Paper Group NAWR 27
Preparing SNACS for Subjects and Objects. Differentiable Cloth Simulation for Inverse Problems. Compositional Plan Vectors. Knowledgeable Storyteller: A Commonsense-Driven Generative Model for Visual Storytelling. Icebreaker: Element-wise Efficient Information Acquisition with a Bayesian Deep Latent Gaussian Model. Rhetorically Controlled Encoder-D …
Preparing SNACS for Subjects and Objects
| Title | Preparing SNACS for Subjects and Objects |
| Authors | Adi Shalev, Jena D. Hwang, Nathan Schneider, Vivek Srikumar, Omri Abend, Ari Rappoport |
| Abstract | Research on adpositions and possessives in multiple languages has led to a small inventory of general-purpose meaning classes that disambiguate tokens. Importantly, that work has argued for a principled separation of the semantic role in a scene from the function coded by morphosyntax. Here, we ask whether this approach can be generalized beyond adpositions and possessives to cover all scene participants{—}including subjects and objects{—}directly, without reference to a frame lexicon. We present new guidelines for English and the results of an interannotator agreement study. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3316/ |
| https://www.aclweb.org/anthology/W19-3316 | |
| PWC | https://paperswithcode.com/paper/preparing-snacs-for-subjects-and-objects |
| Repo | https://github.com/adishalev/SNACS_DMR_IAA |
| Framework | none |
Differentiable Cloth Simulation for Inverse Problems
| Title | Differentiable Cloth Simulation for Inverse Problems |
| Authors | Junbang Liang, Ming Lin, Vladlen Koltun |
| Abstract | We propose a differentiable cloth simulator that can be embedded as a layer in deep neural networks. This approach provides an effective, robust framework for modeling cloth dynamics, self-collisions, and contacts. Due to the high dimensionality of the dynamical system in modeling cloth, traditional gradient computation for collision response can become impractical. To address this problem, we propose to compute the gradient directly using QR decomposition of a much smaller matrix. Experimental results indicate that our method can speed up backpropagation by two orders of magnitude. We demonstrate the presented approach on a number of inverse problems, including parameter estimation and motion control for cloth. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8365-differentiable-cloth-simulation-for-inverse-problems |
| http://papers.nips.cc/paper/8365-differentiable-cloth-simulation-for-inverse-problems.pdf | |
| PWC | https://paperswithcode.com/paper/differentiable-cloth-simulation-for-inverse |
| Repo | https://github.com/williamljb/DifferentiableCloth |
| Framework | pytorch |
Compositional Plan Vectors
| Title | Compositional Plan Vectors |
| Authors | Coline Devin, Daniel Geng, Pieter Abbeel, Trevor Darrell, Sergey Levine |
| Abstract | Autonomous agents situated in real-world environments must be able to master large repertoires of skills. While a single short skill can be learned quickly, it would be impractical to learn every task independently. Instead, the agent should share knowledge across behaviors such that each task can be learned efficiently, and such that the resulting model can generalize to new tasks, especially ones that are compositions or subsets of tasks seen previously. A policy conditioned on a goal or demonstration has the potential to share knowledge between tasks if it sees enough diversity of inputs. However, these methods may not generalize to a more complex task at test time. We introduce compositional plan vectors (CPVs) to enable a policy to perform compositions of tasks without additional supervision. CPVs represent trajectories as the sum of the subtasks within them. We show that CPVs can be learned within a one-shot imitation learning framework without any additional supervision or information about task hierarchy, and enable a demonstration-conditioned policy to generalize to tasks that sequence twice as many skills as the tasks seen during training. Analogously to embeddings such as word2vec in NLP, CPVs can also support simple arithmetic operations – for example, we can add the CPVs for two different tasks to command an agent to compose both tasks, without any additional training. |
| Tasks | Imitation Learning |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9636-compositional-plan-vectors |
