Paper Group NAWR 6
Generative Adversarial Network with Spatial Attention for Face Attribute Editing. From Text to Lexicon: Bridging the Gap between Word Embeddings and Lexical Resources. How SGD Selects the Global Minima in Over-parameterized Learning: A Dynamical Stability Perspective. SEDANSPOT: Detecting Anomalies in Edge Streams. Efficient adaptive non-maximal su …
Generative Adversarial Network with Spatial Attention for Face Attribute Editing
| Title | Generative Adversarial Network with Spatial Attention for Face Attribute Editing |
| Authors | Gang Zhang, Meina Kan, Shiguang Shan, Xilin Chen |
| Abstract | Face attribute editing aims at editing the face image with the given attribute. Most existing works employ Generative Adversarial Network (GAN) to operate face attribute editing. However, these methods inevitably change the attribute-irrelevant regions, as shown in Fig.~ ef{fig1}. Therefore, we introduce the spatial attention mechanism into GAN framework (referred to as SaGAN), to only alter the attribute-specific region and keep the rest unchanged. Our approach SaGAN consists of a generator and a discriminator. The generator contains an attribute manipulation network (AMN) to edit the face image, and a spatial attention network (SAN) to localize the attribute-specific region which restricts the alternation of AMN within this region. The discriminator endeavors to distinguish the generated images from the real ones, and classify the face attribute. Experiments demonstrate that our approach can achieve promising visual results, and keep those attribute-irrelevant regions unchanged. Besides, our approach can benefit the face recognition by data augmentation. |
| Tasks | Data Augmentation, Face Recognition |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Gang_Zhang_Generative_Adversarial_Network_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Gang_Zhang_Generative_Adversarial_Network_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/generative-adversarial-network-with-spatial |
| Repo | https://github.com/elvisyjlin/SpatialAttentionGAN |
| Framework | pytorch |
From Text to Lexicon: Bridging the Gap between Word Embeddings and Lexical Resources
| Title | From Text to Lexicon: Bridging the Gap between Word Embeddings and Lexical Resources |
| Authors | Ilia Kuznetsov, Iryna Gurevych |
| Abstract | Distributional word representations (often referred to as word embeddings) are omnipresent in modern NLP. Early work has focused on building representations for word types, and recent studies show that lemmatization and part of speech (POS) disambiguation of targets in isolation improve the performance of word embeddings on a range of downstream tasks. However, the reasons behind these improvements, the qualitative effects of these operations and the combined performance of lemmatized and POS disambiguated targets are less studied. This work aims to close this gap and puts previous findings into a general perspective. We examine the effect of lemmatization and POS typing on word embedding performance in a novel resource-based evaluation scenario, as well as on standard similarity benchmarks. We show that these two operations have complimentary qualitative and vocabulary-level effects and are best used in combination. We find that the improvement is more pronounced for verbs and show how lemmatization and POS typing implicitly target some of the verb-specific issues. We claim that the observed improvement is a result of better conceptual alignment between word embeddings and lexical resources, stressing the need for conceptually plausible modeling of word embedding targets. |
| Tasks | Coreference Resolution, Lemmatization, Word Embeddings |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1020/ |
| https://www.aclweb.org/anthology/C18-1020 | |
| PWC | https://paperswithcode.com/paper/from-text-to-lexicon-bridging-the-gap-between |
| Repo | https://github.com/UKPLab/coling2018-wcs |
| Framework | none |
How SGD Selects the Global Minima in Over-parameterized Learning: A Dynamical Stability Perspective
| Title | How SGD Selects the Global Minima in Over-parameterized Learning: A Dynamical Stability Perspective |
| Authors | Lei Wu, Chao Ma, Weinan E |
