Paper Group NAWR 26
Kernelized Synaptic Weight Matrices. Deep Temporal Clustering: Fully unsupervised learning of time-domain features. Inter and Intra Topic Structure Learning with Word Embeddings. PyrEval: An Automated Method for Summary Content Analysis. Face Aging With Identity-Preserved Conditional Generative Adversarial Networks. Aggression Detection on Social M …
Kernelized Synaptic Weight Matrices
| Title | Kernelized Synaptic Weight Matrices |
| Authors | Lorenz Muller, Julien Martel, Giacomo Indiveri |
| Abstract | In this paper we introduce a novel neural network architecture, in which weight matrices are re-parametrized in terms of low-dimensional vectors, interacting through kernel functions. A layer of our network can be interpreted as introducing a (potentially infinitely wide) linear layer between input and output. We describe the theory underpinning this model and validate it with concrete examples, exploring how it can be used to impose structure on neural networks in diverse applications ranging from data visualization to recommender systems. We achieve state-of-the-art performance in a collaborative filtering task (MovieLens). |
| Tasks | Recommendation Systems |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2141 |
| http://proceedings.mlr.press/v80/muller18a/muller18a.pdf | |
| PWC | https://paperswithcode.com/paper/kernelized-synaptic-weight-matrices |
| Repo | https://github.com/lorenzMuller/kernelNet_MovieLens |
| Framework | tf |
Deep Temporal Clustering: Fully unsupervised learning of time-domain features
| Title | Deep Temporal Clustering: Fully unsupervised learning of time-domain features |
| Authors | Naveen Sai Madiraju, Seid M. Sadat, Dimitry Fisher, Homa Karimabadi |
| Abstract | Unsupervised learning of timeseries data is a challenging problem in machine learning. Here, we propose a novel algorithm, Deep Temporal Clustering (DTC), a fully unsupervised method, to naturally integrate dimensionality reduction and temporal clustering into a single end to end learning framework. The algorithm starts with an initial cluster estimates using an autoencoder for dimensionality reduction and a novel temporal clustering layer for cluster assignment. Then it jointly optimizes the clustering objective and the dimensionality reduction objective. Based on requirement and application, the temporal clustering layer can be customized with any temporal similarity metric. Several similarity metrics are considered and compared. To gain insight into features that the network has learned for its clustering, we apply a visualization method that generates a heat map of regions of interest in the timeseries. The viability of the algorithm is demonstrated using timeseries data from diverse domains, ranging from earthquakes to sensor data from spacecraft. In each case, we show that our algorithm outperforms traditional methods. This performance is attributed to fully integrated temporal dimensionality reduction and clustering criterion. |
| Tasks | Dimensionality Reduction |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=SJFM0ZWCb |
| https://openreview.net/pdf?id=SJFM0ZWCb | |
| PWC | https://paperswithcode.com/paper/deep-temporal-clustering-fully-unsupervised-1 |
| Repo | https://github.com/saeeeeru/dtc-tensorflow |
| Framework | tf |
Inter and Intra Topic Structure Learning with Word Embeddings
| Title | Inter and Intra Topic Structure Learning with Word Embeddings |
| Authors | He Zhao, Lan Du, Wray Buntine, Mingyuan Zhou |
| Abstract | One important task of topic modeling for text analysis is interpretability. By discovering structured topics one is able to yield improved interpretability as well as modeling accuracy. In this paper, we propose a novel topic model with a deep structure that explores both inter-topic and intra-topic structures informed by word embeddings. Specifically, our model discovers inter topic structures in the form of topic hierarchies and discovers intra topic structures in the form of sub-topics, each of which is informed by word embeddings and captures a fine-grained thematic aspect of a normal topic. Extensive experiments demonstrate that our model achieves the state-of-the-art performance in terms of perplexity, document classification, and topic quality. Moreover, with topic hierarchies and sub-topics, the topics discovered in our model are more interpretable, providing an illuminating means to understand text data. |
| Tasks | Document Classification, Word Embeddings |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2183 |
| http://proceedings.mlr.press/v80/zhao18a/zhao18a.pdf | |
