Paper Group NAWR 9
Context-Dependent Sentiment Analysis in User-Generated Videos. Temporal Residual Networks for Dynamic Scene Recognition. AGA: Attribute-Guided Augmentation. A Principled Framework for Evaluating Summarizers: Comparing Models of Summary Quality against Human Judgments. Discriminating between Similar Languages using Weighted Subword Features. Non-con …
Context-Dependent Sentiment Analysis in User-Generated Videos
| Title | Context-Dependent Sentiment Analysis in User-Generated Videos |
| Authors | Soujanya Poria, Erik Cambria, Devamanyu Hazarika, Navonil Majumder, Amir Zadeh, Louis-Philippe Morency |
| Abstract | Multimodal sentiment analysis is a developing area of research, which involves the identification of sentiments in videos. Current research considers utterances as independent entities, i.e., ignores the interdependencies and relations among the utterances of a video. In this paper, we propose a LSTM-based model that enables utterances to capture contextual information from their surroundings in the same video, thus aiding the classification process. Our method shows 5-10{%} performance improvement over the state of the art and high robustness to generalizability. |
| Tasks | Emotion Recognition, Multimodal Emotion Recognition, Multimodal Sentiment Analysis, Named Entity Recognition, Sarcasm Detection, Sentiment Analysis |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1081/ |
| https://www.aclweb.org/anthology/P17-1081 | |
| PWC | https://paperswithcode.com/paper/context-dependent-sentiment-analysis-in-user |
| Repo | https://github.com/soujanyaporia/multimodal-sentiment-analysis |
| Framework | tf |
Temporal Residual Networks for Dynamic Scene Recognition
| Title | Temporal Residual Networks for Dynamic Scene Recognition |
| Authors | Christoph Feichtenhofer, Axel Pinz, Richard P. Wildes |
| Abstract | This paper combines three contributions to establish a new state-of-the-art in dynamic scene recognition. First, we present a novel ConvNet architecture based on temporal residual units that is fully convolutional in spacetime. Our model augments spatial ResNets with convolutions across time to hierarchically add temporal residuals as the depth of the network increases. Second, existing approaches to video-based recognition are categorized and a baseline of seven previously top performing algorithms is selected for comparative evaluation on dynamic scenes. Third, we introduce a new and challenging video database of dynamic scenes that more than doubles the size of those previously available. This dataset is explicitly split into two subsets of equal size that contain videos with and without camera motion to allow for systematic study of how this variable interacts with the defining dynamics of the scene per se. Our evaluations verify the particular strengths and weaknesses of the baseline algorithms with respect to various scene classes and camera motion parameters. Finally, our temporal ResNet boosts recognition performance and establishes a new state-of-the-art on dynamic scene recognition, as well as on the complementary task of action recognition. |
| Tasks | Scene Recognition, Temporal Action Localization |
| Published | 2017-07-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2017/html/Feichtenhofer_Temporal_Residual_Networks_CVPR_2017_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2017/papers/Feichtenhofer_Temporal_Residual_Networks_CVPR_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/temporal-residual-networks-for-dynamic-scene |
| Repo | https://github.com/feichtenhofer/temporal-resnet |
| Framework | none |
AGA: Attribute-Guided Augmentation
| Title | AGA: Attribute-Guided Augmentation |
| Authors | Mandar Dixit, Roland Kwitt, Marc Niethammer, Nuno Vasconcelos |
| Abstract | We consider the problem of data augmentation, i.e., generating artificial samples to extend a given corpus of training data. Specifically, we propose attributed-guided augmentation (AGA) which learns a mapping that allows to synthesize data such that an attribute of a synthesized sample is at a desired value or strength. This is particularly interesting in situations where little data with no attribute annotation is available for learning, but we have access to a large external corpus of heavily annotated samples. While prior works primarily augment in the space of images, we propose to perform augmentation in feature space instead. We implement our approach as a deep encoder-decoder architecture that learns the synthesis function in an end-to-end manner. We demonstrate the utility of our approach on the problems of (1) one-shot object recognition in a transfer-learning setting where we have no prior knowledge of the new classes, as well as (2) object-based one-shot scene recognition. As external data, we leverage 3D depth and pose information from the SUN RGB-D dataset. Our experiments show that attribute-guided augmentation of high-level CNN features considerably improves one-shot recognition performance on both problems. |
