Papers
See AI2's Award Winning Papers
Learn more about AI2's Lasting Impact Award
Viewing 271-280 of 1016 papers
REV: Information-Theoretic Evaluation of Free-Text Rationales
Hanjie Chen, Faeze Brahman, Xiang Ren, Yangfeng Ji, Yejin Choi, Swabha SwayamdiptaarXiv • 2022 information. Future work might explore evaluation that penalizes rationales which support incorrect predictions, thus bridging together predictive performance with interpretability metrics.Transparency Helps Reveal When Language Models Learn Meaning
Zhaofeng Wu, Will Merrill, Hao Peng, Iz Beltagy, Noah A. SmitharXiv • 2022 Many current NLP systems are built from language models trained to optimize unsupervised objectives on large amounts of raw text. Under what conditions might such a procedure acquire meaning? Our system-atic experiments with synthetic data reveal that, with…Is Reinforcement Learning (Not) for Natural Language Processing?: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization
R. Ramamurthy, Prithviraj Ammanabrolu, Kianté Brantley, Jack Hessel, R. Sifa, C. Bauckhage, Hannaneh Hajishirzi, Yejin ChoiArXiv • 2022 We tackle the problem of aligning pre-trained large language models (LMs) with human preferences. If we view text generation as a sequential decision-making problem, reinforcement learning (RL) appears to be a natural conceptual framework. However, using RL…Machine-learned climate model corrections from a global storm-resolving model: Performance across the annual cycle
Anna Kwa, Spencer. K. Clark, Brian Henn, Noah D. Brenowitz, Jeremy McGibbon, Oliver Watt-Meyer, W. Andre Perkins, Lucas Harris, and Christopher S. BrethertonESSOAr • 2022 One approach to improving the accuracy of a coarse-grid global climate model is to add machine-learned state-dependent corrections to the prognosed model tendencies, such that the climate model evolves more like a reference fine-grid global storm-resolving…Pace v0.1: A python-based performance-portable implementation of the FV3 dynamical core
Johann Dahm, Eddie Davis, Florian Deconinck, Oliver Elbert, Rhea George, Jeremy McGibbon, Tobias Wicky, Elynn Wu, Christopher Kung, Tal Ben-Nun, Lucas Harris, Linus Groner, and Oliver FuhrerEGUsphere • 2022 Progress in leveraging current and emerging high-performance computing infrastructures using traditional weather and climate models has been slow. This has become known more broadly as the software productivity gap. With the end of Moore's Law driving forward…Correcting a 200 km Resolution Climate Model in Multiple Climates by Machine Learning From 25 km Resolution Simulations
S. Clark, Noah Brenowitz, B. Henn, Anna Kwa, J. McGibbon, W. Perkins, Oliver Watt‐Meyer, C. Bretherton, L. HarrisJournal of Advances in Modeling Earth Systems • 2022 Bretherton et al. (2022, https://doi.org/10.1029/2021MS002794) demonstrated a successful approach for using machine learning (ML) to help a coarse‐resolution global atmosphere model with real geography (a ∼200 km version of NOAA's FV3GFS) evolve more like a…Multi-Scale Contrastive Co-Training for Event Temporal Relation Extraction
Hao-Ren Yao, Luke Breitfeller, Aakanksha Naik, Chunxiao Zhou, Carolyn RoséarXiv.org • 2022 Extracting temporal relationships between pairs of events in texts is a crucial yet challenging problem for natural language understanding. Depending on the distance between the events, models must learn to differently balance information from local and…Efficient Methods for Natural Language Processing: A Survey
Marcos Vinícius Treviso, Tianchu Ji, Ji-Ung Lee, Betty van Aken, Qingqing Cao, Manuel R. Ciosici, Michael Hassid, Kenneth Heafield, Sara Hooker, Pedro Henrique Martins, André F. T. Martins, Peter Milder, Colin Raffel, Jessica Zosa Forde, Emma Strubell, Edwin Simpson, N. Slonim, Jesse Dodge, Niranjan Balasubramanian, Iryna Gurevych, Leon Derczynski, Roy SchwartzarXiv • 2022 Getting the most out of limited resources allows advances in natural language processing (NLP) research and practice while being con-servative with resources. Those resources may be data, time, storage, or energy. Recent work in NLP has yielded interesting…Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks
Akari Asai, Matt Gardner, Hannaneh HajishirziNAACL • 2022 Retrieval-augmented generation models have shown state-of-the-art performance across many knowledge-intensive NLP tasks such as open-domain question answering and fact verification. These models are trained to generate a final output given retrieved passages…FaVIQ: FAct Verification from Information-seeking Questions
Jungsoo Park, Sewon Min, Jaewoo Kang, Luke Zettlemoyer, Hannaneh HajishirziACL • 2022 Despite significant interest in developing general purpose fact checking models, it is challenging to construct a large-scale fact verification dataset with realistic real-world claims. Existing claims are either authored by crowdworkers, thereby introducing…