Papers
See AI2's Award Winning Papers
Learn more about AI2's Lasting Impact Award
Viewing 451-460 of 991 papers
Efficient Passage Retrieval with Hashing for Open-domain Question Answering
Ikuya Yamada, Akari Asai, Hanna HajishirziACL • 2021 Most state-of-the-art open-domain question answering systems use a neural retrieval model to encode passages into continuous vectors and extract them from a knowledge source. However, such retrieval models often require large memory to run because of the…Prompting Contrastive Explanations for Commonsense Reasoning Tasks
Bhargavi Paranjape, Julian Michael, Marjan Ghazvininejad, Luke Zettlemoyer, Hanna HajishirziFindings of ACL • 2021 Many commonsense reasoning NLP tasks involve choosing between one or more possible answers to a question or prompt based on knowledge that is often implicit. Large pretrained language models (PLMs) can achieve near-human performance on such tasks, while…ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language
Oyvind Tafjord, B. D. Mishra, P. ClarkFindings of ACL • 2021 Transformers have been shown to emulate logical deduction over natural language theories (logical rules expressed in natural language), reliably assigning true/false labels to candidate implications. However, their ability to generate implications of a theory…fv3gfs-wrapper: a Python wrapper of the FV3GFS atmospheric model
McGibbon, J., N. Brenowitz, M. Cheeseman, S. K. Clark, J. Dahm, E. Davis, O. D. Elbert, R. C. George, L. M. Harris, B. Henn, A. Kwa, W. A. Perkins, O. Watt-Meyer, T. Wicky, C. S. Bretherton, and O. FuhrerGeoscientific Model Development • 2021 Simulation software in geophysics is traditionally written in Fortran or C++ due to the stringent performance requirements these codes have to satisfy. As a result, researchers who use high-productivity languages for exploratory work often find these codes…Correcting weather and climate models by machine learning nudged historical simulations
Watt-Meyer, O., N. Brenowitz, S. K. Clark, B. Henn, A. Kwa, J. McGibbon, W. A. Perkins, and C. S. BrethertonGeophysical Research Letters • 2021 Due to limited resolution and inaccurate physical parameterizations, weather and climate models consistently develop biases compared to the observed atmosphere. Using the FV3GFS model at coarse resolution, we propose a method of machine learning corrective…Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills
Ori Yoran, Alon Talmor, Jonathan BerantarXiv • 2021 Models pre-trained with a language modeling objective possess ample world knowledge and language skills, but are known to struggle in tasks that require reasoning. In this work, we propose to leverage semi-structured tables, and automatically generate at…Analyzing Commonsense Emergence in Few-shot Knowledge Models
Jeff Da, Ronan Le Bras, Ximing Lu, Yejin Choi, Antoine BosselutAKBC • 2021 Recently, commonsense knowledge models — pretrained language models (LM) finetuned on knowledge graph (KG) tuples — showed that considerable amounts of commonsense knowledge can be encoded in the parameters of large language models [Bosselut et al., 2019…Scarecrow: A Framework for Scrutinizing Machine Text
Yao Dou, Maxwell Forbes, Rik Koncel-Kedziorski, Noah A. Smith, Yejin ChoiarXiv • 2021 Modern neural text generation systems can produce remarkably fluent and grammatical texts. While earlier language models suffered from repetition and syntactic errors, the errors made by contemporary models are often semantic, narrative, or discourse failures…Is GPT-3 Text Indistinguishable from Human Text? Scarecrow: A Framework for Scrutinizing Machine Text
Yao Dou, Maxwell Forbes, Rik Koncel-Kedziorski, Noah A. Smith, Yejin ChoiarXiv • 2021 Modern neural language models can produce remarkably fluent and grammatical text. So much, in fact, that recent work by Clark et al. (2021) has reported that conventional crowdsourcing can no longer reliably distinguish between machine-authored (GPT-3) and…Break, Perturb, Build: Automatic Perturbation of Reasoning Paths through Question Decomposition
Mor Geva, Tomer Wolfson, Jonathan BerantTACL • 2021 Recent efforts to create challenge benchmarks that test the abilities of natural language understanding models have largely depended on human annotations. In this work, we introduce the “Break, Perturb, Build” (BPB) framework for automatic reasoning-oriented…