| http://papers.nips.cc/paper/9636-compositional-plan-vectors.pdf | |
| PWC | https://paperswithcode.com/paper/compositional-plan-vectors |
| Repo | https://github.com/cdevin/cpv |
| Framework | pytorch |
Knowledgeable Storyteller: A Commonsense-Driven Generative Model for Visual Storytelling
| Title | Knowledgeable Storyteller: A Commonsense-Driven Generative Model for Visual Storytelling |
| Authors | Pengcheng Yang, Fuli Luo, Peng Chen, Lei Li, Zhiyi Yin, Xiaodong He, Xu Sun |
| Abstract | The visual storytelling (VST) task aims at generating a reasonable and coherent paragraph-level story with the image stream as input. Different from caption that is a direct and literal description of image content, the story in the VST task tends to contain plenty of imaginary concepts that do not appear in the image. This requires the AI agent to reason and associate with the imaginary concepts based on implicit commonsense knowledge to generate a reasonable story describing the image stream. Therefore, in this work, we present a commonsensedriven generative model, which aims to introduce crucial commonsense from the external knowledge base for visual storytelling. Our approach first extracts a set of candidate knowledge graphs from the knowledge base. Then, an elaborately designed vision-aware directional encoding schema is adopted to effectively integrate the most informative commonsense. Besides, we strive to maximize the semantic similarity within the output during decoding to enhance the coherence of the generated text. Results show that our approach can outperform the state-of-the-art systems by a large margin, which achieves a 29% relative improvement of CIDEr score. With additional commonsense and semantic-relevance based objective, the generated stories are more diverse and coherent. |
| Tasks | Knowledge Graphs, Semantic Similarity, Semantic Textual Similarity, Text Generation, Visual Storytelling |
| Published | 2019-05-04 |
| URL | https://www.ijcai.org/proceedings/2019/744 |
| https://www.ijcai.org/proceedings/2019/0744.pdf | |
| PWC | https://paperswithcode.com/paper/knowledgeable-storyteller-a-commonsense |
| Repo | https://github.com/lancopku/CVST |
| Framework | none |
Icebreaker: Element-wise Efficient Information Acquisition with a Bayesian Deep Latent Gaussian Model
| Title | Icebreaker: Element-wise Efficient Information Acquisition with a Bayesian Deep Latent Gaussian Model |
| Authors | Wenbo Gong, Sebastian Tschiatschek, Sebastian Nowozin, Richard E. Turner, José Miguel Hernández-Lobato, Cheng Zhang |
| Abstract | In this paper, we address the ice-start problem, i.e., the challenge of deploying machine learning models when only a little or no training data is initially available, and acquiring each feature element of data is associated with costs. This setting is representative of the real-world machine learning applications. For instance, in the health care domain, obtaining every single measurement comes with a cost. We propose Icebreaker, a principled framework for elementwise training data acquisition. Icebreaker introduces a full Bayesian Deep Latent Gaussian Model (BELGAM) with a novel inference method, which combines recent advances in amortized inference and stochastic gradient MCMC to enable fast and accurate posterior inference. By utilizing BELGAM’s ability to fully quantify model uncertainty, we also propose two information acquisition functions for imputation and active prediction problems. We demonstrate that BELGAM performs significantly better than previous variational autoencoder (VAE) based models, when the data set size is small, using both machine learning benchmarks and real world recommender systems and health-care applications. Moreover, Icebreaker not only demonstrates improved performance compared to baselines, but it is also capable of achieving better test performance with less training data available. |
| Tasks | Imputation, Recommendation Systems |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9621-icebreaker-element-wise-efficient-information-acquisition-with-a-bayesian-deep-latent-gaussian-model |
| http://papers.nips.cc/paper/9621-icebreaker-element-wise-efficient-information-acquisition-with-a-bayesian-deep-latent-gaussian-model.pdf | |
| PWC | https://paperswithcode.com/paper/icebreaker-element-wise-efficient-information |