| Tasks | Data Augmentation, Object Recognition, Scene Recognition, Transfer Learning |
| Published | 2017-07-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2017/html/Dixit_AGA_Attribute-Guided_Augmentation_CVPR_2017_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2017/papers/Dixit_AGA_Attribute-Guided_Augmentation_CVPR_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/aga-attribute-guided-augmentation-1 |
| Repo | https://github.com/rkwitt/GuidedAugmentation |
| Framework | torch |
A Principled Framework for Evaluating Summarizers: Comparing Models of Summary Quality against Human Judgments
| Title | A Principled Framework for Evaluating Summarizers: Comparing Models of Summary Quality against Human Judgments |
| Authors | Maxime Peyrard, Judith Eckle-Kohler |
| Abstract | We present a new framework for evaluating extractive summarizers, which is based on a principled representation as optimization problem. We prove that every extractive summarizer can be decomposed into an objective function and an optimization technique. We perform a comparative analysis and evaluation of several objective functions embedded in well-known summarizers regarding their correlation with human judgments. Our comparison of these correlations across two datasets yields surprising insights into the role and performance of objective functions in the different summarizers. |
| Tasks | |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2005/ |
| https://www.aclweb.org/anthology/P17-2005 | |
| PWC | https://paperswithcode.com/paper/a-principled-framework-for-evaluating |
| Repo | https://github.com/UKPLab/acl2017-theta_evaluation_summarization |
| Framework | none |
Discriminating between Similar Languages using Weighted Subword Features
| Title | Discriminating between Similar Languages using Weighted Subword Features |
| Authors | Adrien Barbaresi |
| Abstract | The present contribution revolves around a contrastive subword n-gram model which has been tested in the Discriminating between Similar Languages shared task. I present and discuss the method used in this 14-way language identification task comprising varieties of 6 main language groups. It features the following characteristics: (1) the preprocessing and conversion of a collection of documents to sparse features; (2) weighted character n-gram profiles; (3) a multinomial Bayesian classifier. Meaningful bag-of-n-grams features can be used as a system in a straightforward way, my approach outperforms most of the systems used in the DSL shared task (3rd rank). |
| Tasks | Language Identification, Text Categorization |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1223/ |
| https://www.aclweb.org/anthology/W17-1223 | |
| PWC | https://paperswithcode.com/paper/discriminating-between-similar-languages-3 |
| Repo | https://github.com/adbar/vardial-experiments |
| Framework | none |
Non-convex Finite-Sum Optimization Via SCSG Methods
| Title | Non-convex Finite-Sum Optimization Via SCSG Methods |
| Authors | Lihua Lei, Cheng Ju, Jianbo Chen, Michael I. Jordan |
| Abstract | We develop a class of algorithms, as variants of the stochastically controlled stochastic gradient (SCSG) methods , for the smooth nonconvex finite-sum optimization problem. Only assuming the smoothness of each component, the complexity of SCSG to reach a stationary point with $E \nabla f(x)^{2}\le \epsilon$ is $O(\min{\epsilon^{-5/3}, \epsilon^{-1}n^{2/3}})$, which strictly outperforms the stochastic gradient descent. Moreover, SCSG is never worse than the state-of-the-art methods based on variance reduction and it significantly outperforms them when the target accuracy is low. A similar acceleration is also achieved when the functions satisfy the Polyak-Lojasiewicz condition. Empirical experiments demonstrate that SCSG outperforms stochastic gradient methods on training multi-layers neural networks in terms of both training and validation loss. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6829-non-convex-finite-sum-optimization-via-scsg-methods |
| http://papers.nips.cc/paper/6829-non-convex-finite-sum-optimization-via-scsg-methods.pdf | |
| PWC | https://paperswithcode.com/paper/non-convex-finite-sum-optimization-via-scsg |
| Repo | https://github.com/Jianbo-Lab/SCSG |
| Framework | tf |
Patient Subtyping via Time-Aware LSTM Networks
| Title | Patient Subtyping via Time-Aware LSTM Networks |
| Authors | Inci M. Baytas, Cao Xiao, Xi Zhang, Fei Wang, Anil K. Jain, Jiayu Zhou |
