Videos
See AI2's full collection of videos on our YouTube channel.Viewing 131-140 of 251 videos
Submodular Optimization and Data Summarization with Applications to Computer Vision
October 17, 2018 | Rishabh IyerVisual Data in the form of Images and Videos have been growing at an unprecedented rate in the last few years. While this massive data is a blessing to data science by helping improve predictive accuracy, it is also a curse since humans are unable to consume this large amount of data. Moreover, today, machine…
Learning from Biomedical Data
October 10, 2018 | Lucy WangHuman interpretability is essential in biomedicine, because information flow between computational platforms and human stakeholders is crucial to the proper management and care of disease. Biomedical data is abundant, but do not lend themselves to easy summary and interpretation. Luckily, there are many…
Resolving Abstract Anaphors in Discourse—Uphill Battles with Neural Ranking Models and Automatic Data Extraction
October 1, 2018 | Ana MarasovicAbstract Anaphora Resolution (AAR) is a challenging task of finding a (typically) non-nominal antecedent of pronouns and noun phrases that refer to abstract objects like facts, events, actions or situations, in the (typically) preceding discourse. An example is given below. Our intuition is that we can learn…
The relevance search in PubMed
September 27, 2018 | Nicolas FioriniPubMed is a free search engine for the biomedical literature accessed by millions of users from around the world each day. With the rapid growth of biomedical literature, finding and retrieving the most relevant papers for a given query is increasingly challenging. I will introduce Best Match, the new relevance…
From Paraphrase Modeling to Controlled Generation
September 19, 2018 | Kevin GimpelA key challenge in natural language understanding is recognizing when two sentences have the same meaning. I'll discuss our work on this problem over the past few years, including the exploration of compositional functional architectures, learning criteria, and naturally-occurring sources of training data. The…
Exposing Brittleness in Reading Comprehension Systems
August 29, 2018 | Robin JiaReading comprehension systems that answer questions over a context passage can often achieve high test accuracy, but they are frustratingly brittle: they often rely heavily on superficial cues, and therefore struggle on out-of-domain inputs. In this talk, I will describe our work on understanding and challenging…
Crafting Intelligible Intelligence
August 28, 2018 | Dan WeldSince AI software uses techniques like deep lookahead search and stochastic optimization of huge neural networks, it often results in complex behavior that is difficult for people to understand. Yet organizations are deploying AI algorithms in many mission-critical settings. To trust their behavior, we must make…
Neural Semi-supervised Learning under Domain Shift
August 24, 2018 | Sebastian RuderDeep neural networks excel at learning from labeled data. In contrast, learning from unlabeled data, especially under domain shift, which is common in many real-world applications, remains a challenge. In this talk, I will touch on three aspects of learning under domain shift: First I will discuss an approach to…
Neural Symbolic Machines: Efficient Reinforcement Learning for Semantic Parsing and Program Synthesis
August 21, 2018 | Chen LiangLearning to generate programs from natural language can support a wide range of applications including question answering, virtual assistant, AutoML, etc. It is natural to apply reinforcement learning to directly optimize the task reward, and generalization to new unseen inputs is crucial. However, three…
Knowledge-Aware Natural Language Understanding
August 6, 2018 | Pradeep DasigiNatural Language Understanding systems typically involve encoding and reasoning components that are trained end-to-end to produce task-specific outputs given human utterances as inputs. I will talk about the role of external knowledge in making both these components better, and describe NLU systems that benefit…