Paper Group NANR 196
The Revision of ISO-Space,Focused on the Movement Link. Economic Event Detection in Company-Specific News Text. Exploiting Dynamic Oracles to Train Projective Dependency Parsers on Non-Projective Trees. PointGrid: A Deep Network for 3D Shape Understanding. NOVEL AND EFFECTIVE PARALLEL MIX-GENERATOR GENERATIVE ADVERSARIAL NETWORKS. Multilingual Mult …
The Revision of ISO-Space,Focused on the Movement Link
Title | The Revision of ISO-Space,Focused on the Movement Link |
Authors | Kiyong Lee, James Pustejovsky, Harry Bunt |
Abstract | |
Tasks | |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/W18-4704/ |
https://www.aclweb.org/anthology/W18-4704 | |
PWC | https://paperswithcode.com/paper/the-revision-of-iso-spacefocused-on-the |
Repo | |
Framework | |
Economic Event Detection in Company-Specific News Text
Title | Economic Event Detection in Company-Specific News Text |
Authors | Gilles Jacobs, Els Lefever, V{'e}ronique Hoste |
Abstract | This paper presents a dataset and supervised classification approach for economic event detection in English news articles. Currently, the economic domain is lacking resources and methods for data-driven supervised event detection. The detection task is conceived as a sentence-level classification task for 10 different economic event types. Two different machine learning approaches were tested: a rich feature set Support Vector Machine (SVM) set-up and a word-vector-based long short-term memory recurrent neural network (RNN-LSTM) set-up. We show satisfactory results for most event types, with the linear kernel SVM outperforming the other experimental set-ups |
Tasks | Sentiment Analysis |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/W18-3101/ |
https://www.aclweb.org/anthology/W18-3101 | |
PWC | https://paperswithcode.com/paper/economic-event-detection-in-company-specific |
Repo | |
Framework | |
Exploiting Dynamic Oracles to Train Projective Dependency Parsers on Non-Projective Trees
Title | Exploiting Dynamic Oracles to Train Projective Dependency Parsers on Non-Projective Trees |
Authors | Lauriane Aufrant, Guillaume Wisniewski, Fran{\c{c}}ois Yvon |
Abstract | Because the most common transition systems are projective, training a transition-based dependency parser often implies to either ignore or rewrite the non-projective training examples, which has an adverse impact on accuracy. In this work, we propose a simple modification of dynamic oracles, which enables the use of non-projective data when training projective parsers. Evaluation on 73 treebanks shows that our method achieves significant gains (+2 to +7 UAS for the most non-projective languages) and consistently outperforms traditional projectivization and pseudo-projectivization approaches. |
Tasks | Dependency Parsing |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/N18-2066/ |
https://www.aclweb.org/anthology/N18-2066 | |
PWC | https://paperswithcode.com/paper/exploiting-dynamic-oracles-to-train |
Repo | |
Framework | |
PointGrid: A Deep Network for 3D Shape Understanding
Title | PointGrid: A Deep Network for 3D Shape Understanding |
Authors | Truc Le, Ye Duan |
Abstract | This paper presents a new deep learning architecture called PointGrid that is designed for 3D model recognition from unorganized point clouds. The new architecture embeds the input point cloud into a 3D grid by a simple, yet effective, sampling strategy and directly learns transformations and features from their raw coordinates. The proposed method is an integration of point and grid, a hybrid model, that leverages the simplicity of grid-based approaches such as VoxelNet while avoid its information loss. PointGrid learns better global information compared with PointNet and is much simpler than PointNet++, Kd-Net, Oct-Net and O-CNN, yet provides comparable recognition accuracy. With experiments on popular shape recognition benchmarks, PointGrid demonstrates competitive performance over existing deep learning methods on both classification and segmentation. |
Tasks | |
Published | 2018-06-01 |
URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Le_PointGrid_A_Deep_CVPR_2018_paper.html |
http://openaccess.thecvf.com/content_cvpr_2018/papers/Le_PointGrid_A_Deep_CVPR_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/pointgrid-a-deep-network-for-3d-shape |
Repo | |
Framework | |
NOVEL AND EFFECTIVE PARALLEL MIX-GENERATOR GENERATIVE ADVERSARIAL NETWORKS
Title | NOVEL AND EFFECTIVE PARALLEL MIX-GENERATOR GENERATIVE ADVERSARIAL NETWORKS |
Authors | Xia Xiao, Sanguthevar Rajasekaran |