| PWC | https://paperswithcode.com/paper/inter-and-intra-topic-structure-learning-with |
| Repo | https://github.com/ethanhezhao/WEDTM |
| Framework | none |
PyrEval: An Automated Method for Summary Content Analysis
| Title | PyrEval: An Automated Method for Summary Content Analysis |
| Authors | Yanjun Gao, Andrew Warner, Rebecca Passonneau |
| Abstract | |
| Tasks | Abstractive Text Summarization |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1511/ |
| https://www.aclweb.org/anthology/L18-1511 | |
| PWC | https://paperswithcode.com/paper/pyreval-an-automated-method-for-summary |
| Repo | https://github.com/serenayj/PyrEval |
| Framework | none |
Face Aging With Identity-Preserved Conditional Generative Adversarial Networks
| Title | Face Aging With Identity-Preserved Conditional Generative Adversarial Networks |
| Authors | Zongwei Wang, Xu Tang, Weixin Luo, Shenghua Gao |
| Abstract | Face aging is of great importance for cross-age recognition and entertainment related applications. However, the lack of labeled faces of the same person across a long age range makes it challenging. Because of different aging speed of different persons, our face aging approach aims at synthesizing a face whose target age lies in some given age group instead of synthesizing a face with a certain age. By grouping faces with target age together, the objective of face aging is equivalent to transferring aging patterns of faces within the target age group to the face whose aged face is to be synthesized. Meanwhile, the synthesized face should have the same identity with the input face. Thus we propose an Identity-Preserved Conditional Generative Adversarial Networks (IPCGANs) framework, in which a Conditional Generative Adversarial Networks module functions as generating a face that looks realistic and is with the target age, an identity-preserved module preserves the identity information and an age classifier forces the generated face with the target age. Both qualitative and quantitative experiments show that our method can generate more realistic faces in terms of image quality, person identity and age consistency with human observations. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Wang_Face_Aging_With_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Face_Aging_With_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/face-aging-with-identity-preserved |
| Repo | https://github.com/dawei6875797/Face-Aging-with-Identity-Preserved-Conditional-Generative-Adversarial-Networks |
| Framework | tf |
Aggression Detection on Social Media Text Using Deep Neural Networks
| Title | Aggression Detection on Social Media Text Using Deep Neural Networks |
| Authors | Vinay Singh, Aman Varshney, Syed Sarfaraz Akhtar, Deepanshu Vijay, Manish Shrivastava |
| Abstract | In the past few years, bully and aggressive posts on social media have grown significantly, causing serious consequences for victims/users of all demographics. Majority of the work in this field has been done for English only. In this paper, we introduce a deep learning based classification system for Facebook posts and comments of Hindi-English Code-Mixed text to detect the aggressive behaviour of/towards users. Our work focuses on text from users majorly in the Indian Subcontinent. The dataset that we used for our models is provided by \textbf{TRAC-1}in their shared task. Our classification model assigns each Facebook post/comment to one of the three predefined categories: {}Overtly Aggressive{''}, {}Covertly Aggressive{''} and {``}Non-Aggressive{''}. We experimented with 6 classification models and our CNN model on a 10 K-fold cross-validation gave the best result with the prediction accuracy of 73.2{%}. | |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5106/ |
| https://www.aclweb.org/anthology/W18-5106 | |
| PWC | https://paperswithcode.com/paper/aggression-detection-on-social-media-text |
| Repo | https://github.com/SilentFlame/AggressionDetection |
| Framework | none |
On Batch Adaptive Training for Deep Learning: Lower Loss and Larger Step Size
| Title | On Batch Adaptive Training for Deep Learning: Lower Loss and Larger Step Size |
| Authors | Runyao Chen, Kun Wu, Ping Luo |
