Paper Group NANR 124
Introducing NIEUW: Novel Incentives and Workflows for Eliciting Linguistic Data. Categorizing Concepts With Basic Level for Vision-to-Language. HashGAN: Deep Learning to Hash With Pair Conditional Wasserstein GAN. The Price of Privacy for Low-rank Factorization. A Method for Human-Interpretable Paraphrasticality Prediction. Interoperable Annotation …
Introducing NIEUW: Novel Incentives and Workflows for Eliciting Linguistic Data
Title | Introducing NIEUW: Novel Incentives and Workflows for Eliciting Linguistic Data |
Authors | Christopher Cieri, James Fiumara, Mark Liberman, Chris Callison-Burch, Jonathan Wright |
Abstract | |
Tasks | |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1024/ |
https://www.aclweb.org/anthology/L18-1024 | |
PWC | https://paperswithcode.com/paper/introducing-nieuw-novel-incentives-and |
Repo | |
Framework | |
Categorizing Concepts With Basic Level for Vision-to-Language
Title | Categorizing Concepts With Basic Level for Vision-to-Language |
Authors | Hanzhang Wang, Hanli Wang, Kaisheng Xu |
Abstract | Vision-to-language tasks require a unified semantic understanding of visual content. However, the information contained in image/video is essentially ambiguous on two perspectives manifested on the diverse understanding among different persons and the various understanding grains even for the same person. Inspired by the basic level in early cognition, a Basic Concept (BaC) category is proposed in this work that contains both consensus and proper level of visual content to help neural network tackle the above problems. Specifically, a salient concept category is firstly generated by intersecting the labels of ImageNet and the vocabulary of MSCOCO dataset. Then, according to the observation from human early cognition that children make fewer mistakes on the basic level, the salient category is further refined by clustering concepts with a defined confusion degree which measures the difficulty for convolutional neural network to distinguish class pairs. Finally, a pre-trained model based on GoogLeNet is produced with the proposed BaC category of 1,372 concept classes. To verify the effectiveness of the proposed categorizing method for vision-to-language tasks, two kinds of experiments are performed including image captioning and visual question answering with the benchmark datasets of MSCOCO, Flickr30k and COCO-QA. The experimental results demonstrate that the representations derived from the cognition-inspired BaC category promote representation learning of neural networks on vision-to-language tasks, and a performance improvement is gained without modifying standard models. |
Tasks | Image Captioning, Question Answering, Representation Learning, Visual Question Answering |
Published | 2018-06-01 |
URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Wang_Categorizing_Concepts_With_CVPR_2018_paper.html |
http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Categorizing_Concepts_With_CVPR_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/categorizing-concepts-with-basic-level-for |
Repo | |
Framework | |
HashGAN: Deep Learning to Hash With Pair Conditional Wasserstein GAN
Title | HashGAN: Deep Learning to Hash With Pair Conditional Wasserstein GAN |
Authors | Yue Cao, Bin Liu, Mingsheng Long, Jianmin Wang |
Abstract | Deep learning to hash improves image retrieval performance by end-to-end representation learning and hash coding from training data with pairwise similarity information. Subject to the scarcity of similarity information that is often expensive to collect for many application domains, existing deep learning to hash methods may overfit the training data and result in substantial loss of retrieval quality. This paper presents HashGAN, a novel architecture for deep learning to hash, which learns compact binary hash codes from both real images and diverse images synthesized by generative models. The main idea is to augment the training data with nearly real images synthesized from a new Pair Conditional Wasserstein GAN (PC-WGAN) conditioned on the pairwise similarity information. Extensive experiments demonstrate that HashGAN can generate high-quality binary hash codes and yield state-of-the-art image retrieval performance on three benchmarks, NUS-WIDE, CIFAR-10, and MS-COCO. |
Tasks | Image Retrieval, Representation Learning |
Published | 2018-06-01 |
URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Cao_HashGAN_Deep_Learning_CVPR_2018_paper.html |
http://openaccess.thecvf.com/content_cvpr_2018/papers/Cao_HashGAN_Deep_Learning_CVPR_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/hashgan-deep-learning-to-hash-with-pair |
Repo | |
Framework | |
The Price of Privacy for Low-rank Factorization
Title | The Price of Privacy for Low-rank Factorization |
Authors | Jalaj Upadhyay |
Abstract | In this paper, we study what price one has to pay to release \emph{differentially private low-rank factorization} of a matrix. We consider various settings that are close to the real world applications of low-rank factorization: (i) the manner in which matrices are updated (row by row or in an arbitrary manner), (ii) whether matrices are distributed or not, and (iii) how the output is produced (once at the end of all updates, also known as \emph{one-shot algorithms} or continually). Even though these settings are well studied without privacy, surprisingly, there are no private algorithm for these settings (except when a matrix is updated row by row). We present the first set of differentially private algorithms for all these settings. Our algorithms when private matrix is updated in an arbitrary manner promise differential privacy with respect to two stronger privacy guarantees than previously studied, use space and time \emph{comparable} to the non-private algorithm, and achieve \emph{optimal accuracy}. To complement our positive results, we also prove that the space required by our algorithms is optimal up to logarithmic factors. When data matrices are distributed over multiple servers, we give a non-interactive differentially private algorithm with communication cost independent of dimension. In concise, we give algorithms that incur {\em optimal cost across all parameters of interest}. We also perform experiments to verify that all our algorithms perform well in practice and outperform the best known algorithm until now for large range of parameters. |