| Repo | https://github.com/microsoft/Icebreaker |
| Framework | pytorch |
Rhetorically Controlled Encoder-Decoder for Modern Chinese Poetry Generation
| Title | Rhetorically Controlled Encoder-Decoder for Modern Chinese Poetry Generation |
| Authors | Zhiqiang Liu, Zuohui Fu, Jie Cao, Gerard de Melo, Yik-Cheung Tam, Cheng Niu, Jie Zhou |
| Abstract | Rhetoric is a vital element in modern poetry, and plays an essential role in improving its aesthetics. However, to date, it has not been considered in research on automatic poetry generation. In this paper, we propose a rhetorically controlled encoder-decoder for modern Chinese poetry generation. Our model relies on a continuous latent variable as a rhetoric controller to capture various rhetorical patterns in an encoder, and then incorporates rhetoric-based mixtures while generating modern Chinese poetry. For metaphor and personification, an automated evaluation shows that our model outperforms state-of-the-art baselines by a substantial margin, while human evaluation shows that our model generates better poems than baseline methods in terms of fluency, coherence, meaningfulness, and rhetorical aesthetics. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1192/ |
| https://www.aclweb.org/anthology/P19-1192 | |
| PWC | https://paperswithcode.com/paper/rhetorically-controlled-encoder-decoder-for |
| Repo | https://github.com/Lucien-qiang/Rhetoric-Generator |
| Framework | tf |
Bias Analysis and Mitigation in the Evaluation of Authorship Verification
| Title | Bias Analysis and Mitigation in the Evaluation of Authorship Verification |
| Authors | Janek Bevendorff, Matthias Hagen, Benno Stein, Martin Potthast |
| Abstract | The PAN series of shared tasks is well known for its continuous and high quality research in the field of digital text forensics. Among others, PAN contributions include original corpora, tailored benchmarks, and standardized experimentation platforms. In this paper we review, theoretically and practically, the authorship verification task and conclude that the underlying experiment design cannot guarantee pushing forward the state of the art{—}in fact, it allows for top benchmarking with a surprisingly straightforward approach. In this regard, we present a {``}Basic and Fairly Flawed{''} (BAFF) authorship verifier that is on a par with the best approaches submitted so far, and that illustrates sources of bias that should be eliminated. We pinpoint these sources in the evaluation chain and present a refined authorship corpus as effective countermeasure. | |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1634/ |
| https://www.aclweb.org/anthology/P19-1634 | |
| PWC | https://paperswithcode.com/paper/bias-analysis-and-mitigation-in-the |
| Repo | https://github.com/webis-de/acl-19 |
| Framework | none |
Multivariate Triangular Quantile Maps for Novelty Detection
| Title | Multivariate Triangular Quantile Maps for Novelty Detection |
| Authors | Jingjing Wang, Sun Sun, Yaoliang Yu |
| Abstract | Novelty detection, a fundamental task in machine learning, has drawn a lot of recent attention due to its wide-ranging applications and the rise of neural approaches. In this work, we present a general framework for neural novelty detection that centers around a multivariate extension of the univariate quantile function. Our framework unifies and extends many classical and recent novelty detection algorithms, and opens the way to exploit recent advances in flow-based neural density estimation. We adapt the multiple gradient descent algorithm to obtain the first efficient end-to-end implementation of our framework that is free of tuning hyperparameters. Extensive experiments over a number of real datasets confirm the efficacy of our proposed method against state-of-the-art alternatives. |
| Tasks | Density Estimation |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8750-multivariate-triangular-quantile-maps-for-novelty-detection |
| http://papers.nips.cc/paper/8750-multivariate-triangular-quantile-maps-for-novelty-detection.pdf | |
| PWC | https://paperswithcode.com/paper/multivariate-triangular-quantile-maps-for |
| Repo | https://github.com/GinGinWang/MTQ |
| Framework | pytorch |
Eidos, INDRA, & Delphi: From Free Text to Executable Causal Models
| Title | Eidos, INDRA, & Delphi: From Free Text to Executable Causal Models |
