Paper Group ANR 715
A Study and Comparison of Human and Deep Learning Recognition Performance Under Visual Distortions. Senti17 at SemEval-2017 Task 4: Ten Convolutional Neural Network Voters for Tweet Polarity Classification. Rule-Based Spanish Morphological Analyzer Built From Spell Checking Lexicon. CLaC at SemEval-2016 Task 11: Exploring linguistic and psycho-ling …
A Study and Comparison of Human and Deep Learning Recognition Performance Under Visual Distortions
| Title | A Study and Comparison of Human and Deep Learning Recognition Performance Under Visual Distortions |
| Authors | Samuel Dodge, Lina Karam |
| Abstract | Deep neural networks (DNNs) achieve excellent performance on standard classification tasks. However, under image quality distortions such as blur and noise, classification accuracy becomes poor. In this work, we compare the performance of DNNs with human subjects on distorted images. We show that, although DNNs perform better than or on par with humans on good quality images, DNN performance is still much lower than human performance on distorted images. We additionally find that there is little correlation in errors between DNNs and human subjects. This could be an indication that the internal representation of images are different between DNNs and the human visual system. These comparisons with human performance could be used to guide future development of more robust DNNs. |
| Tasks | |
| Published | 2017-05-06 |
| URL | http://arxiv.org/abs/1705.02498v1 |
| http://arxiv.org/pdf/1705.02498v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-study-and-comparison-of-human-and-deep |
| Repo | |
| Framework | |
Senti17 at SemEval-2017 Task 4: Ten Convolutional Neural Network Voters for Tweet Polarity Classification
| Title | Senti17 at SemEval-2017 Task 4: Ten Convolutional Neural Network Voters for Tweet Polarity Classification |
| Authors | Hussam Hamdan |
| Abstract | This paper presents Senti17 system which uses ten convolutional neural networks (ConvNet) to assign a sentiment label to a tweet. The network consists of a convolutional layer followed by a fully-connected layer and a Softmax on top. Ten instances of this network are initialized with the same word embeddings as inputs but with different initializations for the network weights. We combine the results of all instances by selecting the sentiment label given by the majority of the ten voters. This system is ranked fourth in SemEval-2017 Task4 over 38 systems with 67.4% |
| Tasks | Word Embeddings |
| Published | 2017-05-04 |
| URL | http://arxiv.org/abs/1705.02023v1 |
| http://arxiv.org/pdf/1705.02023v1.pdf | |
| PWC | https://paperswithcode.com/paper/senti17-at-semeval-2017-task-4-ten |
| Repo | |
| Framework | |
Rule-Based Spanish Morphological Analyzer Built From Spell Checking Lexicon
| Title | Rule-Based Spanish Morphological Analyzer Built From Spell Checking Lexicon |
| Authors | Natalie Ahn |
| Abstract | Preprocessing tools for automated text analysis have become more widely available in major languages, but non-English tools are often still limited in their functionality. When working with Spanish-language text, researchers can easily find tools for tokenization and stemming, but may not have the means to extract more complex word features like verb tense or mood. Yet Spanish is a morphologically rich language in which such features are often identifiable from word form. Conjugation rules are consistent, but many special verbs and nouns take on different rules. While building a complete dictionary of known words and their morphological rules would be labor intensive, resources to do so already exist, in spell checkers designed to generate valid forms of known words. This paper introduces a set of tools for Spanish-language morphological analysis, built using the COES spell checking tools, to label person, mood, tense, gender and number, derive a word’s root noun or verb infinitive, and convert verbs to their nominal form. |
| Tasks | Morphological Analysis, Tokenization |
| Published | 2017-07-23 |
| URL | http://arxiv.org/abs/1707.07331v1 |
| http://arxiv.org/pdf/1707.07331v1.pdf | |
| PWC | https://paperswithcode.com/paper/rule-based-spanish-morphological-analyzer |
| Repo | |
| Framework | |
CLaC at SemEval-2016 Task 11: Exploring linguistic and psycho-linguistic Features for Complex Word Identification
| Title | CLaC at SemEval-2016 Task 11: Exploring linguistic and psycho-linguistic Features for Complex Word Identification |
| Authors | Elnaz Davoodi, Leila Kosseim |
