January 24, 2020

2024 words 10 mins read

Paper Group NANR 196

RELATIONS - Workshop on meaning relations between phrases and sentences. EnGAN: Latent Space MCMC and Maximum Entropy Generators for Energy-based Models. Applying Machine Translation to Psychology: Automatic Translation of Personality Adjectives. Hungarian translators’ perceptions of Neural Machine Translation in the European Commission. Uralic mul …

RELATIONS - Workshop on meaning relations between phrases and sentences


Title	RELATIONS - Workshop on meaning relations between phrases and sentences
Authors
Abstract
Tasks
Published	2019-05-01
URL	https://www.aclweb.org/anthology/W19-0800/
PDF	https://www.aclweb.org/anthology/W19-0800
PWC	https://paperswithcode.com/paper/relations-workshop-on-meaning-relations
Repo
Framework

EnGAN: Latent Space MCMC and Maximum Entropy Generators for Energy-based Models


Title	EnGAN: Latent Space MCMC and Maximum Entropy Generators for Energy-based Models
Authors	Rithesh Kumar, Anirudh Goyal, Aaron Courville, Yoshua Bengio
Abstract	Unsupervised learning is about capturing dependencies between variables and is driven by the contrast between the probable vs improbable configurations of these variables, often either via a generative model which only samples probable ones or with an energy function (unnormalized log-density) which is low for probable ones and high for improbable ones. Here we consider learning both an energy function and an efficient approximate sampling mechanism for the corresponding distribution. Whereas the critic (or discriminator) in generative adversarial networks (GANs) learns to separate data and generator samples, introducing an entropy maximization regularizer on the generator can turn the interpretation of the critic into an energy function, which separates the training distribution from everything else, and thus can be used for tasks like anomaly or novelty detection. This paper is motivated by the older idea of sampling in latent space rather than data space because running a Monte-Carlo Markov Chain (MCMC) in latent space has been found to be easier and more efficient, and because a GAN-like generator can convert latent space samples to data space samples. For this purpose, we show how a Markov chain can be run in latent space whose samples can be mapped to data space, producing better samples. These samples are also used for the negative phase gradient required to estimate the log-likelihood gradient of the data space energy function. To maximize entropy at the output of the generator, we take advantage of recently introduced neural estimators of mutual information. We find that in addition to producing a useful scoring function for anomaly detection, the resulting approach produces sharp samples (like GANs) while covering the modes well, leading to high Inception and Fréchet scores.
Tasks	Anomaly Detection
Published	2019-05-01
URL	https://openreview.net/forum?id=HJlmhs05tm
PDF	https://openreview.net/pdf?id=HJlmhs05tm
PWC	https://paperswithcode.com/paper/engan-latent-space-mcmc-and-maximum-entropy
Repo
Framework

Applying Machine Translation to Psychology: Automatic Translation of Personality Adjectives


Title	Applying Machine Translation to Psychology: Automatic Translation of Personality Adjectives
Authors	Ritsuko Iwai, Daisuke Kawahara, Takatsune Kumada, Sadao Kurohashi
Abstract
Tasks	Machine Translation
Published	2019-08-01
URL	https://www.aclweb.org/anthology/W19-6704/
PDF	https://www.aclweb.org/anthology/W19-6704
PWC	https://paperswithcode.com/paper/applying-machine-translation-to-psychology
Repo
Framework

Hungarian translators’ perceptions of Neural Machine Translation in the European Commission


Title	Hungarian translators’ perceptions of Neural Machine Translation in the European Commission
Authors	{{'A}gnes Leszny{'a}k}
Abstract
Tasks	Machine Translation
Published	2019-08-01
URL	https://www.aclweb.org/anthology/W19-6703/
PDF	https://www.aclweb.org/anthology/W19-6703
PWC	https://paperswithcode.com/paper/hungarian-translators-perceptions-of-neural
Repo
Framework

