Videos
See AI2's full collection of videos on our YouTube channel.Viewing 231-240 of 243 videos
Toward Scene Understanding
December 3, 2014 | Roozbeh MottaghiScene understanding is one of the holy grails of computer vision, and despite decades of research, it is still considered an unsolved problem. In this talk, I will present a number of methods, which help us take a step further towards the ultimate goal of holistic scene understanding. In particular, I will talk…
Open and Exploratory Extraction of Relations (and Common Sense) from Large Text Corpora
November 10, 2014 | Alan AkbikThe use of deep syntactic information such as typed dependencies has been shown to be very effective in Information Extraction (IE). Despite this potential, the process of manually creating rule-based information extractors that operate on dependency trees is not intuitive for persons without an extensive NLP…
Deep Natural Language Semantics by Combining Logical and Distributional Methods using Probabilistic Logic
November 4, 2014 | Raymond MooneyTraditional logical approaches to semantics and newer distributional or vector space approaches have complementary strengths and weaknesses.We have developed methods that integrate logical and distributional models by using a CCG-based parser to produce a detailed logical form for each sentence, and combining the…
Large-Scale Paraphrasing for Natural Language Generation
October 1, 2014 | Chris Callison-BurchI will present my method for learning paraphrases - pairs of English expressions with equivalent meaning - from bilingual parallel corpora, which are more commonly used to train statistical machine translation systems. My method equates pairs of English phrases like --thrown into jail, imprisoned-- when they…
Modeling Biological Processes for Reading Comprehension
August 5, 2014 | Jonathan BerantMachine reading calls for programs that read and understand text, but most current work only attempts to extract facts from redundant web-scale corpora. In this talk, I will focus on a new reading comprehension task that requires complex reasoning over a single document. The input is a paragraph describing a…
Extracting Knowledge from Text with Tractable Markov Logic and Symmetry-Based Semantic Parsing
July 25, 2014 | Pedro DomingosBuilding very large commonsense knowledge bases and reasoning with them is a long-standing dream of AI. Today that knowledge is available in text; all we have to do is extract it. Text, however, is extremely messy, noisy, ambiguous, incomplete, and variable. A formal representation of it needs to be both…
Paul Allen Discusses AI2 and the Future of AI (Discussion of AI2 begins at 17:30)
June 4, 2014 | Paul AllenPaul Allen discusses his vision for the future of AI and AI2 in this fireside chat moderated by Gary Marcus of New York University at the 10th Anniversary Symposium - Allen Institute for Brain Science. AI2-related discussion begins at 17:30.
Crowdsourcing Insights into Problem Structure for Scientific Discovery
May 13, 2014 | Bart SelmanIn recent years, there has been tremendous progress in solving large-scale reasoning and optimization problems. Central to this progress has been the ability to automatically uncover hidden problem structure. Nevertheless, for the very hardest computational tasks, human ingenuity still appears indispensable. We…
Learning and Inference for Natural Language Understanding
March 31, 2014 | Dan RothMachine Learning and Inference methods have become ubiquitous and have had a broad impact on a range of scientific advances and technologies and on our ability to make sense of large amounts of data. Research in Natural Language Processing has both benefited from and contributed to advancements in these methods…
The Aha! Moment: From Data to Insight
February 26, 2014 | Dafna ShahafThe amount of data in the world is increasing at incredible rates. Large-scale data has potential to transform almost every aspect of our world, from science to business; for this potential to be realized, we must turn data into insight. In this talk, I will describe two of my efforts to address this problem…