| Abstract | This paper describes the system deployed by the CLaC-EDLK team to the “SemEval 2016, Complex Word Identification task”. The goal of the task is to identify if a given word in a given context is “simple” or “complex”. Our system relies on linguistic features and cognitive complexity. We used several supervised models, however the Random Forest model outperformed the others. Overall our best configuration achieved a G-score of 68.8% in the task, ranking our system 21 out of 45. |
| Tasks | Complex Word Identification |
| Published | 2017-09-08 |
| URL | http://arxiv.org/abs/1709.02843v1 |
| http://arxiv.org/pdf/1709.02843v1.pdf | |
| PWC | https://paperswithcode.com/paper/clac-at-semeval-2016-task-11-exploring |
| Repo | |
| Framework | |
Morphological Embeddings for Named Entity Recognition in Morphologically Rich Languages
| Title | Morphological Embeddings for Named Entity Recognition in Morphologically Rich Languages |
| Authors | Onur Gungor, Eray Yildiz, Suzan Uskudarli, Tunga Gungor |
| Abstract | In this work, we present new state-of-the-art results of 93.59,% and 79.59,% for Turkish and Czech named entity recognition based on the model of (Lample et al., 2016). We contribute by proposing several schemes for representing the morphological analysis of a word in the context of named entity recognition. We show that a concatenation of this representation with the word and character embeddings improves the performance. The effect of these representation schemes on the tagging performance is also investigated. |
| Tasks | Morphological Analysis, Named Entity Recognition |
| Published | 2017-06-01 |
| URL | http://arxiv.org/abs/1706.00506v1 |
| http://arxiv.org/pdf/1706.00506v1.pdf | |
| PWC | https://paperswithcode.com/paper/morphological-embeddings-for-named-entity |
| Repo | |
| Framework | |
Effective Approaches to Batch Parallelization for Dynamic Neural Network Architectures
| Title | Effective Approaches to Batch Parallelization for Dynamic Neural Network Architectures |
| Authors | Joseph Suarez, Clare Zhu |
| Abstract | We present a simple dynamic batching approach applicable to a large class of dynamic architectures that consistently yields speedups of over 10x. We provide performance bounds when the architecture is not known a priori and a stronger bound in the special case where the architecture is a predetermined balanced tree. We evaluate our approach on Johnson et al.‘s recent visual question answering (VQA) result of his CLEVR dataset by Inferring and Executing Programs (IEP). We also evaluate on sparsely gated mixture of experts layers and achieve speedups of up to 1000x over the naive implementation. |
| Tasks | Question Answering, Visual Question Answering |
| Published | 2017-07-08 |
| URL | http://arxiv.org/abs/1707.02402v1 |
| http://arxiv.org/pdf/1707.02402v1.pdf | |
| PWC | https://paperswithcode.com/paper/effective-approaches-to-batch-parallelization |
| Repo | |
| Framework | |
Projective reconstruction in algebraic vision
| Title | Projective reconstruction in algebraic vision |
| Authors | Atsushi Ito, Makoto Miura, Kazushi Ueda |
| Abstract | We discuss the geometry of rational maps from a projective space of an arbitrary dimension to the product of projective spaces of lower dimensions induced by linear projections. In particular, we give an algebro-geometric variant of the projective reconstruction theorem by Hartley and Schaffalitzky [HS09]. |
| Tasks | |
| Published | 2017-10-17 |
| URL | https://arxiv.org/abs/1710.06205v3 |
| https://arxiv.org/pdf/1710.06205v3.pdf | |
| PWC | https://paperswithcode.com/paper/projective-reconstruction-in-algebraic-vision |
| Repo | |
| Framework | |
Named Entity Sequence Classification
| Title | Named Entity Sequence Classification |
| Authors | Mahdi Namazifar |
| Abstract | Named Entity Recognition (NER) aims at locating and classifying named entities in text. In some use cases of NER, including cases where detected named entities are used in creating content recommendations, it is crucial to have a reliable confidence level for the detected named entities. In this work we study the problem of finding confidence levels for detected named entities. We refer to this problem as Named Entity Sequence Classification (NESC). We frame NESC as a binary classification problem and we use NER as well as recurrent neural networks to find the probability of candidate named entity is a real named entity. We apply this approach to Tweet texts and we show how we could find named entities with high confidence levels from Tweets. |
| Tasks | Named Entity Recognition |
| Published | 2017-12-06 |
| URL | http://arxiv.org/abs/1712.02316v1 |
| http://arxiv.org/pdf/1712.02316v1.pdf | |
| PWC | https://paperswithcode.com/paper/named-entity-sequence-classification |
| Repo | |
