Viewing 21-30 of 35 papers
  • Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation

    Amit Mor-Yosef, Ido Dagan, Yoav GoldbergNAACL2019Data-to-text generation can be conceptually divided into two parts: ordering and structuring the information (planning), and generating fluent language describing the information (realization). Modern neural generation systems conflate these two steps into a single end-to-end differentiable system… more
  • Studying the Inductive Biases of RNNs with Synthetic Variations of Natural Languages

    Shauli Ravfogel, Yoav Goldberg, Tal LinzenNAACL2019How 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 prediction) are complicated by the fact that… more
  • Value-based Search in Execution Space for Mapping Instructions to Programs

    Dor Muhlgay, Jonathan Herzig, Jonathan BerantNAACL2019Training 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 length of the instructions grows… more
  • White-to-Black: Efficient Distillation of Black-Box Adversarial Attacks

    Or Gorodissky, Yoav Chai, Yotam Gil, Jonathan BerantNAACL2019We 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 attack and also that we can perform a black… more
  • Neural network gradient-based learning of black-box function interfaces

    Alon Jacovi, Guy Hadash, Einat Kermany, Boaz Carmeli, Ofer Lavi, George Kour, Jonathan BerantICLR2019Deep 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 manner eliminating the need for training. In… more
  • Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction

    Roei Herzig, Moshiko Raboh, Gal Chechik, Jonathan Berant, Amir GlobersonNeurIPS2018Machine understanding of complex images is a key goal of artificial intelligence. One challenge underlying this task is that visual scenes contain multiple inter-related objects, and that global context plays an important role in interpreting the scene. A natural modeling framework for capturing… more
  • Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing

    Chen Liang, Mohammad Norouzi, Jonathan Berant, Quoc Le, Ni LaoNeurIPS2018This paper presents Memory Augmented Policy Optimization (MAPO): a novel policy optimization formulation that incorporates a memory buffer of promising trajectories to reduce the variance of policy gradient estimates for deterministic environments with discrete actions. The formulation expresses… more
  • Adversarial Removal of Demographic Attributes from Text Data

    Yanai Elazar, Yoav GoldbergEMNLP2018Recent advances in Representation Learning and Adversarial Training seem to succeed in removing unwanted features from the learned representation. We show that demographic information of authors is encoded in—and can be recovered from—the intermediate representations learned by text-based neural… more
  • Can LSTM Learn to Capture Agreement? The Case of Basque

    Shauli Ravfogel, Francis M. Tyers, Yoav GoldbergEMNLP • Workshop: Analyzing and interpreting neural networks for NLP 2018Sequential neural networks models are powerful tools in a variety of Natural Language Processing (NLP) tasks. The sequential nature of these models raises the questions: to what extent can these models implicitly learn hierarchical structures typical to human language, and what kind of grammatical… more
  • Decoupling Structure and Lexicon for Zero-Shot Semantic Parsing

    Jonathan Herzig, Jonathan BerantEMNLP2018Building a semantic parser quickly in a new domain is a fundamental challenge for conversational interfaces, as current semantic parsers require expensive supervision and lack the ability to generalize to new domains. In this paper, we introduce a zero-shot approach to semantic parsing that can… more