| Abstract | Mini-batch gradient descent and its variants are commonly used in deep learning. The principle of mini-batch gradient descent is to use noisy gradient calculated on a batch to estimate the real gradient, thus balancing the computation cost per iteration and the uncertainty of noisy gradient. However, its batch size is a fixed hyper-parameter requiring manual setting before training the neural network. Yin et al. (2017) proposed a batch adaptive stochastic gradient descent (BA-SGD) that can dynamically choose a proper batch size as learning proceeds. We extend the BA-SGD to momentum algorithm and evaluate both the BA-SGD and the batch adaptive momentum (BA-Momentum) on two deep learning tasks from natural language processing to image classification. Experiments confirm that batch adaptive methods can achieve a lower loss compared with mini-batch methods after scanning the same epochs of data. Furthermore, our BA-Momentum is more robust against larger step sizes, in that it can dynamically enlarge the batch size to reduce the larger uncertainty brought by larger step sizes. We also identified an interesting phenomenon, batch size boom. The code implementing batch adaptive framework is now open source, applicable to any gradient-based optimization problems. |
| Tasks | Image Classification |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=SybqeKgA- |
| https://openreview.net/pdf?id=SybqeKgA- | |
| PWC | https://paperswithcode.com/paper/on-batch-adaptive-training-for-deep-learning |
| Repo | https://github.com/thomasyao3096/Batch_Adaptive_Framework |
| Framework | pytorch |
Multiway Attention Networks for Modeling Sentence Pairs
| Title | Multiway Attention Networks for Modeling Sentence Pairs |
| Authors | Chuanqi Tan, Furu Wei, Wenhui Wang, Weifeng Lv, Ming Zhou |
| Abstract | Modeling sentence pairs plays the vital role for judging the relationship between two sentences, such as paraphrase identification, natural language inference, and answer sentence selection. Previous work achieves very promising results using neural networks with attention mechanism. In this paper, we propose the multiway attention networks which employ multiple attention functions to match sentence pairs under the matching-aggregation framework. Specifically, we design four attention functions to match words in corresponding sentences. Then, we aggregate the matching information from each function, and combine the information from all functions to obtain the final representation. Experimental results demonstrate that the proposed multiway attention networks improve the result on the Quora Question Pairs, SNLI, MultiNLI, and answer sentence selection task on the SQuAD dataset. |
| Tasks | Natural Language Inference, Paraphrase Identification |
| Published | 2018-07-01 |
| URL | https://www.ijcai.org/proceedings/2018/0613 |
| https://www.ijcai.org/proceedings/2018/0613.pdf | |
| PWC | https://paperswithcode.com/paper/multiway-attention-networks-for-modeling |
| Repo | https://github.com/zsweet/zsw_AI_model |
| Framework | pytorch |
Geolocation Estimation of Photos using a Hierarchical Model and Scene Classification
| Title | Geolocation Estimation of Photos using a Hierarchical Model and Scene Classification |
| Authors | Eric Muller-Budack, Kader Pustu-Iren, Ralph Ewerth |
| Abstract | While the successful estimation of a photo’s geolocation enables a number of interesting applications, it is also a very challenging task. Due to the complexity of the problem, most existing approaches are restricted to specific areas, imagery, or worldwide landmarks. Only a few proposals predict GPS coordinates without any limitations. In this paper, we introduce several deep learning methods, which pursue the latter approach and treat geolocalization as a classification problem where the earth is subdivided into geographical cells. We propose to exploit hierarchical knowledge of multiple partitionings and additionally extract and take the photo’s scene content into account, i.e., indoor, natural, or urban setting etc. As a result, contextual information at different spatial resolutions as well as more specific features for various environmental settings are incorporated in the learning process of the convolutional neural network. Experimental results on two benchmarks demonstrate the effectiveness of our approach outperforming the state of the art while using a significant lower number of training images and without relying on retrieval methods that require an appropriate reference dataset. |
| Tasks | Scene Classification |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Eric_Muller-Budack_Geolocation_Estimation_of_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Eric_Muller-Budack_Geolocation_Estimation_of_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/geolocation-estimation-of-photos-using-a |
| Repo | https://github.com/TIBHannover/GeoEstimation |
| Framework | tf |
Constrained Optimization Based Low-Rank Approximation of Deep Neural Networks