| Abstract | In the study of various diseases, heterogeneity among patients usually leads to different progression patterns and may require different types of therapeutic intervention. Therefore, it is important to study patient subtyping, which is grouping of patients into disease characterizing subtypes. Subtyping from complex patient data is challenging because of the information heterogeneity and temporal dynamics. Long-Short Term Memory (LSTM) has been successfully used in many domains for processing sequential data, and recently applied for analyzing longitudinal patient records. The LSTM units are designed to handle data with constant elapsed times between consecutive elements of a sequence. Given that time lapse between successive elements in patient records can vary from days to months, the design of traditional LSTM may lead to suboptimal performance. In this paper, we propose a novel LSTM unit called Time-Aware LSTM (T-LSTM) to handle irregular time intervals in longitudinal patient records. We learn a subspace decomposition of the cell memory which enables time decay to discount the memory content according to the elapsed time. We propose a patient subtyping model that leverages the proposed T-LSTM in an auto-encoder to learn a powerful single representation for sequential records of patients, which are then used to cluster patients into clinical subtypes. Experiments on synthetic and real world datasets show that the proposed T-LSTM architecture captures the underlying structures in the sequences with time irregularities. |
| Tasks | Multivariate Time Series Forecasting |
| Published | 2017-08-13 |
| URL | https://doi.org/10.1145/3097983.3097997 |
| http://biometrics.cse.msu.edu/Publications/MachineLearning/Baytasetal_PatientSubtypingViaTimeAwareLSTMNetworks.pdf | |
| PWC | https://paperswithcode.com/paper/patient-subtyping-via-time-aware-lstm |
| Repo | https://github.com/illidanlab/T-LSTM |
| Framework | tf |
UdL at SemEval-2017 Task 1: Semantic Textual Similarity Estimation of English Sentence Pairs Using Regression Model over Pairwise Features
| Title | UdL at SemEval-2017 Task 1: Semantic Textual Similarity Estimation of English Sentence Pairs Using Regression Model over Pairwise Features |
| Authors | Hussein T. Al-Natsheh, Lucie Martinet, Fabrice Muhlenbach, Djamel Abdelkader Zighed |
| Abstract | This paper describes the model UdL we proposed to solve the semantic textual similarity task of SemEval 2017 workshop. The track we participated in was estimating the semantics relatedness of a given set of sentence pairs in English. The best run out of three submitted runs of our model achieved a Pearson correlation score of 0.8004 compared to a hidden human annotation of 250 pairs. We used random forest ensemble learning to map an expandable set of extracted pairwise features into a semantic similarity estimated value bounded between 0 and 5. Most of these features were calculated using word embedding vectors similarity to align Part of Speech (PoS) and Name Entities (NE) tagged tokens of each sentence pair. Among other pairwise features, we experimented a classical tf-idf weighted Bag of Words (BoW) vector model but with character-based range of n-grams instead of words. This sentence vector BoW-based feature gave a relatively high importance value percentage in the feature importances analysis of the ensemble learning. |
| Tasks | Image Captioning, Model Selection, Semantic Similarity, Semantic Textual Similarity, Sentence Embedding, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2013/ |
| https://www.aclweb.org/anthology/S17-2013 | |
| PWC | https://paperswithcode.com/paper/udl-at-semeval-2017-task-1-semantic-textual |
| Repo | https://github.com/natsheh/sensim |
| Framework | tf |
Rotated Word Vector Representations and their Interpretability
| Title | Rotated Word Vector Representations and their Interpretability |
| Authors | Sungjoon Park, JinYeong Bak, Alice Oh |
| Abstract | Vector representation of words improves performance in various NLP tasks, but the high dimensional word vectors are very difficult to interpret. We apply several rotation algorithms to the vector representation of words to improve the interpretability. Unlike previous approaches that induce sparsity, the rotated vectors are interpretable while preserving the expressive performance of the original vectors. Furthermore, any prebuilt word vector representation can be rotated for improved interpretability. We apply rotation to skipgrams and glove and compare the expressive power and interpretability with the original vectors and the sparse overcomplete vectors. The results show that the rotated vectors outperform the original and the sparse overcomplete vectors for interpretability and expressiveness tasks. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1041/ |
| https://www.aclweb.org/anthology/D17-1041 | |
| PWC | https://paperswithcode.com/paper/rotated-word-vector-representations-and-their |
| Repo | https://github.com/SungjoonPark/factor_rotation |
| Framework | pytorch |
Affinity Clustering: Hierarchical Clustering at Scale
| Title | Affinity Clustering: Hierarchical Clustering at Scale |
