Papers

Learn more about AI2's Lasting Impact Award
All Projects
All Years
Viewing 351-360 of 553 papers
  • Studying the Inductive Biases of RNNs with Synthetic Variations of Natural Languages

    Shauli Ravfogel, Yoav Goldberg, Tal LinzenNAACL2019 How do typological properties such as word order and morphological case marking affect the ability of neural sequence models to acquire the syntax of a language? Cross-linguistic comparisons of RNNs' syntactic performance (e.g., on subject-verb agreement… more
  • Text Generation from Knowledge Graphs with Graph Transformers

    Rik Koncel-Kedziorski, Dhanush Bekal, Yi Luan, Mirella Lapata, Hannaneh HajishirziNAACL2019 Generating texts which express complex ideas spanning multiple sentences requires a structured representation of their content (document plan), but these representations are prohibitively expensive to manually produce. In this work, we address the problem of… more
  • Value-based Search in Execution Space for Mapping Instructions to Programs

    Dor Muhlgay, Jonathan Herzig, Jonathan BerantNAACL2019 Training models to map natural language instructions to programs given target world supervision only requires searching for good programs at training time. Search is commonly done using beam search in the space of partial programs or program trees, but as the… more
  • White-to-Black: Efficient Distillation of Black-Box Adversarial Attacks

    Or Gorodissky, Yoav Chai, Yotam Gil, Jonathan BerantNAACL2019 We show that a neural network can learn to imitate the optimization process performed by white-box attack in a much more efficient manner. We train a black-box attack through this imitation process and show our attack is 19x-39x faster than the white-box… more
  • Defending Against Neural Fake News

    Rowan Zellers, Ari Holtzman, Hannah Rashkin, Yonatan Bisk, Ali Farhadi, Franziska Roesner, Yejin ChoiarXiv2019 Recent progress in natural language generation has raised dual-use concerns. While applications like summarization and translation are positive, the underlying technology also might enable adversaries to generate neural fake news: targeted propaganda that… more
  • FlowQA: Grasping Flow in History for Conversational Machine Comprehension

    Hsin-Yuan Huang, Eunsol Choi, Wen-tau YihICLR2019 Conversational machine comprehension requires a deep understanding of the conversation history. To enable traditional, single-turn models to encode the history comprehensively, we introduce Flow, a mechanism that can incorporate intermediate representations… more
  • Neural network gradient-based learning of black-box function interfaces

    Alon Jacovi, Guy Hadash, Einat Kermany, Boaz Carmeli, Ofer Lavi, George Kour, Jonathan BerantICLR2019 Deep neural networks work well at approximating complicated functions when provided with data and trained by gradient descent methods. At the same time, there is a vast amount of existing functions that programmatically solve different tasks in a precise… more
  • Visual Semantic Navigation using Scene Priors

    Wei Yang, Xiaolong Wang, Ali Farhadi, Abhinav Gupta, Roozbeh MottaghiICLR2019 How do humans navigate to target objects in novel scenes? Do we use the semantic/functional priors we have built over years to efficiently search and navigate? For example, to search for mugs, we search cabinets near the coffee machine and for fruits we try… more
  • The Curious Case of Neural Text Degeneration

    Ari Holtzman, Jan Buys, Li Du, Maxwell Forbes, Yejin ChoiICLR2019 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… more
  • ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning

    Maarten Sap, Ronan LeBras, Emily Allaway, Chandra Bhagavatula, Nicholas Lourie, Hannah Rashkin, Brendan Roof, Noah A. Smith, Yejin ChoiAAAI2019 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… more
All Projects
All Years