Uralic multimedia corpora: ISO/TEI corpus data in the project INEL


Title	Uralic multimedia corpora: ISO/TEI corpus data in the project INEL
Authors	Timofey Arkhangelskiy, Anne Ferger, Hanna Hedeland
Abstract
Tasks
Published	2019-01-01
URL	https://aclanthology.info/papers/W19-0310/w19-0310
PDF	https://www.aclweb.org/anthology/W19-0310
PWC	https://paperswithcode.com/paper/uralic-multimedia-corpora-isotei-corpus-data
Repo
Framework

EUSP: An Easy-to-Use Semantic Parsing PlatForm


Title	EUSP: An Easy-to-Use Semantic Parsing PlatForm
Authors	Bo An, Chen Bo, Xianpei Han, Le Sun
Abstract	Semantic parsing aims to map natural language utterances into structured meaning representations. We present a modular platform, EUSP (Easy-to-Use Semantic Parsing PlatForm), that facilitates developers to build semantic parser from scratch. Instead of requiring a large amount of training data or complex grammar knowledge, in our platform developers can build grammar-based semantic parser or neural-based semantic parser through configure files which specify the modules and components that compose semantic parsing system. A high quality grammar-based semantic parsing system only requires domain lexicons rather than costly training data for a semantic parser. Furthermore, we provide a browser-based method to generate the semantic parsing system to minimize the difficulty of development. Experimental results show that the neural-based semantic parser system achieves competitive performance on semantic parsing task, and grammar-based semantic parsers significantly improve the performance of a business search engine.
Tasks	Semantic Parsing
Published	2019-11-01
URL	https://www.aclweb.org/anthology/D19-3012/
PDF	https://www.aclweb.org/anthology/D19-3012
PWC	https://paperswithcode.com/paper/eusp-an-easy-to-use-semantic-parsing-platform
Repo
Framework

FERMI at SemEval-2019 Task 5: Using Sentence embeddings to Identify Hate Speech Against Immigrants and Women in Twitter


Title	FERMI at SemEval-2019 Task 5: Using Sentence embeddings to Identify Hate Speech Against Immigrants and Women in Twitter
Authors	Vijayasaradhi Indurthi, Bakhtiyar Syed, Manish Shrivastava, Nikhil Chakravartula, Manish Gupta, Vasudeva Varma
Abstract	This paper describes our system (Fermi) for Task 5 of SemEval-2019: HatEval: Multilingual Detection of Hate Speech Against Immigrants and Women on Twitter. We participated in the subtask A for English and ranked first in the evaluation on the test set. We evaluate the quality of multiple sentence embeddings and explore multiple training models to evaluate the performance of simple yet effective embedding-ML combination algorithms. Our team - Fermi{'}s model achieved an accuracy of 65.00{%} for English language in task A. Our models, which use pretrained Universal Encoder sentence embeddings for transforming the input and SVM (with RBF kernel) for classification, scored first position (among 68) in the leaderboard on the test set for Subtask A in English language. In this paper we provide a detailed description of the approach, as well as the results obtained in the task.
Tasks	Sentence Embeddings
Published	2019-06-01
URL	https://www.aclweb.org/anthology/S19-2009/
PDF	https://www.aclweb.org/anthology/S19-2009
PWC	https://paperswithcode.com/paper/fermi-at-semeval-2019-task-5-using-sentence
Repo
Framework

Team Howard Beale at SemEval-2019 Task 4: Hyperpartisan News Detection with BERT


Title	Team Howard Beale at SemEval-2019 Task 4: Hyperpartisan News Detection with BERT
Authors	Osman Mutlu, Ozan Arkan Can, Erenay Dayanik
Abstract	This paper describes our system for SemEval-2019 Task 4: Hyperpartisan News Detection (Kiesel et al., 2019). We use pretrained BERT (Devlin et al., 2018) architecture and investigate the effect of different fine tuning regimes on the final classification task. We show that additional pretraining on news domain improves the performance on the Hyperpartisan News Detection task. Our system ranked 8th out of 42 teams with 78.3{%} accuracy on the held-out test dataset.
Tasks
Published	2019-06-01
URL	https://www.aclweb.org/anthology/S19-2175/
PDF	https://www.aclweb.org/anthology/S19-2175
PWC	https://paperswithcode.com/paper/team-howard-beale-at-semeval-2019-task-4
Repo
Framework