| Authors | Mohammadhossein Bateni, Soheil Behnezhad, Mahsa Derakhshan, Mohammadtaghi Hajiaghayi, Raimondas Kiveris, Silvio Lattanzi, Vahab Mirrokni |
| Abstract | Graph clustering is a fundamental task in many data-mining and machine-learning pipelines. In particular, identifying a good hierarchical structure is at the same time a fundamental and challenging problem for several applications. The amount of data to analyze is increasing at an astonishing rate each day. Hence there is a need for new solutions to efficiently compute effective hierarchical clusterings on such huge data. The main focus of this paper is on minimum spanning tree (MST) based clusterings. In particular, we propose affinity, a novel hierarchical clustering based on Boruvka’s MST algorithm. We prove certain theoretical guarantees for affinity (as well as some other classic algorithms) and show that in practice it is superior to several other state-of-the-art clustering algorithms. Furthermore, we present two MapReduce implementations for affinity. The first one works for the case where the input graph is dense and takes constant rounds. It is based on a Massively Parallel MST algorithm for dense graphs that improves upon the state-of-the-art algorithm of Lattanzi et al. (SPAA 2011). Our second algorithm has no assumption on the density of the input graph and finds the affinity clustering in $O(\log n)$ rounds using Distributed Hash Tables (DHTs). We show experimentally that our algorithms are scalable for huge data sets, e.g., for graphs with trillions of edges. |
| Tasks | Graph Clustering |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7262-affinity-clustering-hierarchical-clustering-at-scale |
| http://papers.nips.cc/paper/7262-affinity-clustering-hierarchical-clustering-at-scale.pdf | |
| PWC | https://paperswithcode.com/paper/affinity-clustering-hierarchical-clustering |
| Repo | https://github.com/MahsaDerakhshan/AffinityClustering |
| Framework | none |
Combined Group and Exclusive Sparsity for Deep Neural Networks
| Title | Combined Group and Exclusive Sparsity for Deep Neural Networks |
| Authors | Jaehong Yoon, Sung Ju Hwang |
| Abstract | The number of parameters in a deep neural network is usually very large, which helps with its learning capacity but also hinders its scalability and practicality due to memory/time inefficiency and overfitting. To resolve this issue, we propose a sparsity regularization method that exploits both positive and negative correlations among the features to enforce the network to be sparse, and at the same time remove any redundancies among the features to fully utilize the capacity of the network. Specifically, we propose to use an exclusive sparsity regularization based on (1,2)-norm, which promotes competition for features between different weights, thus enforcing them to fit to disjoint sets of features. We further combine the exclusive sparsity with the group sparsity based on (2,1)-norm, to promote both sharing and competition for features in training of a deep neural network. We validate our method on multiple public datasets, and the results show that our method can obtain more compact and efficient networks while also improving the performance over the base networks with full weights, as opposed to existing sparsity regularizations that often obtain efficiency at the expense of prediction accuracy. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=474 |
| http://proceedings.mlr.press/v70/yoon17a/yoon17a.pdf | |
| PWC | https://paperswithcode.com/paper/combined-group-and-exclusive-sparsity-for |
| Repo | https://github.com/jaehong-yoon93/CGES |
| Framework | tf |
Corpus Selection Approaches for Multilingual Parsing from Raw Text to Universal Dependencies
| Title | Corpus Selection Approaches for Multilingual Parsing from Raw Text to Universal Dependencies |
| Authors | Ryan Hornby, Clark Taylor, Jungyeul Park |
| Abstract | This paper describes UALing{'}s approach to the \textit{CoNLL 2017 UD Shared Task} using corpus selection techniques to reduce training data size. The methodology is simple: we use similarity measures to select a corpus from available training data (even from multiple corpora for surprise languages) and use the resulting corpus to complete the parsing task. The training and parsing is done with the baseline UDPipe system (Straka et al., 2016). While our approach reduces the size of training data significantly, it retains performance within 0.5{%} of the baseline system. Due to the reduction in training data size, our system performs faster than the na{"\i}ve, complete corpus method. Specifically, our system runs in less than 10 minutes, ranking it among the fastest entries for this task. Our system is available at \url{https://github.com/CoNLL-UD-2017/UALING}. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-3021/ |
| https://www.aclweb.org/anthology/K17-3021 | |
| PWC | https://paperswithcode.com/paper/corpus-selection-approaches-for-multilingual |
