Videos
See AI2's full collection of videos on our YouTube channel.Viewing 191-200 of 251 videos
Grounding and Generation of Natural Language Descriptions for Images and Videos
September 19, 2016 | Anna RohrbachIn recent years many challenging problems have emerged in the field of language and vision. Frequently the only form of available annotation is the natural language sentence associated with an image or video. How can we address complex tasks like automatic video description or visual grounding of textual phrases…
Exploring Relational Features and Learning
September 13, 2016 | Ajay NageshInformation Extraction has become an indispensable tool in our quest to handle the data deluge of the information age. In this talk, we discuss the categorization of complex relational features and outline methods to learn feature combinations through induction. We demonstrate the efficacy of induction…
Freebase Semantic Parsing With and Without QA Pairs
September 7, 2016 | Siva ReddyI will present three semantic parsing approaches for querying Freebase in natural language 1) training only on raw web corpus, 2) training on question-answer (QA) pairs, and 3) training on both QA pairs and web corpus. For 1 and 2, we conceptualise semantic parsing as a graph matching problem, where natural…
Distributed Representations of Keywords, Web sites and Pages
August 23, 2016 | Matthew PetersDistributed representations of words, phrases and sentences are central to recent advances in machine translation, language modeling, semantic similarity, and other tasks. In this talk, I'll explore ways to learn similar representations of search queries, web pages and web sites. The first portion of the talk…
Better Knowledge Graphs Through Probabilistic Graphical Models
August 22, 2016 | Jay PujaraAutomated question answering, knowledgeable digital assistants, and grappling with the massive data flooding the Web all depend on structured knowledge. Precise knowledge graphs capturing the many, complex relationships between entities are the missing piece for many problems, but knowledge graph construction is…
Exploiting Universal Grammatical Properties to Induce CCG Grammars
August 1, 2016 | Dan GarretteLearning NLP models from weak forms of supervision has become increasingly important as the field moves toward applications in new languages and domains. Much of the existing work in this area has focused on designing learning approaches that are able to make use of small amounts of human-generated data. In…
Open Information Extraction: Where Are We Going?
July 18, 2016 | Claudio Delli BoviThe Open Information Extraction (OIE) paradigm has received much attention in the NLP community over the last decade. Since the earliest days, most OIE approaches have been focusing on Web-scale corpora, which raises issues such as massive amounts of noise. Also, OIE systems can be very different in nature and…
Near-Optimal Adaptive Information Acquisition: Theory and Applications
July 15, 2016 | Yuxin ChenSequential information gathering, i.e., selectively acquiring the most useful data, plays a key role in interactive machine learning systems. Such problem has been studied in the context of Bayesian active learning and experimental design, decision making, optimal control and numerous other domains. In this talk…
Representing Meaning with a Combination of Logical and Distributional Models
June 21, 2016 | Katrin ErkAs the field of Natural Language Processing develops, more ambitious semantic tasks are being addressed, such as Question Answering (QA) and Recognizing Textual Entailment (RTE). Solving these tasks requires (ideally) an in-depth representation of sentence structure as well as expressive and flexible…
Relating Natural Language and Visual Recognition
June 20, 2016 | Marcus RohrbachLanguage is the most important channel for humans to communicate about what they see. To allow an intelligent system to effectively communicate with humans it is thus important to enable it to relate information in words and sentences with the visual world. For this a system should be compositional, so it is e.g…