Google, IBM & Meta Certificates — All 10,000+ Courses at 40% Off
One annual plan covers every course and certificate on Coursera. 40% off for a limited time.
Get Full Access
Learn how the Expectation-Maximization (EM) algorithm can be effectively applied to solve pronoun-anaphora resolution problems in natural language processing through this seminar by Eugene Charniak from Brown University's Department of Computer Science. Explore the theoretical foundations and practical applications of EM in computational linguistics, specifically focusing on how this statistical method helps identify the correct antecedents for pronouns in text. Discover the algorithmic approaches and experimental results that demonstrate the effectiveness of EM for this challenging NLP task, gaining insights into both the mathematical underpinnings and real-world implementation considerations for pronoun resolution systems.