Abstract | In this paper, we propose a mix-generator generative adversarial networks (PGAN) model that works in parallel by mixing multiple disjoint generators to approximate a complex real distribution. In our model, we propose an adjustment component that collects all the generated data points from the generators, learns the boundary between each pair of generators, and provides error to separate the support of each of the generated distributions. To overcome the instability in a multiplayer game, a shrinkage adjustment component method is introduced to gradually reduce the boundary between generators during the training procedure. To address the linearly growing training time problem in a multiple generators model, we propose a method to train the generators in parallel. This means that our work can be scaled up to large parallel computation frameworks. We present an efficient loss function for the discriminator, an effective adjustment component, and a suitable generator. We also show how to introduce the decay factor to stabilize the training procedure. We have performed extensive experiments on synthetic datasets, MNIST, and CIFAR-10. These experiments reveal that the error provided by the adjustment component could successfully separate the generated distributions and each of the generators can stably learn a part of the real distribution even if only a few modes are contained in the real distribution. |
Tasks | |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=rJHcpW-CW |
https://openreview.net/pdf?id=rJHcpW-CW | |
PWC | https://paperswithcode.com/paper/novel-and-effective-parallel-mix-generator |
Repo | |
Framework | |
Multilingual Multi-class Sentiment Classification Using Convolutional Neural Networks
Title | Multilingual Multi-class Sentiment Classification Using Convolutional Neural Networks |
Authors | Mohammed Attia, Younes Samih, Ali Elkahky, Laura Kallmeyer |
Abstract | |
Tasks | Document Classification, Language Identification, Sentiment Analysis, Text Categorization, Word Embeddings |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1101/ |
https://www.aclweb.org/anthology/L18-1101 | |
PWC | https://paperswithcode.com/paper/multilingual-multi-class-sentiment |
Repo | |
Framework | |
Content Explorer: Recommending Novel Entities for a Document Writer
Title | Content Explorer: Recommending Novel Entities for a Document Writer |
Authors | Michal Lukasik, Richard Zens |
Abstract | Background research is an essential part of document writing. Search engines are great for retrieving information once we know what to look for. However, the bigger challenge is often identifying topics for further research. Automated tools could help significantly in this discovery process and increase the productivity of the writer. In this paper, we formulate the problem of recommending topics to a writer. We consider this as a supervised learning problem and run a user study to validate this approach. We propose an evaluation metric and perform an empirical comparison of state-of-the-art models for extreme multi-label classification on a large data set. We demonstrate how a simple modification of the cross-entropy loss function leads to improved results of the deep learning models. |
Tasks | Extreme Multi-Label Classification, Multi-Label Classification |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/D18-1374/ |
https://www.aclweb.org/anthology/D18-1374 | |
PWC | https://paperswithcode.com/paper/content-explorer-recommending-novel-entities |
Repo | |
Framework | |
A Compositional Bayesian Semantics for Natural Language
Title | A Compositional Bayesian Semantics for Natural Language |
Authors | Jean-Philippe Bernardy, Rasmus Blanck, Stergios Chatzikyriakidis, Shalom Lappin |
Abstract | We propose a compositional Bayesian semantics that interprets declarative sentences in a natural language by assigning them probability conditions. These are conditional probabilities that estimate the likelihood that a competent speaker would endorse an assertion, given certain hypotheses. Our semantics is implemented in a functional programming language. It estimates the marginal probability of a sentence through Markov Chain Monte Carlo (MCMC) sampling of objects in vector space models satisfying specified hypotheses. We apply our semantics to examples with several predicates and generalised quantifiers, including higher-order quantifiers. It captures the vagueness of predication (both gradable and non-gradable), without positing a precise boundary for classifier application. We present a basic account of semantic learning based on our semantic system. We compare our proposal to other current theories of probabilistic semantics, and we show that it offers several important advantages over these accounts. |
Tasks | |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/W18-4101/ |
https://www.aclweb.org/anthology/W18-4101 | |
PWC | https://paperswithcode.com/paper/a-compositional-bayesian-semantics-for |
Repo | |
Framework | |
Cross-domain aspect extraction for sentiment analysis: a transductive learning approach
Title | Cross-domain aspect extraction for sentiment analysis: a transductive learning approach |
Authors | Ricardo Marcondes Marcacini, Rafael Geraldeli Rossi, Ivone Penque Matsuno, Solange Oliveira Rezende |
