Papers
See AI2's Award Winning Papers
Learn more about AI2's Lasting Impact Award
Viewing 551-560 of 991 papers
Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning
Lianhui Qin, Vered Shwartz, P. West, Chandra Bhagavatula, Jena D. Hwang, Ronan Le Bras, Antoine Bosselut, Yejin ChoiEMNLP • 2020 Abductive and counterfactual reasoning, core abilities of everyday human cognition, require reasoning about what might have happened at time t, while conditioning on multiple contexts from the relative past and future. However, simultaneous incorporation of…Beyond Instructional Videos: Probing for More Diverse Visual-Textual Grounding on YouTube
Jack Hessel, Z. Zhu, Bo Pang, Radu Soricut EMNLP • 2020 Pretraining from unlabelled web videos has quickly become the de-facto means of achieving high performance on many video understanding tasks. Features are learned via prediction of grounded relationships between visual content and automatic speech recognition…CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning
Bill Yuchen Lin, M. Shen, Wangchunshu Zhou, Pei Zhou, Chandra Bhagavatula, Yejin Choi, X. RenEMNLP • 2020 Recently, large-scale pre-trained language models have demonstrated impressive performance on several commonsense benchmark datasets. However, building machines with common-sense to compose realistically plausible sentences remains challenging. In this paper…Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics
Swabha Swayamdipta, Roy Schwartz, Nicholas Lourie, Yizhong Wang, Hannaneh Hajishirzi, Noah A. Smith, Yejin ChoiEMNLP • 2020 Large datasets have become commonplace in NLP research. However, the increased emphasis on data quantity has made it challenging to assess the quality of data. We introduce "Data Maps"---a model-based tool to characterize and diagnose datasets. We leverage a…Does my multimodal model learn cross-modal interactions? It’s harder to tell than you might think!
Jack Hessel, Lillian LeeEMNLP • 2020 Modeling expressive cross-modal interactions seems crucial in multimodal tasks, such as visual question answering. However, sometimes high-performing black-box algorithms turn out to be mostly exploiting unimodal signals in the data. We propose a new…Do Language Embeddings Capture Scales?
Xikun Zhang, Deepak Ramachandran, Ian Tenney, Yanai Elazar, Dan RothFindings of EMNLP • BlackboxNLP Workshop • 2020 Pretrained Language Models (LMs) have been shown to possess significant linguistic, common sense, and factual knowledge. One form of knowledge that has not been studied yet in this context is information about the scalar magnitudes of objects. We show that…Domain-Specific Lexical Grounding in Noisy Visual-Textual Documents
Gregory Yauney, Jack Hessel, David MimnoEMNLP • 2020 Images can give us insights into the contextual meanings of words, but current imagetext grounding approaches require detailed annotations. Such granular annotation is rare, expensive, and unavailable in most domainspecific contexts. In contrast, unlabeled…Easy, Reproducible and Quality-Controlled Data Collection with Crowdaq
Qiang Ning, Hao Wu, Pradeep Dasigi, Dheeru Dua, Matt Gardner, IV RobertL.Logan, Ana Marasović, Z. NieEMNLP • Demo • 2020 High-quality and large-scale data are key to success for AI systems. However, large-scale data annotation efforts are often confronted with a set of common challenges: (1) designing a user-friendly annotation interface; (2) training enough annotators…Fact or Fiction: Verifying Scientific Claims
David Wadden, Kyle Lo, Lucy Lu Wang, Shanchuan Lin, Madeleine van Zuylen, Arman Cohan, Hannaneh HajishirziEMNLP • 2020 We introduce the task of scientific fact-checking. Given a corpus of scientific articles and a claim about a scientific finding, a fact-checking model must identify abstracts that support or refute the claim. In addition, it must provide rationales for its…Grounded Compositional Outputs for Adaptive Language Modeling
Nikolaos Pappas, Phoebe Mulcaire, Noah A. SmithEMNLP • 2020 Language models have emerged as a central component across NLP, and a great deal of progress depends on the ability to cheaply adapt them (e.g., through finetuning) to new domains and tasks. A language model's vocabulary---typically selected before training…