| Authors | Rebecca Sharp, Adarsh Pyarelal, Benjamin Gyori, Keith Alcock, Egoitz Laparra, Marco A. Valenzuela-Esc{'a}rcega, Ajay Nagesh, Vikas Yadav, John Bachman, Zheng Tang, Heather Lent, Fan Luo, Mithun Paul, Steven Bethard, Kobus Barnard, Clayton Morrison, Mihai Surdeanu |
| Abstract | Building causal models of complicated phenomena such as food insecurity is currently a slow and labor-intensive manual process. In this paper, we introduce an approach that builds executable probabilistic models from raw, free text. The proposed approach is implemented through three systems: Eidos, INDRA, and Delphi. Eidos is an open-domain machine reading system designed to extract causal relations from natural language. It is rule-based, allowing for rapid domain transfer, customizability, and interpretability. INDRA aggregates multiple sources of causal information and performs assembly to create a coherent knowledge base and assess its reliability. This assembled knowledge serves as the starting point for modeling. Delphi is a modeling framework that assembles quantified causal fragments and their contexts into executable probabilistic models that respect the semantics of the original text, and can be used to support decision making. |
| Tasks | Decision Making, Reading Comprehension |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-4008/ |
| https://www.aclweb.org/anthology/N19-4008 | |
| PWC | https://paperswithcode.com/paper/eidos-indra-delphi-from-free-text-to |
| Repo | https://github.com/ml4ai/delphi |
| Framework | none |
Low-Complexity Nonparametric Bayesian Online Prediction with Universal Guarantees
| Title | Low-Complexity Nonparametric Bayesian Online Prediction with Universal Guarantees |
| Authors | Alix Lheritier, Frederic Cazals |
| Abstract | We propose a novel nonparametric online predictor for discrete labels conditioned on multivariate continuous features. The predictor is based on a feature space discretization induced by a full-fledged k-d tree with randomly picked directions and a recursive Bayesian distribution, which allows to automatically learn the most relevant feature scales characterizing the conditional distribution. We prove its pointwise universality, i.e., it achieves a normalized log loss performance asymptotically as good as the true conditional entropy of the labels given the features. The time complexity to process the n-th sample point is O(log n) in probability with respect to the distribution generating the data points, whereas other exact nonparametric methods require to process all past observations. Experiments on challenging datasets show the computational and statistical efficiency of our algorithm in comparison to standard and state-of-the-art methods. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9600-low-complexity-nonparametric-bayesian-online-prediction-with-universal-guarantees |
| http://papers.nips.cc/paper/9600-low-complexity-nonparametric-bayesian-online-prediction-with-universal-guarantees.pdf | |
| PWC | https://paperswithcode.com/paper/low-complexity-nonparametric-bayesian-online |
| Repo | https://github.com/alherit/kd-switch |
| Framework | pytorch |
The Point Where Reality Meets Fantasy: Mixed Adversarial Generators for Image Splice Detection
| Title | The Point Where Reality Meets Fantasy: Mixed Adversarial Generators for Image Splice Detection |
| Authors | Vladimir V. Kniaz, Vladimir Knyaz, Fabio Remondino |
| Abstract | Modern photo editing tools allow creating realistic manipulated images easily. While fake images can be quickly generated, learning models for their detection is challenging due to the high variety of tampering artifacts and the lack of large labeled datasets of manipulated images. In this paper, we propose a new framework for training of discriminative segmentation model via an adversarial process. We simultaneously train four models: a generative retouching model G_R that translates manipulated image to the real image domain, a generative annotation model G_A that estimates the pixel-wise probability of image patch being either real or fake, and two discriminators D_R and D_A that qualify the output of G_R and G_A. The aim of model G_R is to maximize the probability of model G_A making a mistake. Our method extends the generative adversarial networks framework with two main contributions: (1) training of a generative model