Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore text dependencies, information cascades, and multi-input attention in this comprehensive lecture by David Smith from the Center for Language & Speech Processing at Johns Hopkins University. Delve into methods for inferring and exploiting dependency structures in texts, including a new directed spanning tree model for information cascades and a contrastive training procedure. Learn about extracting parallel passages from multilingual corpora using polylingual topic models to improve translation systems. Discover techniques for detecting and correcting multiple transcriptions of the same passage in noisy OCR data using multi-input attention models. Gain insights into applications of natural language processing in information retrieval, social sciences, and humanities, as well as computational linguistic models of structure learning and historical change.
