Recurrent and convolutional neural networks comprise two distinct families of models that have proven to be useful for encoding natural language utterances. In this paper we present SoPa, a new model that aims to bridge these two approaches. SoPa combines neural representation learning with weighted finite-state automata (WFSAs) to learn a soft version of traditional surface patterns. We show that SoPa is an extension of a one-layer CNN, and that such CNNs are equivalent to a restricted version of SoPa, and accordingly, to a restricted form of WFSA. Empirically, on three text classification tasks, SoPa is comparable or better than both a BiLSTM (RNN) baseline and a CNN baseline, and is particularly useful in small data settings. Click to Read Paper
We introduce the structured projection of intermediate gradients optimization technique (SPIGOT), a new method for backpropagating through neural networks that include hard-decision structured predictions (e.g., parsing) in intermediate layers. SPIGOT requires no marginal inference, unlike structured attention networks (Kim et al., 2017) and some reinforcement learning-inspired solutions (Yogatama et al., 2017). Like so-called straight-through estimators (Hinton, 2012), SPIGOT defines gradient-like quantities associated with intermediate nondifferentiable operations, allowing backpropagation before and after them; SPIGOT's proxy aims to ensure that, after a parameter update, the intermediate structure will remain well-formed. We experiment on two structured NLP pipelines: syntactic-then-semantic dependency parsing, and semantic parsing followed by sentiment classification. We show that training with SPIGOT leads to a larger improvement on the downstream task than a modularly-trained pipeline, the straight-through estimator, and structured attention, reaching a new state of the art on semantic dependency parsing. Click to Read Paper
We present a deep neural architecture that parses sentences into three semantic dependency graph formalisms. By using efficient, nearly arc-factored inference and a bidirectional-LSTM composed with a multi-layer perceptron, our base system is able to significantly improve the state of the art for semantic dependency parsing, without using hand-engineered features or syntax. We then explore two multitask learning approaches---one that shares parameters across formalisms, and one that uses higher-order structures to predict the graphs jointly. We find that both approaches improve performance across formalisms on average, achieving a new state of the art. Our code is open-source and available at https://github.com/Noahs-ARK/NeurboParser. Click to Read Paper
Despite the tremendous empirical success of neural models in natural language processing, many of them lack the strong intuitions that accompany classical machine learning approaches. Recently, connections have been shown between convolutional neural networks (CNNs) and weighted finite state automata (WFSAs), leading to new interpretations and insights. In this work, we show that some recurrent neural networks also share this connection to WFSAs. We characterize this connection formally, defining rational recurrences to be recurrent hidden state update functions that can be written as the Forward calculation of a finite set of WFSAs. We show that several recent neural models use rational recurrences. Our analysis provides a fresh view of these models and facilitates devising new neural architectures that draw inspiration from WFSAs. We present one such model, which performs better than two recent baselines on language modeling and text classification. Our results demonstrate that transferring intuitions from classical models like WFSAs can be an effective approach to designing and understanding neural models. Click to Read Paper
We present a new approach to learning semantic parsers from multiple datasets, even when the target semantic formalisms are drastically different, and the underlying corpora do not overlap. We handle such "disjoint" data by treating annotations for unobserved formalisms as latent structured variables. Building on state-of-the-art baselines, we show improvements both in frame-semantic parsing and semantic dependency parsing by modeling them jointly. Click to Read Paper
We investigate the problem of producing structured graph representations of visual scenes. Our work analyzes the role of motifs: regularly appearing substructures in scene graphs. We present new quantitative insights on such repeated structures in the Visual Genome dataset. Our analysis shows that object labels are highly predictive of relation labels but not vice-versa. We also find that there are recurring patterns even in larger subgraphs: more than 50% of graphs contain motifs involving at least two relations. Our analysis motivates a new baseline: given object detections, predict the most frequent relation between object pairs with the given labels, as seen in the training set. This baseline improves on the previous state-of-the-art by an average of 3.6% relative improvement across evaluation settings. We then introduce Stacked Motif Networks, a new architecture designed to capture higher order motifs in scene graphs that further improves over our strong baseline by an average 7.1% relative gain. Our code is available at github.com/rowanz/neural-motifs. Click to Read Paper