Unsupervised Person Re-Identification by Camera-Aware Similarity Consistency Learning


Title	Unsupervised Person Re-Identification by Camera-Aware Similarity Consistency Learning
Authors	Ancong Wu, Wei-Shi Zheng, Jian-Huang Lai
Abstract	For matching pedestrians across disjoint camera views in surveillance, person re-identification (Re-ID) has made great progress in supervised learning. However, it is infeasible to label data in a number of new scenes when extending a Re-ID system. Thus, studying unsupervised learning for Re-ID is important for saving labelling cost. Yet, cross-camera scene variation is a key challenge for unsupervised Re-ID, such as illumination, background and viewpoint variations, which cause domain shift in the feature space and result in inconsistent pairwise similarity distributions that degrade matching performance. To alleviate the effect of cross-camera scene variation, we propose a Camera-Aware Similarity Consistency Loss to learn consistent pairwise similarity distributions for intra-camera matching and cross-camera matching. To avoid learning ineffective knowledge in consistency learning, we preserve the prior common knowledge of intra-camera matching in the pretrained model as reliable guiding information, which does not suffer from cross-camera scene variation as cross-camera matching. To learn similarity consistency more effectively, we further develop a coarse-to-fine consistency learning scheme to learn consistency globally and locally in two steps. Experiments show that our method outperformed the state-of-the-art unsupervised Re-ID methods.
Tasks	Person Re-Identification, Unsupervised Person Re-Identification
Published	2019-10-01
URL	http://openaccess.thecvf.com/content_ICCV_2019/html/Wu_Unsupervised_Person_Re-Identification_by_Camera-Aware_Similarity_Consistency_Learning_ICCV_2019_paper.html
PDF	http://openaccess.thecvf.com/content_ICCV_2019/papers/Wu_Unsupervised_Person_Re-Identification_by_Camera-Aware_Similarity_Consistency_Learning_ICCV_2019_paper.pdf
PWC	https://paperswithcode.com/paper/unsupervised-person-re-identification-by
Repo
Framework

Depth-Induced Multi-Scale Recurrent Attention Network for Saliency Detection


Title	Depth-Induced Multi-Scale Recurrent Attention Network for Saliency Detection
Authors	Yongri Piao, Wei Ji, Jingjing Li, Miao Zhang, Huchuan Lu
Abstract	In this work, we propose a novel depth-induced multi-scale recurrent attention network for saliency detection. It achieves dramatic performance especially in complex scenarios. There are three main contributions of our network that are experimentally demonstrated to have significant practical merits. First, we design an effective depth refinement block using residual connections to fully extract and fuse multi-level paired complementary cues from RGB and depth streams. Second, depth cues with abundant spatial information are innovatively combined with multi-scale context features for accurately locating salient objects. Third, we boost our model’s performance by a novel recurrent attention module inspired by Internal Generative Mechanism of human brain. This module can generate more accurate saliency results via comprehensively learning the internal semantic relation of the fused feature and progressively optimizing local details with memory-oriented scene understanding. In addition, we create a large scale RGB-D dataset containing more complex scenarios, which can contribute to comprehensively evaluating saliency models. Extensive experiments on six public datasets and ours demonstrate that our method can accurately identify salient objects and achieve consistently superior performance over 16 state-of-the-art RGB and RGB-D approaches.
Tasks	Saliency Detection, Scene Understanding
Published	2019-10-01
URL	http://openaccess.thecvf.com/content_ICCV_2019/html/Piao_Depth-Induced_Multi-Scale_Recurrent_Attention_Network_for_Saliency_Detection_ICCV_2019_paper.html
PDF	http://openaccess.thecvf.com/content_ICCV_2019/papers/Piao_Depth-Induced_Multi-Scale_Recurrent_Attention_Network_for_Saliency_Detection_ICCV_2019_paper.pdf
PWC	https://paperswithcode.com/paper/depth-induced-multi-scale-recurrent-attention
Repo
Framework