| Title | Constrained Optimization Based Low-Rank Approximation of Deep Neural Networks |
| Authors | Chong Li, C. J. Richard Shi |
| Abstract | We present COBLA—Constrained Optimization Based Low-rank Approximation—a systematic method of finding an optimal low-rank approximation of a trained convolutional neural network, subject to constraints in the number of multiply-accumulate (MAC) operations and the memory footprint. COBLA optimally allocates the constrained computation resource into each layer of the approximated network. The singular value decomposition of the network weight is computed, then a binary masking variable is introduced to denote whether a particular singular value and the corresponding singular vectors are used in low-rank approximation. With this formulation, the number of the MAC operations and the memory footprint are represented as linear constraints in terms of the binary masking variables. The resulted 0-1 integer programming problem is approximately solved by sequential quadratic programming. COBLA does not introduce any hyperparameter. We empirically demonstrate that COBLA outperforms prior art using the SqueezeNet and VGG-16 architecture on the ImageNet dataset. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Chong_Li_Constrained_Optimization_Based_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Chong_Li_Constrained_Optimization_Based_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/constrained-optimization-based-low-rank |
| Repo | https://github.com/chongli-uw/cobla |
| Framework | none |
One Size Fits All? A simple LSTM for non-literal token and construction-level classification
| Title | One Size Fits All? A simple LSTM for non-literal token and construction-level classification |
| Authors | Erik-L{^a}n Do Dinh, Steffen Eger, Iryna Gurevych |
| Abstract | In this paper, we tackle four different tasks of non-literal language classification: token and construction level metaphor detection, classification of idiomatic use of infinitive-verb compounds, and classification of non-literal particle verbs. One of the tasks operates on the token level, while the three other tasks classify constructions such as {}hot topic{''} or {}stehen lassen{''} ({}to allow sth. to stand{''} vs. {}to abandon so.{''}). The two metaphor detection tasks are in English, while the two non-literal language detection tasks are in German. We propose a simple context-encoding LSTM model and show that it outperforms the state-of-the-art on two tasks. Additionally, we experiment with different embeddings for the token level metaphor detection task and find that 1) their performance varies according to the genre, and 2) word2vec embeddings perform best on 3 out of 4 genres, despite being one of the simplest tested model. In summary, we present a large-scale analysis of a neural model for non-literal language classification (i) at different granularities, (ii) in different languages, (iii) over different non-literal language phenomena. |
| Tasks | Multi-Task Learning |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4508/ |
| https://www.aclweb.org/anthology/W18-4508 | |
| PWC | https://paperswithcode.com/paper/one-size-fits-all-a-simple-lstm-for-non |
| Repo | https://github.com/UKPLab/latech-cflf-2018-nonliteral |
| Framework | none |
On-Device Neural Language Model Based Word Prediction
| Title | On-Device Neural Language Model Based Word Prediction |
| Authors | Seunghak Yu, Nilesh Kulkarni, Haejun Lee, Jihie Kim |
| Abstract | Recent developments in deep learning with application to language modeling have led to success in tasks of text processing, summarizing and machine translation. However, deploying huge language models for the mobile device such as on-device keyboards poses computation as a bottle-neck due to their puny computation capacities. In this work, we propose an on-device neural language model based word prediction method that optimizes run-time memory and also provides a real-time prediction environment. Our model size is 7.40MB and has average prediction time of 6.47 ms. Our proposed model outperforms the existing methods for word prediction in terms of keystroke savings and word prediction rate and has been successfully commercialized. |
| Tasks | Language Modelling, Machine Translation, Model Compression, Network Pruning, Speech Recognition |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-2028/ |
| https://www.aclweb.org/anthology/C18-2028 | |
| PWC | https://paperswithcode.com/paper/on-device-neural-language-model-based-word |