| Abstract | The question of which global minima are accessible by a stochastic gradient decent (SGD) algorithm with specific learning rate and batch size is studied from the perspective of dynamical stability. The concept of non-uniformity is introduced, which, together with sharpness, characterizes the stability property of a global minimum and hence the accessibility of a particular SGD algorithm to that global minimum. In particular, this analysis shows that learning rate and batch size play different roles in minima selection. Extensive empirical results seem to correlate well with the theoretical findings and provide further support to these claims. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8049-how-sgd-selects-the-global-minima-in-over-parameterized-learning-a-dynamical-stability-perspective |
| http://papers.nips.cc/paper/8049-how-sgd-selects-the-global-minima-in-over-parameterized-learning-a-dynamical-stability-perspective.pdf | |
| PWC | https://paperswithcode.com/paper/how-sgd-selects-the-global-minima-in-over |
| Repo | https://github.com/leiwu1990/sgd.stability |
| Framework | pytorch |
SEDANSPOT: Detecting Anomalies in Edge Streams
| Title | SEDANSPOT: Detecting Anomalies in Edge Streams |
| Authors | Dhivya Eswaran, Christos Faloutsos |
| Abstract | Given a stream of edges from a time-evolving (un)weighted (un)directed graph, we consider the problem of detecting anomalous edges in near real-time using sublinear memory. We propose SEDANSPOT, a principled randomized algorithm, which exploits two tell-tale signs of anomalous edges: they tend to (i) occur as bursts of activity and (ii) connect parts of the graph which are sparsely connected. SEDANSPOT has the following desirable properties: (a) Burst resistance: It provably downsamples edges from bursty periods of network traffic, (b) Holistic scoring: It takes into account the whole (sampled) graph while scoring the anomalousness of an edge, giving diminishing importance to far-away neighbors, (c) Efficiency: It supports fast updates and scoring and hence can be efficiently maintained over stream; further, it can detect anomalous edges in sublinear space and constant time per edge. Through experiments on real-world data, we demonstrate that SEDANSPOT is 3× faster and 270% more accurate (in terms of AUC) than the state-of-the-art. |
| Tasks | Anomaly Detection in Edge Streams |
| Published | 2018-11-20 |
| URL | https://www.cs.cmu.edu/~deswaran/papers/icdm18-sedanspot.pdf |
| https://www.cs.cmu.edu/~deswaran/papers/icdm18-sedanspot.pdf | |
| PWC | https://paperswithcode.com/paper/sedanspot-detecting-anomalies-in-edge-streams |
| Repo | https://github.com/dhivyaeswaran/sedanspot |
| Framework | none |
Efficient adaptive non-maximal suppression algorithms for homogeneous spatial keypoint distribution
| Title | Efficient adaptive non-maximal suppression algorithms for homogeneous spatial keypoint distribution |
| Authors | Oleksandr Bailo, Francois Rameau, Kyungdon Joo, Jinsun Park, Oleksandr Bogdan, In So Kweon |
| Abstract | Keypoint detection usually results in a large number of keypoints which are mostly clustered, redundant, and noisy. These keypoints often require special processing like Adaptive Non-Maximal Suppression (ANMS) to retain the most relevant ones. In this paper, we present three new efficient ANMS approaches which ensure a fast and homogeneous repartition of the keypoints in the image. For this purpose, a square approximation of the search range to suppress irrelevant points is proposed to reduce the computational complexity of the ANMS. To further speed up the proposed approaches, we also introduce a novel strategy to initialize the search range based on image dimension which leads to a faster convergence. An exhaustive survey and comparisons with already existing methods are provided to highlight the effectiveness and scalability of our methods and the initialization strategy. |
| Tasks | Keypoint Detection |
| Published | 2018-04-15 |
| URL | https://bit.ly/2lSb9Yv |
| https://bit.ly/2mgjULT | |
| PWC | https://paperswithcode.com/paper/efficient-adaptive-non-maximal-suppression |
| Repo | https://github.com/BAILOOL/ANMS-Codes |
| Framework | none |
KRAUTS: A German Temporally Annotated News Corpus
| Title | KRAUTS: A German Temporally Annotated News Corpus |
| Authors | Jannik Str{"o}tgen, Anne-Lyse Minard, Lukas Lange, Manuela Speranza, Bernardo Magnini |
| Abstract | |
| Tasks | Information Retrieval, Question Answering |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1085/ |