We present a new, efficient frame-semantic parser that labels semantic arguments to FrameNet predicates. Built using an extension to the segmental RNN that emphasizes recall, our basic system achieves competitive performance without any calls to a syntactic parser. We then introduce a method that uses phrase-syntactic annotations from the Penn Treebank during training only, through a multitask objective; no parsing is required at training or test time. This "syntactic scaffold" offers a cheaper alternative to traditional syntactic pipelining, and achieves state-of-the-art performance. Click to Read Paper
We present a novel abstractive summarization framework that draws on the recent development of a treebank for the Abstract Meaning Representation (AMR). In this framework, the source text is parsed to a set of AMR graphs, the graphs are transformed into a summary graph, and then text is generated from the summary graph. We focus on the graph-to-graph transformation that reduces the source semantic graph into a summary graph, making use of an existing AMR parser and assuming the eventual availability of an AMR-to-text generator. The framework is data-driven, trainable, and not specifically designed for a particular domain. Experiments on gold-standard AMR annotations and system parses show promising results. Code is available at: https://github.com/summarization Click to Read Paper
We introduce the syntactic scaffold, an approach to incorporating syntactic information into semantic tasks. Syntactic scaffolds avoid expensive syntactic processing at runtime, only making use of a treebank during training, through a multitask objective. We improve over strong baselines on PropBank semantics, frame semantics, and coreference resolution, achieving competitive performance on all three tasks. Click to Read Paper
A Deep Neural Network for Pixel-Level Electromagnetic Particle Identification in the MicroBooNE Liquid Argon Time Projection Chamber
Aug 22, 2018
MicroBooNE collaboration, C. Adams, M. Alrashed, R. An, J. Anthony, J. Asaadi, A. Ashkenazi, M. Auger, S. Balasubramanian, B. Baller, C. Barnes, G. Barr, M. Bass, F. Bay, A. Bhat, K. Bhattacharya, M. Bishai, A. Blake, T. Bolton, L. Camilleri, D. Caratelli, I. Caro Terrazas, R. Carr, R. Castillo Fernandez, F. Cavanna, G. Cerati, Y. Chen, E. Church, D. Cianci, E. Cohen, G. H. Collin, J. M. Conrad, M. Convery, L. Cooper-Troendle, J. I. Crespo-Anadon, M. Del Tutto, D. Devitt, A. Diaz, K. Duffy, S. Dytman, B. Eberly, A. Ereditato, L. Escudero Sanchez, J. Esquivel, J. J. Evans, A. A. Fadeeva, R. S. Fitzpatrick, B. T. Fleming, D. Franco, A. P. Furmanski, D. Garcia-Gamez, G. T. Garvey, V. Genty, D. Goeldi, S. Gollapinni, O. Goodwin, E. Gramellini, H. Greenlee, R. Grosso, R. Guenette, P. Guzowski, A. Hackenburg, P. Hamilton, O. Hen, J. Hewes, C. Hill, G. A. Horton-Smith, A. Hourlier, E. -C. Huang, C. James, J. Jan de Vries, L. Jiang, R. A. Johnson, J. Joshi, H. Jostlein, Y. -J. Jwa, G. Karagiorgi, W. Ketchum, B. Kirby, M. Kirby, T. Kobilarcik, I. Kreslo, Y. Li, A. Lister, B. R. Littlejohn, S. Lockwitz, D. Lorca, W. C. Louis, M. Luethi, B. Lundberg, X. Luo, A. Marchionni, S. Marcocci, C. Mariani, J. Marshall, J. Martin-Albo, D. A. Martinez Caicedo, A. Mastbaum, V. Meddage, T. Mettler, G. B. Mills, K. Mistry, A. Mogan, J. Moon, M. Mooney, C. D. Moore, J. Mousseau, M. Murphy, R. Murrells, D. Naples, P. Nienaber, J. Nowak, O. Palamara, V. Pandey, V. Paolone, A. Papadopoulou, V. Papavassiliou, S. F. Pate, Z. Pavlovic, E. Piasetzky, D. Porzio, G. Pulliam, X. Qian, J. L. Raaf, A. Rafique, L. Rochester, M. Ross-Lonergan, C. Rudolf von Rohr, B. Russell, D. W. Schmitz, A. Schukraft, W. Seligman, M. H. Shaevitz, R. Sharankova, J. Sinclair, A. Smith, E. L. Snider, M. Soderberg, S. Soldner-Rembold, S. R. Soleti, P. Spentzouris, J. Spitz, J. St. John, T. Strauss, K. Sutton, S. Sword-Fehlberg, A. M. Szelc, N. Tagg, W. Tang, K. Terao, M. Thomson, R. T. Thornton, M. Toups, Y. -T. Tsai, S. Tufanli, T. Usher, W. Van De Pontseele, R. G. Van de Water, B. Viren, M. Weber, H. Wei, D. A. Wickremasinghe, K. Wierman, Z. Williams, S. Wolbers, T. Wongjirad, K. Woodruff, T. Yang, G. Yarbrough, L. E. Yates, G. P. Zeller, J. Zennamo, C. Zhang

We have developed a convolutional neural network (CNN) that can make a pixel-level prediction of objects in image data recorded by a liquid argon time projection chamber (LArTPC) for the first time. We describe the network design, training techniques, and software tools developed to train this network. The goal of this work is to develop a complete deep neural network based data reconstruction chain for the MicroBooNE detector. We show the first demonstration of a network's validity on real LArTPC data using MicroBooNE collection plane images. The demonstration is performed for stopping muon and a $\nu_\mu$ charged current neutral pion data samples. Click to Read Paper
We consider the stochastic bandit problem with a continuous set of arms, with the expected reward function over the arms assumed to be fixed but unknown. We provide two new Gaussian process-based algorithms for continuous bandit optimization-Improved GP-UCB (IGP-UCB) and GP-Thomson sampling (GP-TS), and derive corresponding regret bounds. Specifically, the bounds hold when the expected reward function belongs to the reproducing kernel Hilbert space (RKHS) that naturally corresponds to a Gaussian process kernel used as input by the algorithms. Along the way, we derive a new self-normalized concentration inequality for vector- valued martingales of arbitrary, possibly infinite, dimension. Finally, experimental evaluation and comparisons to existing algorithms on synthetic and real-world environments are carried out that highlight the favorable gains of the proposed strategies in many cases. Click to Read Paper