| Framework | |
Self-Regulating Artificial General Intelligence
| Title | Self-Regulating Artificial General Intelligence |
| Authors | Joshua S. Gans |
| Abstract | Here we examine the paperclip apocalypse concern for artificial general intelligence (or AGI) whereby a superintelligent AI with a simple goal (ie., producing paperclips) accumulates power so that all resources are devoted towards that simple goal and are unavailable for any other use. We provide conditions under which a paper apocalypse can arise but also show that, under certain architectures for recursive self-improvement of AIs, that a paperclip AI may refrain from allowing power capabilities to be developed. The reason is that such developments pose the same control problem for the AI as they do for humans (over AIs) and hence, threaten to deprive it of resources for its primary goal. |
| Tasks | |
| Published | 2017-11-12 |
| URL | http://arxiv.org/abs/1711.04309v2 |
| http://arxiv.org/pdf/1711.04309v2.pdf | |
| PWC | https://paperswithcode.com/paper/self-regulating-artificial-general |
| Repo | |
| Framework | |
Scalable Demand-Aware Recommendation
| Title | Scalable Demand-Aware Recommendation |
| Authors | Jinfeng Yi, Cho-Jui Hsieh, Kush Varshney, Lijun Zhang, Yao Li |
| Abstract | Recommendation for e-commerce with a mix of durable and nondurable goods has characteristics that distinguish it from the well-studied media recommendation problem. The demand for items is a combined effect of form utility and time utility, i.e., a product must both be intrinsically appealing to a consumer and the time must be right for purchase. In particular for durable goods, time utility is a function of inter-purchase duration within product category because consumers are unlikely to purchase two items in the same category in close temporal succession. Moreover, purchase data, in contrast to ratings data, is implicit with non-purchases not necessarily indicating dislike. Together, these issues give rise to the positive-unlabeled demand-aware recommendation problem that we pose via joint low-rank tensor completion and product category inter-purchase duration vector estimation. We further relax this problem and propose a highly scalable alternating minimization approach with which we can solve problems with millions of users and millions of items in a single thread. We also show superior prediction accuracies on multiple real-world data sets. |
| Tasks | |
| Published | 2017-02-21 |
| URL | http://arxiv.org/abs/1702.06347v3 |
| http://arxiv.org/pdf/1702.06347v3.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-demand-aware-recommendation |
| Repo | |
| Framework | |
A Classification-Based Study of Covariate Shift in GAN Distributions
| Title | A Classification-Based Study of Covariate Shift in GAN Distributions |
| Authors | Shibani Santurkar, Ludwig Schmidt, Aleksander Mądry |
| Abstract | A basic, and still largely unanswered, question in the context of Generative Adversarial Networks (GANs) is whether they are truly able to capture all the fundamental characteristics of the distributions they are trained on. In particular, evaluating the diversity of GAN distributions is challenging and existing methods provide only a partial understanding of this issue. In this paper, we develop quantitative and scalable tools for assessing the diversity of GAN distributions. Specifically, we take a classification-based perspective and view loss of diversity as a form of covariate shift introduced by GANs. We examine two specific forms of such shift: mode collapse and boundary distortion. In contrast to prior work, our methods need only minimal human supervision and can be readily applied to state-of-the-art GANs on large, canonical datasets. Examining popular GANs using our tools indicates that these GANs have significant problems in reproducing the more distributional properties of their training dataset. |
| Tasks | |
| Published | 2017-11-02 |
| URL | http://arxiv.org/abs/1711.00970v7 |
| http://arxiv.org/pdf/1711.00970v7.pdf | |
| PWC | https://paperswithcode.com/paper/a-classification-based-study-of-covariate |
| Repo | |
| Framework | |
Cross-lingual Abstract Meaning Representation Parsing
| Title | Cross-lingual Abstract Meaning Representation Parsing |
| Authors | Marco Damonte, Shay B. Cohen |
