February 1, 2020

2824 words 14 mins read

Paper Group AWR 102

Classification and Clustering of Arguments with Contextualized Word Embeddings. The Complexity of Morality: Checking Markov Blanket Consistency with DAGs via Morality. Enriching Pre-trained Language Model with Entity Information for Relation Classification. Mastering the Game of Sungka from Random Play. Subword ELMo. A Skeleton-bridged Deep Learnin …

Classification and Clustering of Arguments with Contextualized Word Embeddings


Title	Classification and Clustering of Arguments with Contextualized Word Embeddings
Authors	Nils Reimers, Benjamin Schiller, Tilman Beck, Johannes Daxenberger, Christian Stab, Iryna Gurevych
Abstract	We experiment with two recent contextualized word embedding methods (ELMo and BERT) in the context of open-domain argument search. For the first time, we show how to leverage the power of contextualized word embeddings to classify and cluster topic-dependent arguments, achieving impressive results on both tasks and across multiple datasets. For argument classification, we improve the state-of-the-art for the UKP Sentential Argument Mining Corpus by 20.8 percentage points and for the IBM Debater - Evidence Sentences dataset by 7.4 percentage points. For the understudied task of argument clustering, we propose a pre-training step which improves by 7.8 percentage points over strong baselines on a novel dataset, and by 12.3 percentage points for the Argument Facet Similarity (AFS) Corpus.
Tasks	Argument Mining, Word Embeddings
Published	2019-06-24
URL	https://arxiv.org/abs/1906.09821v1
PDF	https://arxiv.org/pdf/1906.09821v1.pdf
PWC	https://paperswithcode.com/paper/classification-and-clustering-of-arguments
Repo	https://github.com/UKPLab/acl2019-BERT-argument-classification-and-clustering
Framework	pytorch

The Complexity of Morality: Checking Markov Blanket Consistency with DAGs via Morality


Title	The Complexity of Morality: Checking Markov Blanket Consistency with DAGs via Morality
Authors	Yang Li, Kevin Korb, Lloyd Allison
Abstract	A family of Markov blankets in a faithful Bayesian network satisfies the symmetry and consistency properties. In this paper, we draw a bijection between families of consistent Markov blankets and moral graphs. We define the new concepts of weak recursive simpliciality and perfect elimination kits. We prove that they are equivalent to graph morality. In addition, we prove that morality can be decided in polynomial time for graphs with maximum degree less than $5$, but the problem is NP-complete for graphs with higher maximum degrees.
Tasks
Published	2019-03-05
URL	http://arxiv.org/abs/1903.01707v1
PDF	http://arxiv.org/pdf/1903.01707v1.pdf
PWC	https://paperswithcode.com/paper/the-complexity-of-morality-checking-markov
Repo	https://github.com/kelvinyangli/wrsgraph
Framework	none

Enriching Pre-trained Language Model with Entity Information for Relation Classification


Title	Enriching Pre-trained Language Model with Entity Information for Relation Classification
Authors	Shanchan Wu, Yifan He
Abstract	Relation classification is an important NLP task to extract relations between entities. The state-of-the-art methods for relation classification are primarily based on Convolutional or Recurrent Neural Networks. Recently, the pre-trained BERT model achieves very successful results in many NLP classification / sequence labeling tasks. Relation classification differs from those tasks in that it relies on information of both the sentence and the two target entities. In this paper, we propose a model that both leverages the pre-trained BERT language model and incorporates information from the target entities to tackle the relation classification task. We locate the target entities and transfer the information through the pre-trained architecture and incorporate the corresponding encoding of the two entities. We achieve significant improvement over the state-of-the-art method on the SemEval-2010 task 8 relational dataset.
Tasks	Language Modelling, Relation Classification, Relation Extraction
Published	2019-05-20
URL	https://arxiv.org/abs/1905.08284v1
PDF	https://arxiv.org/pdf/1905.08284v1.pdf
PWC	https://paperswithcode.com/paper/enriching-pre-trained-language-model-with
Repo	https://github.com/monologg/R-BERT
Framework	pytorch

