Papers
See AI2's Award Winning Papers
Learn more about AI2's Lasting Impact Award
Viewing 211-220 of 241 papers
CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge
Alon Talmor, Jonathan Herzig, Nicholas Lourie, Jonathan BerantNAACL • 2019 When answering a question, people often draw upon their rich world knowledge in addition to the particular context. Recent work has focused primarily on answering questions given some relevant document or context, and required very little general background…MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms
ida Amini, Saadia Gabriel, Peter Lin, Rik Koncel-Kedziorski, Yejin Choi, Hannaneh HajishirziNAACL • 2019 We introduce a large-scale dataset of math word problems and an interpretable neural math problem solver by learning to map problems to their operation programs. Due to annotation challenges, current datasets in this domain have been either relatively small…The Curious Case of Neural Text Degeneration
Ari Holtzman, Jan Buys, Li Du, Maxwell Forbes, Yejin ChoiICLR • 2019 Despite considerable advances in neural language modeling, it remains an open question what the best decoding strategy is for text generation from a language model (e.g. to generate a story). The counter-intuitive empirical observation is that even though the…Tactical Rewind: Self-Correction via Backtracking in Vision-And-Language Navigation
Liyiming Ke, Xiujun Li, Yonatan Bisk, Ari Holtzman, Zhe Gan, Jingjing Liu, Jianfeng Gao, Yejin Choi, S. SrinivasaCVPR • 2019 We present the Frontier Aware Search with backTracking (FAST) Navigator, a general framework for action decoding, that achieves state-of-the-art results on the 2018 Room-to-Room (R2R) Vision-and-Language navigation challenge. Given a natural language…DREAM: A Challenge Data Set and Models for Dialogue-Based Reading Comprehension
Kai Sun, Dian Yu, Jianshu Chen, Dong Yu, Yejin Choi, Claire CardieTACL • 2019 We present DREAM, the first dialogue-based multiple-choice reading comprehension data set. Collected from English as a Foreign Language examinations designed by human experts to evaluate the comprehension level of Chinese learners of English, our data set…ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning
Maarten Sap, Ronan Le Bras, Emily Allaway, Chandra Bhagavatula, Nicholas Lourie, Hannah Rashkin, Brendan Roof, Noah A. Smith, Yejin ChoiAAAI • 2019 We present ATOMIC, an atlas of everyday commonsense reasoning, organized through 877k textual descriptions of inferential knowledge. Compared to existing resources that center around taxonomic knowledge, ATOMIC focuses on inferential knowledge organized as…EARLY FUSION for Goal Directed Robotic Vision
Aaron Walsman, Yonatan Bisk, Saadia Gabriel, Dipendra Kumar Misra, Yoav Artzi, Yejin Choi, D. FoxIROS • 2018 Building perceptual systems for robotics which perform well under tight computational budgets requires novel architectures which rethink the traditional computer vision pipeline. Modern vision architectures require the agent to build a summary representation…Neural Metaphor Detection in Context
Ge Gao, Eunsol Choi, Yejin Choi and Luke ZettlemoyerEMNLP • 2018 We present end-to-end neural models for detecting metaphorical word use in context. We show that relatively standard BiLSTM models which operate on complete sentences work well in this setting, in comparison to previous work that used more restricted forms of…SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference
Rowan Zellers, Yonatan Bisk, Roy Schwartz, and Yejin ChoiEMNLP • 2018 Given a partial description like"she opened the hood of the car,"humans can reason about the situation and anticipate what might come next ("then, she examined the engine"). In this paper, we introduce the task of grounded commonsense inference, unifying…QuAC: Question Answering in Context
Eunsol Choi, He He, Mohit Iyyer, Mark Yatskar, Wen-tau Yih, Yejin Choi, Percy Liang and Luke ZettlemoyerEMNLP • 2018 We present QuAC, a dataset for Question Answering in Context that contains 14K information-seeking QA dialogs (100K questions in total). The dialogs involve two crowd workers: (1) a student who poses a sequence of freeform questions to learn as much as…