| Abstract | Abstract Meaning Representation (AMR) annotation efforts have mostly focused on English. In order to train parsers on other languages, we propose a method based on annotation projection, which involves exploiting annotations in a source language and a parallel corpus of the source language and a target language. Using English as the source language, we show promising results for Italian, Spanish, German and Chinese as target languages. Besides evaluating the target parsers on non-gold datasets, we further propose an evaluation method that exploits the English gold annotations and does not require access to gold annotations for the target languages. This is achieved by inverting the projection process: a new English parser is learned from the target language parser and evaluated on the existing English gold standard. |
| Tasks | |
| Published | 2017-04-14 |
| URL | http://arxiv.org/abs/1704.04539v2 |
| http://arxiv.org/pdf/1704.04539v2.pdf | |
| PWC | https://paperswithcode.com/paper/cross-lingual-abstract-meaning-representation |
| Repo | |
| Framework | |
StackInsights: Cognitive Learning for Hybrid Cloud Readiness
| Title | StackInsights: Cognitive Learning for Hybrid Cloud Readiness |
| Authors | Mu Qiao, Luis Bathen, Simon-Pierre Génot, Sunhwan Lee, Ramani Routray |
| Abstract | Hybrid cloud is an integrated cloud computing environment utilizing a mix of public cloud, private cloud, and on-premise traditional IT infrastructures. Workload awareness, defined as a detailed full range understanding of each individual workload, is essential in implementing the hybrid cloud. While it is critical to perform an accurate analysis to determine which workloads are appropriate for on-premise deployment versus which workloads can be migrated to a cloud off-premise, the assessment is mainly performed by rule or policy based approaches. In this paper, we introduce StackInsights, a novel cognitive system to automatically analyze and predict the cloud readiness of workloads for an enterprise. Our system harnesses the critical metrics across the entire stack: 1) infrastructure metrics, 2) data relevance metrics, and 3) application taxonomy, to identify workloads that have characteristics of a) low sensitivity with respect to business security, criticality and compliance, and b) low response time requirements and access patterns. Since the capture of the data relevance metrics involves an intrusive and in-depth scanning of the content of storage objects, a machine learning model is applied to perform the business relevance classification by learning from the meta level metrics harnessed across stack. In contrast to traditional methods, StackInsights significantly reduces the total time for hybrid cloud readiness assessment by orders of magnitude. |
| Tasks | |
| Published | 2017-12-16 |
| URL | http://arxiv.org/abs/1712.06015v1 |
| http://arxiv.org/pdf/1712.06015v1.pdf | |
| PWC | https://paperswithcode.com/paper/stackinsights-cognitive-learning-for-hybrid |
| Repo | |
| Framework | |
Learning Active Learning from Data
| Title | Learning Active Learning from Data |
| Authors | Ksenia Konyushkova, Raphael Sznitman, Pascal Fua |
| Abstract | In this paper, we suggest a novel data-driven approach to active learning (AL). The key idea is to train a regressor that predicts the expected error reduction for a candidate sample in a particular learning state. By formulating the query selection procedure as a regression problem we are not restricted to working with existing AL heuristics; instead, we learn strategies based on experience from previous AL outcomes. We show that a strategy can be learnt either from simple synthetic 2D datasets or from a subset of domain-specific data. Our method yields strategies that work well on real data from a wide range of domains. |
| Tasks | Active Learning |
| Published | 2017-03-09 |
| URL | http://arxiv.org/abs/1703.03365v3 |
| http://arxiv.org/pdf/1703.03365v3.pdf | |
| PWC | https://paperswithcode.com/paper/learning-active-learning-from-data |
| Repo | |
| Framework | |
Neon2: Finding Local Minima via First-Order Oracles
| Title | Neon2: Finding Local Minima via First-Order Oracles |
| Authors | Zeyuan Allen-Zhu, Yuanzhi Li |
| Abstract | We propose a reduction for non-convex optimization that can (1) turn an stationary-point finding algorithm into an local-minimum finding one, and (2) replace the Hessian-vector product computations with only gradient computations. It works both in the stochastic and the deterministic settings, without hurting the algorithm’s performance. As applications, our reduction turns Natasha2 into a first-order method without hurting its performance. It also converts SGD, GD, SCSG, and SVRG into algorithms finding approximate local minima, outperforming some best known results. |
| Tasks | |
| Published | 2017-11-17 |
| URL | http://arxiv.org/abs/1711.06673v3 |
| http://arxiv.org/pdf/1711.06673v3.pdf | |
| PWC | https://paperswithcode.com/paper/neon2-finding-local-minima-via-first-order |
| Repo | |
| Framework | |