Mastering the Game of Sungka from Random Play


Title	Mastering the Game of Sungka from Random Play
Authors	Darwin Bautista, Raimarc Dionido
Abstract	Recent work in reinforcement learning demonstrated that learning solely through self-play is not only possible, but could also result in novel strategies that humans never would have thought of. However, optimization methods cast as a game between two players require careful tuning to prevent suboptimal results. Hence, we look at random play as an alternative method. In this paper, we train a DQN agent to play Sungka, a two-player turn-based board game wherein the players compete to obtain more stones than the other. We show that even with purely random play, our training algorithm converges very fast and is stable. Moreover, we test our trained agent against several baselines and show its ability to consistently win against these.
Tasks
Published	2019-05-17
URL	https://arxiv.org/abs/1905.07102v1
PDF	https://arxiv.org/pdf/1905.07102v1.pdf
PWC	https://paperswithcode.com/paper/mastering-the-game-of-sungka-from-random-play
Repo	https://github.com/baudm/sungka-ai
Framework	pytorch

Subword ELMo


Title	Subword ELMo
Authors	Jiangtong Li, Hai Zhao, Zuchao Li, Wei Bi, Xiaojiang Liu
Abstract	Embedding from Language Models (ELMo) has shown to be effective for improving many natural language processing (NLP) tasks, and ELMo takes character information to compose word representation to train language models.However, the character is an insufficient and unnatural linguistic unit for word representation.Thus we introduce Embedding from Subword-aware Language Models (ESuLMo) which learns word representation from subwords using unsupervised segmentation over words.We show that ESuLMo can enhance four benchmark NLP tasks more effectively than ELMo, including syntactic dependency parsing, semantic role labeling, implicit discourse relation recognition and textual entailment, which brings a meaningful improvement over ELMo.
Tasks	Dependency Parsing, Natural Language Inference, Semantic Role Labeling
Published	2019-09-18
URL	https://arxiv.org/abs/1909.08357v1
PDF	https://arxiv.org/pdf/1909.08357v1.pdf
PWC	https://paperswithcode.com/paper/subword-elmo
Repo	https://github.com/Jiangtong-Li/Subword-ELMo
Framework	pytorch

A Skeleton-bridged Deep Learning Approach for Generating Meshes of Complex Topologies from Single RGB Images


Title	A Skeleton-bridged Deep Learning Approach for Generating Meshes of Complex Topologies from Single RGB Images
Authors	Jiapeng Tang, Xiaoguang Han, Junyi Pan, Kui Jia, Xin Tong
Abstract	This paper focuses on the challenging task of learning 3D object surface reconstructions from single RGB images. Existing methods achieve varying degrees of success by using different geometric representations. However, they all have their own drawbacks, and cannot well reconstruct those surfaces of complex topologies. To this end, we propose in this paper a skeleton-bridged, stage-wise learning approach to address the challenge. Our use of skeleton is due to its nice property of topology preservation, while being of lower complexity to learn. To learn skeleton from an input image, we design a deep architecture whose decoder is based on a novel design of parallel streams respectively for synthesis of curve- and surface-like skeleton points. We use different shape representations of point cloud, volume, and mesh in our stage-wise learning, in order to take their respective advantages. We also propose multi-stage use of the input image to correct prediction errors that are possibly accumulated in each stage. We conduct intensive experiments to investigate the efficacy of our proposed approach. Qualitative and quantitative results on representative object categories of both simple and complex topologies demonstrate the superiority of our approach over existing ones. We will make our ShapeNet-Skeleton dataset publicly available.
Tasks
Published	2019-03-12
URL	http://arxiv.org/abs/1903.04704v2
PDF	http://arxiv.org/pdf/1903.04704v2.pdf
PWC	https://paperswithcode.com/paper/a-skeleton-bridged-deep-learning-approach-for
Repo	https://github.com/tangjiapeng/SkeletonBridgeRecon
Framework	pytorch

