LING 388: Computers and Language Lecture 10
Class exercises with TA last week Some feedback: how did it go?
Named Entity Recognition (NER) Jurafsky & Martin (JM) textbook on Speech and Language Processing Used in LING 438/538 course in Fall See JM Chapter 22: Information Extraction 22.1 Named Entity Recognition 22.2 Relation Detection and Classification also Chapter 21 for Anaphora Resolution
Named Entity Recognition (NER) (also Identification and Extraction) tries to locate and classify atomic elements in text into predefined categories such as the names of persons, organizations, locations, expressions of times, quantities, monetary values, percentages, etc. [paraphrased from http://en.wikipedia.org/wiki/Named- entity_recognition]
Illinois NER System Website: http://cogcomp.org/page/demo_view/ner
Example WSJ9_002.txt
Illinois NER System NLP systems might also compute: anaphora reference http://cogcomp.cs.illinois.edu/demo/ner/
JM Chapter 22
JM Chapter 22
JM Chapter 22 Ambiguity: sometimes systematic, sometimes not
Illinois NER system On the ambiguous examples, so-so performance:
JM Chapter 22 Word by word labeling (IOB “inside outside beginning”)
JM Chapter 22 POS information Shape Syntactic chunking
JM Chapter 22
JM Chapter 22 What features to use in making a decision (used also for Machine Learning)?