| Repo | https://github.com/CoNLL-UD-2017/UALING |
| Framework | none |
YASS: Yet Another Spike Sorter
| Title | YASS: Yet Another Spike Sorter |
| Authors | Jin Hyung Lee, David E. Carlson, Hooshmand Shokri Razaghi, Weichi Yao, Georges A. Goetz, Espen Hagen, Eleanor Batty, E.J. Chichilnisky, Gaute T. Einevoll, Liam Paninski |
| Abstract | Spike sorting is a critical first step in extracting neural signals from large-scale electrophysiological data. This manuscript describes an efficient, reliable pipeline for spike sorting on dense multi-electrode arrays (MEAs), where neural signals appear across many electrodes and spike sorting currently represents a major computational bottleneck. We present several new techniques that make dense MEA spike sorting more robust and scalable. Our pipeline is based on an efficient multi-stage ‘‘triage-then-cluster-then-pursuit’’ approach that initially extracts only clean, high-quality waveforms from the electrophysiological time series by temporarily skipping noisy or ‘‘collided’’ events (representing two neurons firing synchronously). This is accomplished by developing a neural network detection method followed by efficient outlier triaging. The clean waveforms are then used to infer the set of neural spike waveform templates through nonparametric Bayesian clustering. Our clustering approach adapts a ‘‘coreset’’ approach for data reduction and uses efficient inference methods in a Dirichlet process mixture model framework to dramatically improve the scalability and reliability of the entire pipeline. The ‘‘triaged’’ waveforms are then finally recovered with matching-pursuit deconvolution techniques. The proposed methods improve on the state-of-the-art in terms of accuracy and stability on both real and biophysically-realistic simulated MEA data. Furthermore, the proposed pipeline is efficient, learning templates and clustering faster than real-time for a 500-electrode dataset, largely on a single CPU core. |
| Tasks | Time Series |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6989-yass-yet-another-spike-sorter |
| http://papers.nips.cc/paper/6989-yass-yet-another-spike-sorter.pdf | |
| PWC | https://paperswithcode.com/paper/yass-yet-another-spike-sorter |
| Repo | https://github.com/paninski-lab/yass |
| Framework | pytorch |
Where is Misty? Interpreting Spatial Descriptors by Modeling Regions in Space
| Title | Where is Misty? Interpreting Spatial Descriptors by Modeling Regions in Space |
| Authors | Nikita Kitaev, Dan Klein |
| Abstract | We present a model for locating regions in space based on natural language descriptions. Starting with a 3D scene and a sentence, our model is able to associate words in the sentence with regions in the scene, interpret relations such as {}on top of{'} or {}next to,{'} and finally locate the region described in the sentence. All components form a single neural network that is trained end-to-end without prior knowledge of object segmentation. To evaluate our model, we construct and release a new dataset consisting of Minecraft scenes with crowdsourced natural language descriptions. We achieve a 32{%} relative error reduction compared to a strong neural baseline. |
| Tasks | Semantic Segmentation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1015/ |
| https://www.aclweb.org/anthology/D17-1015 | |
| PWC | https://paperswithcode.com/paper/where-is-misty-interpreting-spatial |
| Repo | https://github.com/nikitakit/voxelworld |
| Framework | none |
Classification of telicity using cross-linguistic annotation projection
| Title | Classification of telicity using cross-linguistic annotation projection |
| Authors | Annemarie Friedrich, Damyana Gateva |
| Abstract | This paper addresses the automatic recognition of telicity, an aspectual notion. A telic event includes a natural endpoint ({}she walked home{''}), while an atelic event does not ({}she walked around{''}). Recognizing this difference is a prerequisite for temporal natural language understanding. In English, this classification task is difficult, as telicity is a covert linguistic category. In contrast, in Slavic languages, aspect is part of a verb{'}s meaning and even available in machine-readable dictionaries. Our contributions are as follows. We successfully leverage additional silver standard training data in the form of projected annotations from parallel English-Czech data as well as context information, improving automatic telicity classification for English significantly compared to previous work. We also create a new data set of English texts manually annotated with telicity. |
| Tasks | Machine Translation, Question Answering, Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1271/ |
| https://www.aclweb.org/anthology/D17-1271 | |
| PWC | https://paperswithcode.com/paper/classification-of-telicity-using-cross |
| Repo | https://github.com/annefried/telicity |
| Framework | none |
