Explore cutting-edge research in Natural Language Processing through a series of graduate student presentations from the UW Paul G. Allen School of Computer Science & Engineering. Delve into four diverse topics: Julian Michael's approach to representing meaning with question-answer pairs, Antoine Bosselut's work on commonsense transformers for automatic knowledge graph construction, Lucy Lin's analysis of religiosity and public policy in Congress using scalable NLP methods, and Sachin Mehta's efficient machine learning techniques for visual and textual data. Gain insights into innovative NLP techniques, including semantic representation, commonsense reasoning, large-scale text analysis, and efficient deep learning models for sequence modeling. Recorded on November 7, 2019, this 51-minute colloquium offers a comprehensive overview of current NLP research trends and their applications in various domains.