On the Use of ArXiv as a Dataset


Title	On the Use of ArXiv as a Dataset
Authors	Colin B. Clement, Matthew Bierbaum, Kevin P. O’Keeffe, Alexander A. Alemi
Abstract	The arXiv has collected 1.5 million pre-print articles over 28 years, hosting literature from scientific fields including Physics, Mathematics, and Computer Science. Each pre-print features text, figures, authors, citations, categories, and other metadata. These rich, multi-modal features, combined with the natural graph structure—created by citation, affiliation, and co-authorship—makes the arXiv an exciting candidate for benchmarking next-generation models. Here we take the first necessary steps toward this goal, by providing a pipeline which standardizes and simplifies access to the arXiv’s publicly available data. We use this pipeline to extract and analyze a 6.7 million edge citation graph, with an 11 billion word corpus of full-text research articles. We present some baseline classification results, and motivate application of more exciting generative graph models.
Tasks
Published	2019-04-30
URL	http://arxiv.org/abs/1905.00075v1
PDF	http://arxiv.org/pdf/1905.00075v1.pdf
PWC	https://paperswithcode.com/paper/on-the-use-of-arxiv-as-a-dataset
Repo	https://github.com/mattbierbaum/arxiv-public-datasets
Framework	none

Overton: A Data System for Monitoring and Improving Machine-Learned Products


Title	Overton: A Data System for Monitoring and Improving Machine-Learned Products
Authors	Christopher Ré, Feng Niu, Pallavi Gudipati, Charles Srisuwananukorn
Abstract	We describe a system called Overton, whose main design goal is to support engineers in building, monitoring, and improving production machine learning systems. Key challenges engineers face are monitoring fine-grained quality, diagnosing errors in sophisticated applications, and handling contradictory or incomplete supervision data. Overton automates the life cycle of model construction, deployment, and monitoring by providing a set of novel high-level, declarative abstractions. Overton’s vision is to shift developers to these higher-level tasks instead of lower-level machine learning tasks. In fact, using Overton, engineers can build deep-learning-based applications without writing any code in frameworks like TensorFlow. For over a year, Overton has been used in production to support multiple applications in both near-real-time applications and back-of-house processing. In that time, Overton-based applications have answered billions of queries in multiple languages and processed trillions of records reducing errors 1.7-2.9 times versus production systems.
Tasks
Published	2019-09-07
URL	https://arxiv.org/abs/1909.05372v1
PDF	https://arxiv.org/pdf/1909.05372v1.pdf
PWC	https://paperswithcode.com/paper/overton-a-data-system-for-monitoring-and
Repo	https://github.com/DataScienceNigeria/OVERTON-from-Apple
Framework	tf

FCOS: Fully Convolutional One-Stage Object Detection


Title	FCOS: Fully Convolutional One-Stage Object Detection
Authors	Zhi Tian, Chunhua Shen, Hao Chen, Tong He
Abstract	We propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to semantic segmentation. Almost all state-of-the-art object detectors such as RetinaNet, SSD, YOLOv3, and Faster R-CNN rely on pre-defined anchor boxes. In contrast, our proposed detector FCOS is anchor box free, as well as proposal free. By eliminating the predefined set of anchor boxes, FCOS completely avoids the complicated computation related to anchor boxes such as calculating overlapping during training. More importantly, we also avoid all hyper-parameters related to anchor boxes, which are often very sensitive to the final detection performance. With the only post-processing non-maximum suppression (NMS), FCOS with ResNeXt-64x4d-101 achieves 44.7% in AP with single-model and single-scale testing, surpassing previous one-stage detectors with the advantage of being much simpler. For the first time, we demonstrate a much simpler and flexible detection framework achieving improved detection accuracy. We hope that the proposed FCOS framework can serve as a simple and strong alternative for many other instance-level tasks. Code is available at:Code is available at: https://tinyurl.com/FCOSv1
Tasks	Object Detection, Semantic Segmentation
Published	2019-04-02
URL	https://arxiv.org/abs/1904.01355v5
PDF	https://arxiv.org/pdf/1904.01355v5.pdf
PWC	https://paperswithcode.com/paper/fcos-fully-convolutional-one-stage-object
Repo	https://github.com/chencq1234/maskrcnn_facebook
Framework	pytorch