| https://www.aclweb.org/anthology/L18-1085 | |
| PWC | https://paperswithcode.com/paper/krauts-a-german-temporally-annotated-news |
| Repo | https://github.com/JannikStroetgen/KRAUTS |
| Framework | none |
OpenKE: An Open Toolkit for Knowledge Embedding
| Title | OpenKE: An Open Toolkit for Knowledge Embedding |
| Authors | Xu Han, Shulin Cao, Xin Lv, Yankai Lin, Zhiyuan Liu, Maosong Sun, Juanzi Li |
| Abstract | We release an open toolkit for knowledge embedding (OpenKE), which provides a unified framework and various fundamental models to embed knowledge graphs into a continuous low-dimensional space. OpenKE prioritizes operational efficiency to support quick model validation and large-scale knowledge representation learning. Meanwhile, OpenKE maintains sufficient modularity and extensibility to easily incorporate new models into the framework. Besides the toolkit, the embeddings of some existing large-scale knowledge graphs pre-trained by OpenKE are also available, which can be directly applied for many applications including information retrieval, personalized recommendation and question answering. The toolkit, documentation, and pre-trained embeddings are all released on \url{http://openke.thunlp.org/}. |
| Tasks | Information Retrieval, Knowledge Graphs, Question Answering, Representation Learning |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/D18-2024/ |
| https://www.aclweb.org/anthology/D18-2024 | |
| PWC | https://paperswithcode.com/paper/openke-an-open-toolkit-for-knowledge |
| Repo | https://github.com/thunlp/OpenKE |
| Framework | tf |
Distinguishing affixoid formations from compounds
| Title | Distinguishing affixoid formations from compounds |
| Authors | Josef Ruppenhofer, Michael Wiegand, Rebecca Wilm, Katja Markert |
| Abstract | |
| Tasks | Sentiment Analysis |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/papers/C18-1325/c18-1325 |
| https://www.aclweb.org/anthology/C18-1325 | |
| PWC | https://paperswithcode.com/paper/distinguishing-affixoid-formations-from |
| Repo | https://github.com/josefkr/affixoids |
| Framework | none |
Farewell Freebase: Migrating the SimpleQuestions Dataset to DBpedia
| Title | Farewell Freebase: Migrating the SimpleQuestions Dataset to DBpedia |
| Authors | Michael Azmy, Peng Shi, Jimmy Lin, Ihab Ilyas |
| Abstract | Question answering over knowledge graphs is an important problem of interest both commercially and academically. There is substantial interest in the class of natural language questions that can be answered via the lookup of a single fact, driven by the availability of the popular SimpleQuestions dataset. The problem with this dataset, however, is that answer triples are provided from Freebase, which has been defunct for several years. As a result, it is difficult to build {``}real-world{''} question answering systems that are operationally deployable. Furthermore, a defunct knowledge graph means that much of the infrastructure for querying, browsing, and manipulating triples no longer exists. To address this problem, we present SimpleDBpediaQA, a new benchmark dataset for simple question answering over knowledge graphs that was created by mapping SimpleQuestions entities and predicates from Freebase to DBpedia. Although this mapping is conceptually straightforward, there are a number of nuances that make the task non-trivial, owing to the different conceptual organizations of the two knowledge graphs. To lay the foundation for future research using this dataset, we leverage recent work to provide simple yet strong baselines with and without neural networks. | |
| Tasks | Knowledge Graphs, Question Answering, Transfer Learning |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1178/ |
| https://www.aclweb.org/anthology/C18-1178 | |
| PWC | https://paperswithcode.com/paper/farewell-freebase-migrating-the |
| Repo | https://github.com/castorini/SimpleDBpediaQA |
| Framework | none |
Novelty Goes Deep. A Deep Neural Solution To Document Level Novelty Detection
| Title | Novelty Goes Deep. A Deep Neural Solution To Document Level Novelty Detection |
| Authors | Tirthankar Ghosal, Vignesh Edithal, Asif Ekbal, Pushpak Bhattacharyya, George Tsatsaronis, Srinivasa Satya Sameer Kumar Chivukula |
