training example with metadata:
|
| 4 |
+
```
|
| 5 |
+
htmlOn |||
|
| 6 |
+
<li id:n-sitesupport><a>Donate to Wikipedia</a></li>
|
| 7 |
+
<li id:n-shoplink><a>Wikipedia store</a></li>
|
| 8 |
+
</ul></div></div><div class:portal id:p-interaction><h3 id:p-interaction-label>Interaction</h3>
|
| 9 |
+
<div class:body><ul><li id:n-help><a>Help</a></li>
|
| 10 |
+
<li id:n-aboutsite><a>About Wikipedia</a></li>
|
| 11 |
+
<li id:n-portal><a>Community portal</a></li>
|
| 12 |
+
<li id:n-recentchanges><a>Recent changes</a></li>
|
| 13 |
+
<li id:n-contactpage><a>Contact page</a></li>
|
| 14 |
+
</ul></div></div><div class:portal id:p-tb><h3 id:p-tb-label>Tools</h3>
|
| 15 |
+
<div class:body><ul><li id:t-whatlinkshere><a>What links here</a></li>
|
| 16 |
+
<li id:t-recentchangeslinked><a>Related changes</a></li>
|
| 17 |
+
<li id:t-upload><a>Upload file</a></li>
|
| 18 |
+
<li id:t-specialpages><a>Special pages</a></li>
|
| 19 |
+
<li id:t-permalink><a>Permanent link</a></li>
|
| 20 |
+
<li id:t-info><a>Page information</a></li>
|
| 21 |
+
<li id:t-wikibase><a>Wikidata item</a></li>
|
| 22 |
+
<li id:t-cite><a>Cite this page</a></li>
|
| 23 |
+
</ul></div></div><div class:portal id:p-coll-print_export><h3 id:p-coll-print_export-label>Print/export</h3>
|
| 24 |
+
<div class:body><ul><li id:coll-create_a_book><a>Create a book</a></li>
|
| 25 |
+
<li id:coll-download-as-rdf2latex><a>Download as PDF</a></li>
|
| 26 |
+
<li id:t-print><a>Printable version</a></li>
|
| 27 |
+
</ul></div></div><div class:portal id:p-lang><h3 id:p-lang-label>Languages</h3>
|
| 28 |
+
<div class:body><ul><li class:interlanguage-link interwiki-ca><a class:interlanguage-link-target>Català</a></li>
|
| 29 |
+
<li class:interlanguage-link interwiki-da><a class:interlanguage-link-target>Dansk</a></li>
|
| 30 |
+
<li class:interlanguage-link interwiki-de><a class:interlanguage-link-target>Deutsch</a></li>
|
| 31 |
+
<li class:interlanguage-link interwiki-es><a class:interlanguage-link-target>Español</a></li>
|
| 32 |
+
<li class:interlanguage-link interwiki-eu><a class:interlanguage-link-target>Euskara</a></li>
|
| 33 |
+
<li class:interlanguage-link interwiki-fa><a class:interlanguage-link-target>فارسی</a></li>
|
| 34 |
+
<li class:interlanguage-link interwiki-fr><a class:interlanguage-link-target>Français</a></li>
|
| 35 |
+
<li class:interlanguage-link interwiki-id><a class:interlanguage-link-target>Bahasa Indonesia</a></li>
|
| 36 |
+
<li class:interlanguage-link interwiki-nl><a class:interlanguage-link-target>Nederlands</a></li>
|
| 37 |
+
<li class:interlanguage-link interwiki-pt><a class:interlanguage-link-target>Português</a></li>
|
| 38 |
+
<li class:interlanguage-link interwiki-fi><a class:interlanguage-link-target>Suomi</a></li>
|
| 39 |
+
<li class:interlanguage-link interwiki-vi><a class:interlanguage-link-target>Tiếng Việt</a></li>
|
| 40 |
+
<button class:mw-interlanguage-selector mw-ui-button>5 more</button>
|
| 41 |
+
</ul><div class:after-portlet after-portlet-lang><span class:wb-langlinks-edit wb-langlinks-link><a class:wbc-editpage>Edit links</a></span></div>
|
| 42 |
+
</div></div></
|
| 43 |
+
```
|