Proceedings of the 1st Workshop on Discourse Structure in Neural NLG


Title	Proceedings of the 1st Workshop on Discourse Structure in Neural NLG
Authors
Abstract
Tasks
Published	2019-11-01
URL	https://www.aclweb.org/anthology/W19-8100/
PDF	https://www.aclweb.org/anthology/W19-8100
PWC	https://paperswithcode.com/paper/proceedings-of-the-1st-workshop-on-discourse
Repo
Framework

Modelling word translation entropy and syntactic equivalence with machine learning


Title	Modelling word translation entropy and syntactic equivalence with machine learning
Authors	Bram Vanroy, Orph{'e}e De Clercq, Lieve Macken
Abstract
Tasks
Published	2019-08-01
URL	https://www.aclweb.org/anthology/W19-7002/
PDF	https://www.aclweb.org/anthology/W19-7002
PWC	https://paperswithcode.com/paper/modelling-word-translation-entropy-and
Repo
Framework

Morphological Neural Pre- and Post-Processing for Slavic Languages


Title	Morphological Neural Pre- and Post-Processing for Slavic Languages
Authors	Giorgio Bernardinello
Abstract
Tasks
Published	2019-08-01
URL	https://www.aclweb.org/anthology/W19-6731/
PDF	https://www.aclweb.org/anthology/W19-6731
PWC	https://paperswithcode.com/paper/morphological-neural-pre-and-post-processing
Repo
Framework

Padam: Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks


Title	Padam: Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks
Authors	Jinghui Chen, Quanquan Gu
Abstract	Adaptive gradient methods, which adopt historical gradient information to automatically adjust the learning rate, despite the nice property of fast convergence, have been observed to generalize worse than stochastic gradient descent (SGD) with momentum in training deep neural networks. This leaves how to close the generalization gap of adaptive gradient methods an open problem. In this work, we show that adaptive gradient methods such as Adam, Amsgrad, are sometimes “over adapted”. We design a new algorithm, called Partially adaptive momentum estimation method (Padam), which unifies the Adam/Amsgrad with SGD by introducing a partial adaptive parameter p, to achieve the best from both worlds. Experiments on standard benchmarks show that Padam can maintain fast convergence rate as Adam/Amsgrad while generalizing as well as SGD in training deep neural networks. These results would suggest practitioners pick up adaptive gradient methods once again for faster training of deep neural networks.
Tasks
Published	2019-05-01
URL	https://openreview.net/forum?id=BJll6o09tm
PDF	https://openreview.net/pdf?id=BJll6o09tm
PWC	https://paperswithcode.com/paper/padam-closing-the-generalization-gap-of
Repo
Framework

Neural Graph Evolution: Automatic Robot Design


Title	Neural Graph Evolution: Automatic Robot Design
Authors	Tingwu Wang, Yuhao Zhou, Sanja Fidler, Jimmy Ba
Abstract	Despite the recent successes in robotic locomotion control, the design of robot relies heavily on human engineering. Automatic robot design has been a long studied subject, but the recent progress has been slowed due to the large combinatorial search space and the difficulty in evaluating the found candidates. To address the two challenges, we formulate automatic robot design as a graph search problem and perform evolution search in graph space. We propose Neural Graph Evolution (NGE), which performs selection on current candidates and evolves new ones iteratively. Different from previous approaches, NGE uses graph neural networks to parameterize the control policies, which reduces evaluation cost on new candidates with the help of skill transfer from previously evaluated designs. In addition, NGE applies Graph Mutation with Uncertainty (GM-UC) by incorporating model uncertainty, which reduces the search space by balancing exploration and exploitation. We show that NGE significantly outperforms previous methods by an order of magnitude. As shown in experiments, NGE is the first algorithm that can automatically discover kinematically preferred robotic graph structures, such as a fish with two symmetrical flat side-fins and a tail, or a cheetah with athletic front and back legs. Instead of using thousands of cores for weeks, NGE efficiently solves searching problem within a day on a single 64 CPU-core Amazon EC2 machine.
Tasks
Published	2019-05-01
URL	https://openreview.net/forum?id=BkgWHnR5tm
PDF	https://openreview.net/pdf?id=BkgWHnR5tm
PWC	https://paperswithcode.com/paper/neural-graph-evolution-automatic-robot-design
Repo
Framework