Self Driving RC Car using Behavioral Cloning


Title	Self Driving RC Car using Behavioral Cloning
Authors	Aliasgar Haji, Priyam Shah, Srinivas Bijoor
Abstract	Self Driving Car technology is a vehicle that guides itself without human conduction. The first truly autonomous cars appeared in the 1980s with projects funded by DARPA( Defense Advance Research Project Agency ). Since then a lot has changed with the improvements in the fields of Computer Vision and Machine Learning. We have used the concept of behavioral cloning to convert a normal RC model car into an autonomous car using Deep Learning technology
Tasks
Published	2019-10-10
URL	https://arxiv.org/abs/1910.06734v1
PDF	https://arxiv.org/pdf/1910.06734v1.pdf
PWC	https://paperswithcode.com/paper/self-driving-rc-car-using-behavioral-cloning
Repo	https://github.com/meyerv11045/Self-Driving-RC-Car
Framework	tf


Title	Composite optimization for robust blind deconvolution
Authors	Vasileios Charisopoulos, Damek Davis, Mateo Díaz, Dmitriy Drusvyatskiy
Abstract	The blind deconvolution problem seeks to recover a pair of vectors from a set of rank one bilinear measurements. We consider a natural nonsmooth formulation of the problem and show that under standard statistical assumptions, its moduli of weak convexity, sharpness, and Lipschitz continuity are all dimension independent. This phenomenon persists even when up to half of the measurements are corrupted by noise. Consequently, standard algorithms, such as the subgradient and prox-linear methods, converge at a rapid dimension-independent rate when initialized within constant relative error of the solution. We then complete the paper with a new initialization strategy, complementing the local search algorithms. The initialization procedure is both provably efficient and robust to outlying measurements. Numerical experiments, on both simulated and real data, illustrate the developed theory and methods.
Tasks
Published	2019-01-06
URL	http://arxiv.org/abs/1901.01624v2
PDF	http://arxiv.org/pdf/1901.01624v2.pdf
PWC	https://paperswithcode.com/paper/composite-optimization-for-robust-blind
Repo	https://github.com/COR-OPT/RobustBlindDeconv
Framework	none

An Evaluation Toolkit to Guide Model Selection and Cohort Definition in Causal Inference


Title	An Evaluation Toolkit to Guide Model Selection and Cohort Definition in Causal Inference
Authors	Yishai Shimoni, Ehud Karavani, Sivan Ravid, Peter Bak, Tan Hung Ng, Sharon Hensley Alford, Denise Meade, Yaara Goldschmidt
Abstract	Real world observational data, together with causal inference, allow the estimation of causal effects when randomized controlled trials are not available. To be accepted into practice, such predictive models must be validated for the dataset at hand, and thus require a comprehensive evaluation toolkit, as introduced here. Since effect estimation cannot be evaluated directly, we turn to evaluating the various observable properties of causal inference, namely the observed outcome and treatment assignment. We developed a toolkit that expands established machine learning evaluation methods and adds several causal-specific ones. Evaluations can be applied in cross-validation, in a train-test scheme, or on the training data. Multiple causal inference methods are implemented within the toolkit in a way that allows modular use of the underlying machine learning models. Thus, the toolkit is agnostic to the machine learning model that is used. We showcase our approach using a rheumatoid arthritis cohort (consisting of about 120K patients) extracted from the IBM MarketScan(R) Research Database. We introduce an iterative pipeline of data definition, model definition, and model evaluation. Using this pipeline, we demonstrate how each of the evaluation components helps drive model selection and refinement of data extraction criteria in a way that provides more reproducible results and ensures that the causal question is answerable with available data. Furthermore, we show how the evaluation toolkit can be used to ensure that performance is maintained when applied to subsets of the data, thus allowing exploration of questions that move towards personalized medicine.
Tasks	Causal Inference, Model Selection
Published	2019-06-02
URL	https://arxiv.org/abs/1906.00442v1
PDF	https://arxiv.org/pdf/1906.00442v1.pdf
PWC	https://paperswithcode.com/paper/190600442
Repo	https://github.com/IBM/causallib
Framework	none