G_R against a deep semantic segmentation network G_A that learns rich scene semantics for manipulated region detection, (2) proposing per class semantic loss that facilitates semantically consistent image retouching by the G_R. We collected large-scale manipulated image dataset to train our model. The dataset includes 16k real and fake images with pixel-level annotations of manipulated areas. The dataset also provides ground truth pixel-level object annotations. We validate our approach on several modern manipulated image datasets, where quantitative results and ablations demonstrate that our method achieves and surpasses the state-of-the-art in manipulated image detection. We made our code and dataset publicly available. |
| Tasks | Semantic Segmentation |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8315-the-point-where-reality-meets-fantasy-mixed-adversarial-generators-for-image-splice-detection |
| http://papers.nips.cc/paper/8315-the-point-where-reality-meets-fantasy-mixed-adversarial-generators-for-image-splice-detection.pdf | |
| PWC | https://paperswithcode.com/paper/the-point-where-reality-meets-fantasy-mixed |
| Repo | https://github.com/vlkniaz/MAGritte |
| Framework | pytorch |
#YouToo? Detection of Personal Recollections of Sexual Harassment on Social Media
| Title | #YouToo? Detection of Personal Recollections of Sexual Harassment on Social Media |
| Authors | Arijit Ghosh Chowdhury, Ramit Sawhney, Rajiv Ratn Shah, Debanjan Mahata |
| Abstract | The availability of large-scale online social data, coupled with computational methods can help us answer fundamental questions relat- ing to our social lives, particularly our health and well-being. The {#}MeToo trend has led to people talking about personal experiences of harassment more openly. This work at- tempts to aggregate such experiences of sex- ual abuse to facilitate a better understanding of social media constructs and to bring about social change. It has been found that disclo- sure of abuse has positive psychological im- pacts. Hence, we contend that such informa- tion can leveraged to create better campaigns for social change by analyzing how users react to these stories and to obtain a better insight into the consequences of sexual abuse. We use a three part Twitter-Specific Social Media Lan- guage Model to segregate personal recollec- tions of sexual harassment from Twitter posts. An extensive comparison with state-of-the-art generic and specific models along with a de- tailed error analysis explores the merit of our proposed model. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1241/ |
| https://www.aclweb.org/anthology/P19-1241 | |
| PWC | https://paperswithcode.com/paper/youtoo-detection-of-personal-recollections-of |
| Repo | https://github.com/arijit1410/ACL2019-YouToo |
| Framework | none |
Attribution-Based Confidence Metric For Deep Neural Networks
| Title | Attribution-Based Confidence Metric For Deep Neural Networks |
| Authors | Susmit Jha, Sunny Raj, Steven Fernandes, Sumit K. Jha, Somesh Jha, Brian Jalaian, Gunjan Verma, Ananthram Swami |
| Abstract | We propose a novel confidence metric, namely, attribution-based confidence (ABC) for deep neural networks (DNNs). ABC metric characterizes whether the output of a DNN on an input can be trusted. DNNs are known to be brittle on inputs outside the training distribution and are, hence, susceptible to adversarial attacks. This fragility is compounded by a lack of effectively computable measures of model confidence that correlate well with the accuracy of DNNs. These factors have impeded the adoption of DNNs in high-assurance systems. The proposed ABC metric addresses these challenges. It does not require access to the training data, the use of ensembles, or the need to train a calibration model on a held-out validation set. Hence, the new metric is usable even when only a trained model is available for inference. We mathematically motivate the proposed metric and evaluate its effectiveness with two sets of experiments. First, we study the change in accuracy and the associated confidence over out-of-distribution inputs. Second, we consider several digital and physically realizable attacks such as FGSM, CW, DeepFool, PGD, and adversarial patch generation methods. The ABC metric is low on out-of-distribution data and adversarial examples, where the accuracy of the model is also low. These experiments demonstrate the effectiveness of the ABC metric to make DNNs more trustworthy and resilient. |
