Papers
See AI2's Award Winning Papers
Learn more about AI2's Lasting Impact Award
Viewing 431-440 of 991 papers
Conversational Multi-Hop Reasoning with Neural Commonsense Knowledge and Symbolic Logic Rules
Forough Arabshahi, Jennifer Lee, A. Bosselut, Yejin Choi, Tom MitchellEMNLP • 2021 One of the challenges faced by conversational agents is their inability to identify unstated presumptions of their users’ commands, a task trivial for humans due to their common sense. In this paper, we propose a zero-shot commonsense reasoning system for…General-Purpose Question-Answering with Macaw
Oyvind Tafjord, Peter ClarkarXiv • 2021 Despite the successes of pretrained language models, there are still few high-quality, general-purpose QA systems that are freely available. In response, we present MACAW, a versatile, generative question-answering (QA) system that we are making available to…Domain-Specific Multi-Level IR Rewriting for GPU: The Open Earth Comp
Gysi, T., C. Müller, T. Grosser, T. Hoefler, O. Zinenko, O. Fuhrer, E. Davis, and T. WickyACM Transactions on Architecture and Code Optimization • 2021 Most compilers have a single core intermediate representation (IR) (e.g., LLVM) sometimes complemented with vaguely defined IR-like data structures. This IR is commonly low-level and close to machine instructions. As a result, optimizations relying on domain…Factorizing Perception and Policy for Interactive Instruction Following
Kunal Pratap Singh, Suvaansh Bhambri, Byeonghwi Kim, R. Mottaghi, Jonghyun ChoiarXiv • 2021 Performing simple household tasks based on language directives is very natural to humans, yet it remains an open challenge for AI agents. The ‘interactive instruction following’ task attempts to make progress towards building agents that jointly navigate…It's not Rocket Science : Interpreting Figurative Language in Narratives
Tuhin Chakrabarty, Yejin Choi, Vered ShwartzACL • 2021 Figurative language is ubiquitous in English. Yet, the vast majority of NLP research focuses on literal language. Existing text representations by design rely on compositionality, while figurative language is often non-compositional. In this paper, we study…Question Decomposition with Dependency Graphs
Matan Hasson, Jonathan BerantAKBC • 2021 QDMR is a meaning representation for complex questions, which decomposes questions into a sequence of atomic steps. While stateof-the-art QDMR parsers use the common sequence-to-sequence (seq2seq) approach, a QDMR structure fundamentally describes labeled…All That’s ‘Human’ Is Not Gold: Evaluating Human Evaluation of Generated Text
Elizabeth Clark, Tal August, Sofia Serrano, Nikita Haduong, Suchin Gururangan, Noah A. SmithACL • 2021 Human evaluations are typically considered the gold standard in natural language generation, but as models' fluency improves, how well can evaluators detect and judge machine-generated text? We run a study assessing non-experts' ability to distinguish between…Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies
Mor Geva, Daniel Khashabi, Elad Segal, Tushar Khot, Dan Roth, Jonathan BerantTACL • 2021 A key limitation in current datasets for multi-hop reasoning is that the required steps for answering the question are mentioned in it explicitly. In this work, we introduce STRATEGYQA, a question answering (QA) benchmark where the required reasoning steps…Edited Media Understanding Frames: Reasoning about the Intent and Implications of Visual Disinformation
Jeff Da, Maxwell Forbes, Rowan Zellers, Anthony Zheng, Jena D. Hwang, Antoine Bosselut, Yejin ChoiACL • 2021 Multimodal disinformation, from `deepfakes' to simple edits that deceive, is an important societal problem. Yet at the same time, the vast majority of media edits are harmless -- such as a filtered vacation photo. The difference between this example, and…Effective Attention Sheds Light On Interpretability
Kaiser Sun and Ana MarasovićFindings of ACL • 2021 An attention matrix of a transformer selfattention sublayer can provably be decomposed into two components and only one of them (effective attention) contributes to the model output. This leads us to ask whether visualizing effective attention gives different…