| Abstract | The rapid growth of documents across the web has necessitated finding means of discarding redundant documents and retaining novel ones. Capturing redundancy is challenging as it may involve investigating at a deep semantic level. Techniques for detecting such semantic redundancy at the document level are scarce. In this work we propose a deep Convolutional Neural Networks (CNN) based model to classify a document as novel or redundant with respect to a set of relevant documents already seen by the system. The system is simple and do not require any manual feature engineering. Our novel scheme encodes relevant and relative information from both source and target texts to generate an intermediate representation which we coin as the Relative Document Vector (RDV). The proposed method outperforms the existing state-of-the-art on a document-level novelty detection dataset by a margin of ∼5{%} in terms of accuracy. We further demonstrate the effectiveness of our approach on a standard paraphrase detection dataset where paraphrased passages closely resemble to semantically redundant documents. |
| Tasks | Document Summarization, Feature Engineering, Information Retrieval |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1237/ |
| https://www.aclweb.org/anthology/C18-1237 | |
| PWC | https://paperswithcode.com/paper/novelty-goes-deep-a-deep-neural-solution-to |
| Repo | https://github.com/edithal-14/A-Deep-Neural-Solution-To-Document-Level-Novelty-Detection-COLING-2018- |
| Framework | tf |
Structural Causal Bandits: Where to Intervene?
| Title | Structural Causal Bandits: Where to Intervene? |
| Authors | Sanghack Lee, Elias Bareinboim |
| Abstract | We study the problem of identifying the best action in a sequential decision-making setting when the reward distributions of the arms exhibit a non-trivial dependence structure, which is governed by the underlying causal model of the domain where the agent is deployed. In this setting, playing an arm corresponds to intervening on a set of variables and setting them to specific values. In this paper, we show that whenever the underlying causal model is not taken into account during the decision-making process, the standard strategies of simultaneously intervening on all variables or on all the subsets of the variables may, in general, lead to suboptimal policies, regardless of the number of interventions performed by the agent in the environment. We formally acknowledge this phenomenon and investigate structural properties implied by the underlying causal model, which lead to a complete characterization of the relationships between the arms’ distributions. We leverage this characterization to build a new algorithm that takes as input a causal structure and finds a minimal, sound, and complete set of qualified arms that an agent should play to maximize its expected reward. We empirically demonstrate that the new strategy learns an optimal policy and leads to orders of magnitude faster convergence rates when compared with its causal-insensitive counterparts. |
| Tasks | Decision Making |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7523-structural-causal-bandits-where-to-intervene |
| http://papers.nips.cc/paper/7523-structural-causal-bandits-where-to-intervene.pdf | |
| PWC | https://paperswithcode.com/paper/structural-causal-bandits-where-to-intervene |
| Repo | https://github.com/sanghack81/SCMMAB-NIPS2018 |
| Framework | none |
Spectral Illumination Correction: Achieving Relative Color Constancy Under the Spectral Domain
| Title | Spectral Illumination Correction: Achieving Relative Color Constancy Under the Spectral Domain |
| Authors | Yunfeng Zhao, Huiyu Zhou, Chris Elliott, Karen Rafferty |
| Abstract | Achieving color constancy between and within images, i.e., minimizing the color difference between the same object imaged under nonuniform and varied illuminations is crucial for computer vision tasks such as colorimetric analysis and object recognition. Most current methods attempt to solve this by illumination correction on perceptual color spaces. In this paper, we proposed two pixel-wise algorithms to achieve relative color constancy by working under the spectral domain. That is, the proposed algorithms map each pixel to the reflectance ratio of objects appeared in the scene and perform illumination correction in this spectral domain. Also, we proposed a camera calibration technique that calculates the characteristics of a camera without the need of a standard reference. We show that both of the proposed algorithms achieved the best performance on nonuniform illumination correction and relative illumination matching respectively compared to the benchmarked algorithms. |
