Stanford CS224N: Natural Language Processing with Deep Learning Course | Winter 2019 - Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 16 – Coreference Resolution

For more information about Stanford’s Artificial Intelligence professional and graduate programs, visit: https://stanford.io/30l2Kkw Professor Christopher Manning, Stanford University http://onlinehub.stanford.edu/ Professor Christopher Manning Thomas M. Siebel Professor in Machine Learning, Professor of Linguistics and of Computer Science Director, Stanford Artificial Intelligence Laboratory (SAIL) To follow along with the course schedule and syllabus, visit: http://web.stanford.edu/class/cs224n/index.html#schedule 0:00 Introduction 0:23 Announcements 2:00 What is Coreference Resolution? 12:04 Applications 16:40 Coreference Resolution in Two Steps 19:39 Mention Detection: Not so Simple 22:19 Can we avoid a pipelined system? 23:39 4. On to Coreference! First, some linguistics 26:11 Anaphora vs Coreference 27:59 Anaphora vs. Coreference 29:24 Anaphora vs. Cataphora 32:33 Four kinds of Coreference Models 34:43 Hobbs Algorithm Example 40:07 Knowledge-based Pronominal Coreference 45:01 Hobbs' algorithm: commentary 46:06 Coreference Models: Mention Pair 47:33 Mention Pair Training 48:05 Mention Pair Test Time 52:01 7. Coreference Models: Mention Ranking 54:57 Coreference Models: Training 56:05 Mention Ranking Models: Test Time 56:49 A. Non-Neural Coref Model: Features