Papers
See AI2's Award Winning Papers
Learn more about AI2's Lasting Impact Award
Viewing 391-400 of 991 papers
Finetuning Pretrained Transformers into RNNs
Jungo Kasai, Hao Peng, Yizhe Zhang, Dani Yogatama, Gabriel Ilharco, Nikolaos Pappas, Yi Mao, Weizhu Chen, Noah A. SmithEMNLP • 2021 Transformers have outperformed recurrent neural networks (RNNs) in natural language generation. But this comes with a significant computational cost, as the attention mechanism’s complexity scales quadratically with sequence length. Efficient transformer…Generative Context Pair Selection for Multi-hop Question Answering
Dheeru Dua, Cicero Nogueira dos Santos, Patrick Ng, Ben Athiwaratkun, Bing Xiang, Matt Gardner, Sameer SinghEMNLP • 2021 Compositional reasoning tasks like multi-hop question answering, require making latent decisions to get the final answer, given a question. However, crowdsourced datasets often capture only a slice of the underlying task distribution, which can induce…GooAQ: Open Question Answering with Diverse Answer Types
Daniel Khashabi, Amos Ng, Tushar Khot, Ashish Sabharwal, Hanna Hajishirzi, Chris Callison-BurchFindings of EMNLP • 2021 While day-to-day questions come with a variety of answer types, the current questionanswering (QA) literature has failed to adequately address the answer diversity of questions. To this end, we present GOOAQ, a large-scale dataset with a variety of answer…How Much Coffee Was Consumed During EMNLP 2019? Fermi Problems: A New Reasoning Challenge for AI
A. Kalyan, Abhinav Kumar, Arjun Chandrasekaran, Ashish Sabharwal, Peter ClarkEMNLP • 2021 Many real-world problems require the combined application of multiple reasoning abilities employing suitable abstractions, commonsense knowledge, and creative synthesis of problem-solving strategies. To help advance AI systems towards such capabilities, we…Learning with Instance Bundles for Reading Comprehension
Dheeru Dua, Pradeep Dasigi, Sameer Singh and Matt GardnerEMNLP • 2021 When training most modern reading comprehension models, all the questions associated with a context are treated as being independent from each other. However, closely related questions and their corresponding answers are not independent, and leveraging these…Measuring Association Between Labels and Free-Text Rationales
Sarah Wiegreffe, Ana Marasović, Noah A. SmithEMNLP • 2021 Interpretable NLP has taking increasing interest in ensuring that explanations are faithful to the model’s decision-making process. This property is crucial for machine learning researchers and practitioners using explanations to better understand models…Mitigating False-Negative Contexts in Multi-document Question Answering with Retrieval Marginalization
Ansong Ni, Matt Gardner, Pradeep DasigiEMNLP • 2021 Question Answering (QA) tasks requiring information from multiple documents often rely on a retrieval model to identify relevant information from which the reasoning model can derive an answer. The retrieval model is typically trained to maximize the…Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences
Denis Emelin, Ronan Le Bras, Jena D. Hwang, Maxwell Forbes, Yejin ChoiEMNLP • 2021 In social settings, much of human behavior is governed by unspoken rules of conduct. For artificial systems to be fully integrated into social environments, adherence to such norms is a central prerequisite. We investigate whether contemporary NLG models can…MS2: Multi-Document Summarization of Medical Studies
Jay DeYoung, Iz Beltagy, Madeleine van Zuylen, Bailey Kuehl, Lucy Lu WangEMNLP • 2021 To assess the effectiveness of any medical intervention, researchers must conduct a timeintensive and highly manual literature review. NLP systems can help to automate or assist in parts of this expensive process. In support of this goal, we release MSˆ2…Paired Examples as Indirect Supervision in Latent Decision Models
Nitish Gupta, Sameer Singh, Matt Gardner and Dan RothEMNLP • 2021 Compositional, structured models are appealing because they explicitly decompose problems and provide interpretable intermediate outputs that give confidence that the model is not simply latching onto data artifacts. Learning these models is challenging…