| Tasks | Calibration, Color Constancy, Object Recognition |
| Published | 2018-12-06 |
| URL | https://ieeexplore.ieee.org/document/8642637 |
| https://pureadmin.qub.ac.uk/ws/portalfiles/portal/163783181/sic_converted.pdf | |
| PWC | https://paperswithcode.com/paper/spectral-illumination-correction-achieving |
| Repo | https://github.com/zyfccc/Spectral-Illumination-Correction-Achieving-Relative-Color-Constancy-Under-the-Spectral-Domain |
| Framework | tf |
Inherent Biases in Reference-based Evaluation for Grammatical Error Correction
| Title | Inherent Biases in Reference-based Evaluation for Grammatical Error Correction |
| Authors | Leshem Choshen, Omri Abend |
| Abstract | The prevalent use of too few references for evaluating text-to-text generation is known to bias estimates of their quality (henceforth, low coverage bias or LCB). This paper shows that overcoming LCB in Grammatical Error Correction (GEC) evaluation cannot be attained by re-scaling or by increasing the number of references in any feasible range, contrary to previous suggestions. This is due to the long-tailed distribution of valid corrections for a sentence. Concretely, we show that LCB incentivizes GEC systems to avoid correcting even when they can generate a valid correction. Consequently, existing systems obtain comparable or superior performance compared to humans, by making few but targeted changes to the input. Similar effects on Text Simplification further support our claims. |
| Tasks | Grammatical Error Correction, Text Generation, Text Simplification |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1059/ |
| https://www.aclweb.org/anthology/P18-1059 | |
| PWC | https://paperswithcode.com/paper/inherent-biases-in-reference-based-evaluation-1 |
| Repo | https://github.com/borgr/IBGEC |
| Framework | none |
Opposite neighborhood: a new method to select reference points of minimal learning machines
| Title | Opposite neighborhood: a new method to select reference points of minimal learning machines |
| Authors | Madson Luiz Dantas Dias, Lucas Silva De Sousa, Ajalmar Rêgo da Rocha Neto, Amauri H. de Souza Júnior |
| Abstract | This paper introduces a new approach to select reference points in minimal learning machines (MLMs) for classification tasks. The MLM training procedure comprises the selection of a subset of the data, named reference points (RPs), that is used to build a linear regression model between distances taken in the input and output spaces. In this matter, we propose a strategy, named opposite neighborhood (ON), to tackle the problem of selecting RPs by locating RPs out of class-overlapping regions. Experiments were carried out using UCI data sets. As a result, the proposal is able to both produce sparser models and achieve competitive performance when compared to the regular MLM. |
| Tasks | |
| Published | 2018-03-22 |
| URL | https://link.springer.com/chapter/10.1007%2F978-3-319-95312-0_34 |
| https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2018-198.pdf | |
| PWC | https://paperswithcode.com/paper/opposite-neighborhood-a-new-method-to-select |
| Repo | https://github.com/omadson/scikit-mlm |
| Framework | none |
EmotiKLUE at IEST 2018: Topic-Informed Classification of Implicit Emotions
| Title | EmotiKLUE at IEST 2018: Topic-Informed Classification of Implicit Emotions |
| Authors | Thomas Proisl, Philipp Heinrich, Besim Kabashi, Stefan Evert |
| Abstract | EmotiKLUE is a submission to the Implicit Emotion Shared Task. It is a deep learning system that combines independent representations of the left and right contexts of the emotion word with the topic distribution of an LDA topic model. EmotiKLUE achieves a macro average \textit{F₁}score of 67.13{%}, significantly outperforming the baseline produced by a simple ML classifier. Further enhancements after the evaluation period lead to an improved \textit{F₁}score of 68.10{%}. |
| Tasks | Opinion Mining |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6234/ |
| https://www.aclweb.org/anthology/W18-6234 | |
| PWC | https://paperswithcode.com/paper/emotiklue-at-iest-2018-topic-informed |
| Repo | https://github.com/tsproisl/EmotiKLUE |
| Framework | none |
