Yhteystiedot

Yleisen kielitieteen laitos
PL 9 (Siltavuorenpenger 20 A)
00014 HELSINGIN YLIOPISTO

Puhelin +358 (09) 1911 (vaihde)
Faksi +358 (09) 191 29307

tulostettava versio

7. Further Topics: Named Entity Recognition

• Lecture notes
  • CoNLL-2002 Shared Task: Language Independent Named Entity Recognition
    Erik Tjong Kim Sang
  • CoNLL-2003 Shared Task: Language Independent Named Entity Recognition
    Erik Tjong Kim Sang and Fien De Meulder
• Further reading
  • Introduction to the CoNLL-2002 Shared Task: Language Independent Named Entity Recognition Erik Tjong Kim Sang (2002)
  • Introduction to the CoNLL-2003 Shared Task: Language Independent Named Entity Recognition Erik Tjong Kim Sang and Fien De Meulder (2003)

5.1. OpenNLP Name Finder

• Practical work
  • OpenNLP name finder recognizes several different types of entities. It uses a separate maximum entropy model for each type. There are 7 ready-made models: person, location, organization, date, time, money, percentage.
  • Copy the script clt350-opennlp-namefinder to your directory and make it executable. This script runs OpenNLP sentence detector followed by OpenNLP name finder. It takes input from stdin and sends output to stdout.
  • Use it like this to find named entities in Sonnet 130:
    ./clt350-opennlp-namefinder <sonnet130.txt >names.txt &
  • Try named entity recognition with bigger texts and corpora: Jane Austen's Northanger Abbey, or half a million words in Jane Austen's six main novels.

5.2. Training New Models

• Practical work
  • Training Models for OpenNLP Name Finder

Assignment 3

• Training a Maximum Entropy Model