Abstract | Aspect-Based Sentiment Analysis (ABSA) is a promising approach to analyze consumer reviews at a high level of detail, where the opinion about each fea- ture of the product or service is considered. ABSA usually explores supervised inductive learning algorithms, which requires intense human effort for the la- beling process. In this paper, we investigate Cross-Domain Transfer Learning approaches, in which aspects already labeled in some domains can be used to support the aspect extraction of another domain where there are no labeled aspects. Existing cross-domain transfer learning approaches learn classifiers from labeled aspects in the source domain and then apply these classifiers in the target domain, i.e., two separate stages that may cause inconsistency due to different feature spaces. To overcome this drawback, we present an inno- vative approach called CD-ALPHN (Cross-Domain Aspect Label Propagation through Heterogeneous Networks). First, we propose a heterogeneous network- based representation that combines different features (labeled aspects, unlabeled aspects, and linguistic features) from source and target domain as nodes in a single network. Second, we propose a label propagation algorithm for aspect extraction from heterogeneous networks, where the linguistic features are used as a bridge for this propagation. Our algorithm is based on a transductive learning process, where we explore both labeled and unlabeled aspects during the label propagation. Experimental results show that the CD-ALPHN out- performs the state-of-the-art methods in scenarios where there is a high-level of inconsistency between the source and target domains — the most common scenario in real-world applications. Keywords: Cross Domain, Opinion Mining, Aspect Extraction |
Tasks | Aspect-Based Sentiment Analysis, Aspect Extraction, Opinion Mining, Sentiment Analysis, Transfer Learning |
Published | 2018-10-21 |
URL | https://www.sciencedirect.com/science/article/pii/S0167923618301386 |
https://www.sciencedirect.com/science/article/pii/S0167923618301386 | |
PWC | https://paperswithcode.com/paper/cross-domain-aspect-extraction-for-sentiment |
Repo | |
Framework | |
A Constrained Deep Neural Network for Ordinal Regression
Title | A Constrained Deep Neural Network for Ordinal Regression |
Authors | Yanzhu Liu, Adams Wai Kin Kong, Chi Keong Goh |
Abstract | Ordinal regression is a supervised learning problem aiming to classify instances into ordinal categories. It is challenging to automatically extract high-level features for representing intraclass information and interclass ordinal relationship simultaneously. This paper proposes a constrained optimization formulation for the ordinal regression problem which minimizes the negative loglikelihood for multiple categories constrained by the order relationship between instances. Mathematically, it is equivalent to an unconstrained formulation with a pairwise regularizer. An implementation based on the CNN framework is proposed to solve the problem such that high-level features can be extracted automatically, and the optimal solution can be learned through the traditional back-propagation method. The proposed pairwise constraints make the algorithm work even on small datasets, and a proposed efficient implementation make it be scalable for large datasets. Experimental results on four real-world benchmarks demonstrate that the proposed algorithm outperforms the traditional deep learning approaches and other state-of-the-art approaches based on hand-crafted features. |
Tasks | |
Published | 2018-06-01 |
URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Liu_A_Constrained_Deep_CVPR_2018_paper.html |
http://openaccess.thecvf.com/content_cvpr_2018/papers/Liu_A_Constrained_Deep_CVPR_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/a-constrained-deep-neural-network-for-ordinal |
Repo | |
Framework | |
Long-term Forecasting using Tensor-Train RNNs
Title | Long-term Forecasting using Tensor-Train RNNs |
Authors | Rose Yu, Stephan Zheng, Anima Anandkumar, Yisong Yue |
Abstract | We present Tensor-Train RNN (TT-RNN), a novel family of neural sequence architectures for multivariate forecasting in environments with nonlinear dynamics. Long-term forecasting in such systems is highly challenging, since there exist long-term temporal dependencies, higher-order correlations and sensitivity to error propagation. Our proposed tensor recurrent architecture addresses these issues by learning the nonlinear dynamics directly using higher order moments and high-order state transition functions. Furthermore, we decompose the higher-order structure using the tensor-train (TT) decomposition to reduce the number of parameters while preserving the model performance. We theoretically establish the approximation properties of Tensor-Train RNNs for general sequence inputs, and such guarantees are not available for usual RNNs. We also demonstrate significant long-term prediction improvements over general RNN and LSTM architectures on a range of simulated environments with nonlinear dynamics, as well on real-world climate and traffic data. |
Tasks | |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=HJJ0w--0W |