WikiDataSets: Standardized sub-graphs from Wikidata


Title	WikiDataSets: Standardized sub-graphs from Wikidata
Authors	Armand Boschin, Thomas Bonald
Abstract	Developing new ideas and algorithms in the fields of graph processing and relational learning requires public datasets. While Wikidata is the largest open source knowledge graph, involving more than fifty million entities, it is larger than needed in many cases and even too large to be processed easily. Still, it is a goldmine of relevant facts and relations. Using this knowledge graph is time consuming and prone to task specific tuning which can affect reproducibility of results. Providing a unified framework to extract topic-specific subgraphs solves this problem and allows researchers to evaluate algorithms on common datasets. This paper presents various topic-specific subgraphs of Wikidata along with the generic Python code used to extract them. These datasets can help develop new methods of knowledge graph processing and relational learning.
Tasks	Relational Reasoning
Published	2019-06-11
URL	https://arxiv.org/abs/1906.04536v3
PDF	https://arxiv.org/pdf/1906.04536v3.pdf
PWC	https://paperswithcode.com/paper/wikidatasets-standardized-sub-graphs-from
Repo	https://github.com/armand33/WikiDataSets
Framework	none

NeuRoRA: Neural Robust Rotation Averaging


Title	NeuRoRA: Neural Robust Rotation Averaging
Authors	Pulak Purkait, Tat-Jun Chin, Ian Reid
Abstract	Multiple rotation averaging is an essential task for structure from motion, mapping, and robot navigation. The task is to estimate the absolute orientations of several cameras given some of their noisy relative orientation measurements. The conventional methods for this task seek parameters of the absolute orientations that agree best with the observed noisy measurements according to a robust cost function. These robust cost functions are highly nonlinear and are designed based on certain assumptions about the noise and outlier distributions. In this work, we aim to build a neural network that learns the noise patterns from the data and predict/regress the model parameters from the noisy relative orientations. The proposed network is a combination of two networks: (1) a view-graph cleaning network, which detects outlier edges in the view-graph and rectifies noisy measurements; and (2) a fine-tuning network, which fine-tunes an initialization of absolute orientations bootstrapped from the cleaned graph, in a single step. The proposed combined network is very fast, moreover, being trained on a large number of synthetic graphs, it is more accurate than the conventional iterative optimization methods. Although the idea of replacing robust optimization methods by a graph-based network is demonstrated only for multiple rotation averaging, it could easily be extended to other graph-based geometric problems, for example, pose-graph optimization.
Tasks	Robot Navigation
Published	2019-12-10
URL	https://arxiv.org/abs/1912.04485v2
PDF	https://arxiv.org/pdf/1912.04485v2.pdf
PWC	https://paperswithcode.com/paper/neurora-neural-robust-rotation-averaging
Repo	https://github.com/pulak09/NeuRoRA
Framework	pytorch

Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation


Title	Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation
Authors	Chenze Shao, Yang Feng, Jinchao Zhang, Fandong Meng, Xilin Chen, Jie Zhou
Abstract	Non-Autoregressive Transformer (NAT) aims to accelerate the Transformer model through discarding the autoregressive mechanism and generating target words independently, which fails to exploit the target sequential information. Over-translation and under-translation errors often occur for the above reason, especially in the long sentence translation scenario. In this paper, we propose two approaches to retrieve the target sequential information for NAT to enhance its translation ability while preserving the fast-decoding property. Firstly, we propose a sequence-level training method based on a novel reinforcement algorithm for NAT (Reinforce-NAT) to reduce the variance and stabilize the training procedure. Secondly, we propose an innovative Transformer decoder named FS-decoder to fuse the target sequential information into the top layer of the decoder. Experimental results on three translation tasks show that the Reinforce-NAT surpasses the baseline NAT system by a significant margin on BLEU without decelerating the decoding speed and the FS-decoder achieves comparable translation performance to the autoregressive Transformer with considerable speedup.
Tasks	Machine Translation
Published	2019-06-22
URL	https://arxiv.org/abs/1906.09444v1
PDF	https://arxiv.org/pdf/1906.09444v1.pdf
PWC	https://paperswithcode.com/paper/retrieving-sequential-information-for-non
Repo	https://github.com/ictnlp/BoN-NAT
Framework	pytorch