| Repo | https://github.com/meinwerk/WordPrediction |
| Framework | none |
PointCNN: Convolution On X-Transformed Points
| Title | PointCNN: Convolution On X-Transformed Points |
| Authors | Yangyan Li, Rui Bu, Mingchao Sun, Wei Wu, Xinhan Di, Baoquan Chen |
| Abstract | We present a simple and general framework for feature learning from point cloud. The key to the success of CNNs is the convolution operator that is capable of leveraging spatially-local correlation in data represented densely in grids (e.g. images). However, point cloud are irregular and unordered, thus a direct convolving of kernels against the features associated with the points will result in deserting the shape information while being variant to the orders. To address these problems, we propose to learn a X-transformation from the input points, which is used for simultaneously weighting the input features associated with the points and permuting them into latent potentially canonical order. Then element-wise product and sum operations of typical convolution operator are applied on the X-transformed features. The proposed method is a generalization of typical CNNs into learning features from point cloud, thus we call it PointCNN. Experiments show that PointCNN achieves on par or better performance than state-of-the-art methods on multiple challenging benchmark datasets and tasks. |
| Tasks | Semantic Segmentation |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7362-pointcnn-convolution-on-x-transformed-points |
| http://papers.nips.cc/paper/7362-pointcnn-convolution-on-x-transformed-points.pdf | |
| PWC | https://paperswithcode.com/paper/pointcnn-convolution-on-x-transformed-points |
| Repo | https://github.com/yangyanli/PointCNN |
| Framework | tf |
Focal Visual-Text Attention for Memex Question Answering
| Title | Focal Visual-Text Attention for Memex Question Answering |
| Authors | Junwei Liang, Lu Jiang, Liangliang Cao, Yannis Kalantidis, Li-Jia Li, and Alexander Hauptmann |
| Abstract | Recent insights on language and vision with neural networks have been successfully applied to simple single-image visual question answering. However, to tackle real-life question answering problems on multimedia collections such as personal photo albums, we have to look at whole collections with sequences of photos. This paper proposes a new multimodal MemexQA task: given a sequence of photos from a user, the goal is to automatically answer questions that help users recover their memory about an event captured in these photos. In addition to a text answer, a few grounding photos are also given to justify the answer. The grounding photos are necessary as they help users quickly verifying the answer. Towards solving the task, we 1) present the MemexQA dataset, the first publicly available multimodal question answering dataset consisting of real personal photo albums; 2) propose an end-to-end trainable network that makes use of a hierarchical process to dynamically determine what media and what time to focus on in the sequential data to answer the question. Experimental results on the MemexQA dataset demonstrate that our model outperforms strong baselines and yields the most relevant grounding photos on this challenging task. |
| Tasks | Memex Question Answering, Question Answering, Visual Question Answering |
| Published | 2018-12-14 |
| URL | https://ieeexplore.ieee.org/document/8603827 |
| https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8603827 | |
| PWC | https://paperswithcode.com/paper/focal-visual-text-attention-for-memex |
| Repo | https://github.com/JunweiLiang/FVTA_memoryqa |
| Framework | tf |
Simple Models for Word Formation in Slang
| Title | Simple Models for Word Formation in Slang |
| Authors | Vivek Kulkarni, William Yang Wang |
| Abstract | We propose the first generative models for three types of extra-grammatical word formation phenomena abounding in slang: Blends, Clippings, and Reduplicatives. Adopting a data-driven approach coupled with linguistic knowledge, we propose simple models with state of the art performance on human annotated gold standard datasets. Overall, our models reveal insights into the generative processes of word formation in slang {–} insights which are increasingly relevant in the context of the rising prevalence of slang and non-standard varieties on the Internet |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1129/ |
| https://www.aclweb.org/anthology/N18-1129 | |
| PWC | https://paperswithcode.com/paper/simple-models-for-word-formation-in-slang |
| Repo | https://github.com/viveksck/simplicity |
| Framework | pytorch |