https://openreview.net/pdf?id=HJJ0w--0W | |
PWC | https://paperswithcode.com/paper/long-term-forecasting-using-tensor-train-rnns-1 |
Repo | |
Framework | |
Improving Classification of Twitter Behavior During Hurricane Events
Title | Improving Classification of Twitter Behavior During Hurricane Events |
Authors | Kevin Stowe, Jennings Anderson, Martha Palmer, Leysia Palen, Ken Anderson |
Abstract | A large amount of social media data is generated during natural disasters, and identifying the relevant portions of this data is critical for researchers attempting to understand human behavior, the effects of information sources, and preparatory actions undertaken during these events. In order to classify human behavior during hazard events, we employ machine learning for two tasks: identifying hurricane related tweets and classifying user evacuation behavior during hurricanes. We show that feature-based and deep learning methods provide different benefits for tweet classification, and ensemble-based methods using linguistic, temporal, and geospatial features can effectively classify user behavior. |
Tasks | |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/W18-3512/ |
https://www.aclweb.org/anthology/W18-3512 | |
PWC | https://paperswithcode.com/paper/improving-classification-of-twitter-behavior |
Repo | |
Framework | |
KTH Tangrams: A Dataset for Research on Alignment and Conceptual Pacts in Task-Oriented Dialogue
Title | KTH Tangrams: A Dataset for Research on Alignment and Conceptual Pacts in Task-Oriented Dialogue |
Authors | Todd Shore, Theofronia Androulakaki, Gabriel Skantze |
Abstract | |
Tasks | |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1123/ |
https://www.aclweb.org/anthology/L18-1123 | |
PWC | https://paperswithcode.com/paper/kth-tangrams-a-dataset-for-research-on |
Repo | |
Framework | |
Towards a Variability Measure for Multiword Expressions
Title | Towards a Variability Measure for Multiword Expressions |
Authors | Caroline Pasquer, Agata Savary, Jean-Yves Antoine, Carlos Ramisch |
Abstract | One of the most outstanding properties of multiword expressions (MWEs), especially verbal ones (VMWEs), important both in theoretical models and applications, is their idiosyncratic variability. Some MWEs are always continuous, while some others admit certain types of insertions. Components of some MWEs are rarely or never modified, while some others admit either specific or unrestricted modification. This unpredictable variability profile of MWEs hinders modeling and processing them as {``}words-with-spaces{''} on the one hand, and as regular syntactic structures on the other hand. Since variability of MWEs is a matter of scale rather than a binary property, we propose a 2-dimensional language-independent measure of variability dedicated to verbal MWEs based on syntactic and discontinuity-related clues. We assess its relevance with respect to a linguistic benchmark and its utility for the tasks of VMWE classification and variant identification on a French corpus. | |
Tasks | |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/N18-2068/ |
https://www.aclweb.org/anthology/N18-2068 | |
PWC | https://paperswithcode.com/paper/towards-a-variability-measure-for-multiword |
Repo | |
Framework | |
Dense Decoder Shortcut Connections for Single-Pass Semantic Segmentation
Title | Dense Decoder Shortcut Connections for Single-Pass Semantic Segmentation |
Authors | Piotr Bilinski, Victor Prisacariu |
Abstract | We propose a novel end-to-end trainable, deep, encoder-decoder architecture for single-pass semantic segmentation. Our approach is based on a cascaded architecture with feature-level long-range skip connections. The encoder incorporates the structure of ResNeXt’s residual building blocks and adopts the strategy of repeating a building block that aggregates a set of transformations with the same topology. The decoder features a novel architecture, consisting of blocks, that (i) capture context information, (ii) generate semantic features, and (iii) enable fusion between different output resolutions. Crucially, we introduce dense decoder shortcut connections to allow decoder blocks to use semantic feature maps from all previous decoder levels, i.e. from all higher-level feature maps. The dense decoder connections allow for effective information propagation from one decoder block to another, as well as for multi-level feature fusion that significantly improves the accuracy. Importantly, these connections allow our method to obtain state-of-the-art performance on several challenging datasets, without the need of time-consuming multi-scale averaging of previous works. |
Tasks | Semantic Segmentation |
Published | 2018-06-01 |
URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Bilinski_Dense_Decoder_Shortcut_CVPR_2018_paper.html |
http://openaccess.thecvf.com/content_cvpr_2018/papers/Bilinski_Dense_Decoder_Shortcut_CVPR_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/dense-decoder-shortcut-connections-for-single |
Repo | |
Framework | |