| Tasks | Calibration |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9355-attribution-based-confidence-metric-for-deep-neural-networks |
| http://papers.nips.cc/paper/9355-attribution-based-confidence-metric-for-deep-neural-networks.pdf | |
| PWC | https://paperswithcode.com/paper/attribution-based-confidence-metric-for-deep |
| Repo | https://github.com/en/articles |
| Framework | none |
sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
| Title | sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning |
| Authors | Chmiela, S., Sauceda, H. E., Poltavsky, I., Müller, K.-R., Tkatchenko, A. |
| Abstract | We present an optimized implementation of the recently proposed symmetric gradient domain machine learning (sGDML) model. The sGDML model is able to faithfully reproduce global potential energy surfaces (PES) for molecules with a few dozen atoms from a limited number of user-provided reference molecular conformations and the associated atomic forces. Here, we introduce a Python software package to reconstruct and evaluate custom sGDML force fields (FFs), without requiring in-depth knowledge about the details of the model. A user-friendly command-line interface offers assistance through the complete process of model creation, in an effort to make this novel machine learning approach accessible to broad practitioners. Our paper serves as a documentation, but also includes a practical application example of how to reconstruct and use a PBE0+MBD FF for paracetamol. Finally, we show how to interface sGDML with the FF simulation engines ASE (Larsen et al., 2017) and i-PI (Kapil et al., 2019) to run numerical experiments, including structure optimization, classical and path integral molecular dynamics and nudged elastic band calculations. |
| Tasks | MD17 dataset |
| Published | 2019-07-01 |
| URL | https://www.sciencedirect.com/science/article/pii/S0010465519300591?via%3Dihub |
| https://www.sciencedirect.com/science/article/pii/S0010465519300591/pdfft?md5=53f2b9d0c500af23f128af5339f5cc04&pid=1-s2.0-S0010465519300591-main.pdf | |
| PWC | https://paperswithcode.com/paper/sgdml-constructing-accurate-and-data-1 |
| Repo | https://github.com/stefanch/sGDML |
| Framework | pytorch |
Expanding functional protein sequence space using generative adversarial networks
| Title | Expanding functional protein sequence space using generative adversarial networks |
| Authors | Donatas Repecka, Vykintas Jauniskis, Laurynas Karpus, Elzbieta Rembeza, Jan Zrimec, SimonaPoviloniene, Irmantas Rokaitis, Audrius Laurynenas, Wissam Abuajwa, Otto Savolainen, RolandasMeskys, Martin K. M. Engqvist, Aleksej Zelezniak |
| Abstract | De novo protein design for catalysis of any desired chemical reaction is a long standing goal in proteinengineering, due to the broad spectrum of technological, scientific and medical applications. Currently,mapping protein sequence to protein function is, however, neither computationionally nor experimentally tangible1,2. Here we developed ProteinGAN, a specialised variant of the generative adversarial network3that is able to ‘learn’ natural protein sequence diversity and enables the generation of functional proteinsequences. ProteinGAN learns the evolutionary relationships of protein sequences directly from thecomplex multidimensional amino acid sequence space and creates new, highly diverse sequence variantswith natural-like physical properties. Using malate dehydrogenase as a template enzyme, we show that24% of the ProteinGAN-generated and experimentally tested sequences are soluble and display wild-typelevel catalytic activity in the tested conditionsin vitro, even in highly mutated (>100 mutations) sequences.ProteinGAN therefore demonstrates the potential of artificial intelligence to rapidly generate highly diversenovel functional proteins within the allowed biological constraints of the sequence space. |
| Tasks | |
| Published | 2019-10-02 |
| URL | https://www.biorxiv.org/content/10.1101/789719v1.abstract |
| https://www.biorxiv.org/content/biorxiv/early/2019/10/04/789719.full.pdf | |
| PWC | https://paperswithcode.com/paper/expanding-functional-protein-sequence-space |
| Repo | https://github.com/biomatterdesigns/ProteinGAN |
| Framework | tf |
