ClassroomThe classroom
Back to the lesson libraryMECHANISM · 14 MIN
M14.2 CONNECT THE MECHANISM

Turn text into structured labels and relations

A news story says someone joined a company. Tag the words, find the names, and parse who did what, then learn how to tell whether the labels are any good.

LESSON OVERVIEW14 min lesson

Lesson overview

A news story says someone joined a company. Tag the words, find the names, and parse who did what, then learn how to tell whether the labels are any good.

What you’ll explore

  • Tagging, parsing, named-entity recognition, and information extraction impose annotation schemas on language; ambiguity and domain shifts affect their reliability.
GO TO THE SOURCE

Original explanations, connected to the research.

Building a Large Annotated Corpus of English: The Penn Treebank (Marcus, Santorini & Marcinkiewicz, 1993)Speech and Language Processing, 3rd edition draft, chapters on POS tagging, NER, and dependency parsing (Jurafsky & Martin)Universal Dependencies — universal POS tagsIntroduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition (Tjong Kim Sang & De Meulder, 2003)
Suggest a correction

A precise note can make an explanation better.

Choose the scene and describe what needs attention. Download a feedback file to share through a channel you already use. This page does not send feedback or connect you with a reviewer.

The file includes this note, the scene title, and lesson metadata. Your saved progress and quiz responses are excluded. Download before leaving or reloading to keep your note.