Papers
See AI2's Award Winning Papers
Learn more about AI2's Lasting Impact Award
Viewing 321-330 of 991 papers
Situated Dialogue Learning through Procedural Environment Generation
Prithviraj Ammanabrolu, Renee Jia, Mark O. RiedlACL • 2022 We teach goal-driven agents to interactively act and speak in situated environments by training on generated curriculums. Our agents operate in LIGHT (Urbanek et al. 2019)—a large-scale crowd-sourced fantasy text adventure game wherein an agent perceives and…ACCoRD: A Multi-Document Approach to Generating Diverse Descriptions of Scientific Concepts
Sonia K. Murthy, Kyle Lo, Daniel King, Chandra Bhagavatula, Bailey Kuehl, Sophie Johnson, Jon Borchardt, Daniel S. Weld, Tom Hope, Doug DowneyarXiv • 2022 Systems that can automatically define unfamiliar terms hold the promise of improving the accessibility of scientific texts, especially for readers who may lack prerequisite background knowledge. However, current systems assume a single “best” description per…Understanding Dataset Difficulty with 𝒱-Usable Information
Kawin Ethayarajh, Yejin Choi, and Swabha SwayamdiptaICML • 2022 Estimating the difficulty of a dataset typically involves comparing state-of-the-art models to humans; the bigger the performance gap, the harder the dataset is said to be. However, this comparison provides little understanding of how difficult each instance…PRIMERA: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization
Wen Xiao, Iz Beltagy, G. Carenini, Arman CohanACL • 2022 We introduce PRIMERA, a pre-trained model for multi-document representation with a focus on summarization that reduces the need for dataset-specific architectures and large amounts of fine-tuning labeled data. PRIMERA uses our newly proposed pre-training…Better Retrieval May Not Lead to Better Question Answering
Zhengzhong Liang, Tushar Khot, Steven Bethard, Mihai Surdeanu, Ashish SabharwalarXiv • 2022 Considerable progress has been made recently in open-domain question answering (QA) problems, which require Information Retrieval (IR) and Reading Comprehension (RC). A popular approach to improve the system's performance is to improve the quality of the…Saturated Transformers are Constant-Depth Threshold Circuits
William Merrill, Ashish Sabharwal, Noah A. SmithTACL • 2022 Transformers have become a standard neural network architecture for many NLP problems, motivating theoretical analysis of their power in terms of formal languages. Recent work has shown that transformers with *hard* attention are quite limited in power, as…Scaling Creative Inspiration with Fine-Grained Functional Facets of Product Ideas
Tom Hope, Ronen Tamari, Hyeonsu Kang, Daniel Hershcovich, J. Chan, A. Kittur, Dafna ShahafCHI • 2022 Web-scale repositories of products, patents and scientific papers offer an opportunity for building automated systems that scour millions of existing ideas and assist users in discovering novel inspirations and solutions to problems. Yet the current way ideas…The Curious Case of Commonsense Intelligence
Yejin ChoiDaedalus • 2022 Abstract Commonsense intelligence is a long-standing puzzle in AI. Despite considerable advances in deep learning, AI continues to be narrow and brittle due to its lack of common sense. Why is common sense so trivial for humans but so hard for machines? In…From Who You Know to What You Read: Augmenting Scientific Recommendations with Implicit Social Networks
Hyeonsu Kang, Rafal Kocielnik, Andrew Head, Jiangjiang Yang, Matt Latzke, A. Kittur, Daniel S. Weld, Doug Downey, Jonathan BraggCHI • 2022 The ever-increasing pace of scientific publication necessitates methods for quickly identifying relevant papers. While neural recommenders trained on user interests can help, they still result in long, monotonous lists of suggested papers. To improve the…Inferring Implicit Relations with Language Models
Uri Katz, Mor Geva, Jonathan BerantNAACL • UnImplicit • 2022 A prominent challenge for modern language understanding systems is the ability to answer implicit reasoning questions, where the required reasoning steps for answering the question are not mentioned in the text explicitly. In this work, we investigate why…