Tasks | |
Published | 2018-12-01 |
URL | http://papers.nips.cc/paper/7672-the-price-of-privacy-for-low-rank-factorization |
http://papers.nips.cc/paper/7672-the-price-of-privacy-for-low-rank-factorization.pdf | |
PWC | https://paperswithcode.com/paper/the-price-of-privacy-for-low-rank |
Repo | |
Framework | |
A Method for Human-Interpretable Paraphrasticality Prediction
Title | A Method for Human-Interpretable Paraphrasticality Prediction |
Authors | Maria Moritz, Johannes Hellrich, Sven B{"u}chel |
Abstract | The detection of reused text is important in a wide range of disciplines. However, even as research in the field of plagiarism detection is constantly improving, heavily modified or paraphrased text is still challenging for current methodologies. For historical texts, these problems are even more severe, since text sources were often subject to stronger and more frequent modifications. Despite the need for tools to automate text criticism, e.g., tracing modifications in historical text, algorithmic support is still limited. While current techniques can tell if and how frequently a text has been modified, very little work has been done on determining the degree and kind of paraphrastic modification{—}despite such information being of substantial interest to scholars. We present a human-interpretable, feature-based method to measure paraphrastic modification. Evaluating our technique on three data sets, we find that our approach performs competitive to text similarity scores borrowed from machine translation evaluation, being much harder to interpret. |
Tasks | Machine Translation |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/W18-4513/ |
https://www.aclweb.org/anthology/W18-4513 | |
PWC | https://paperswithcode.com/paper/a-method-for-human-interpretable |
Repo | |
Framework | |
Interoperable Annotation of Events and Event Relations across Domains
Title | Interoperable Annotation of Events and Event Relations across Domains |
Authors | Jun Araki, Lamana Mulaffer, P, Arun ian, Yukari Yamakawa, Kemal Oflazer, Teruko Mitamura |
Abstract | |
Tasks | |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/W18-4702/ |
https://www.aclweb.org/anthology/W18-4702 | |
PWC | https://paperswithcode.com/paper/interoperable-annotation-of-events-and-event |
Repo | |
Framework | |
Monocular Depth Estimation with Affinity, Vertical Pooling, and Label Enhancement
Title | Monocular Depth Estimation with Affinity, Vertical Pooling, and Label Enhancement |
Authors | Yukang Gan, Xiangyu Xu, Wenxiu Sun, Liang Lin |
Abstract | While significant progress has been made in monocular depth estimation with Convolutional Neural Networks (CNNs) extracting absolute features, such as edges and textures, the depth constraint of neighboring pixels, namely relative features, has been mostly ignored by recent methods. To overcome this limitation, we explicitly model the relationships of different image locations with an affinity layer and combine absolute and relative features in an end-to-end network. In addition, we also consider another prior knowledge that major depth changes in images lie in the vertical direction, and thus, it is beneficial to capture local vertical features for refined depth estimation. In the proposed algorithm we introduce vertical pooling to aggregate image features vertically to improve the depth accuracy.Furthermore, since the Lidar depth ground truth is quite sparse, we enhance the depth labels by generating high-quality dense depth maps with off-the-shelf stereo matching method which takes left-right image pairs as input.We also integrate multi-scale structures in our network to obtain global understanding the image depth and exploit residual learning to help depth refinement.We demonstrate that the proposed algorithm performs favorably against state-of-the-art methods both qualitatively and quantitatively on the KITTI driving dataset. |
Tasks | Depth Estimation, Monocular Depth Estimation, Stereo Matching, Stereo Matching Hand |
Published | 2018-09-01 |
URL | http://openaccess.thecvf.com/content_ECCV_2018/html/YuKang_Gan_Monocular_Depth_Estimation_ECCV_2018_paper.html |
http://openaccess.thecvf.com/content_ECCV_2018/papers/YuKang_Gan_Monocular_Depth_Estimation_ECCV_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/monocular-depth-estimation-with-affinity |
Repo | |
Framework | |
Beyond 1/2-Approximation for Submodular Maximization on Massive Data Streams
Title | Beyond 1/2-Approximation for Submodular Maximization on Massive Data Streams |
Authors | Ashkan Norouzi-Fard, Jakub Tarnawski, Slobodan Mitrovic, Amir Zandieh, Aidasadat Mousavifar, Ola Svensson |
Abstract | Many tasks in machine learning and data mining, such as data diversification, non-parametric learning, kernel machines, clustering etc., require extracting a small but representative summary from a massive dataset. Often, such problems can be posed as maximizing a submodular set function subject to a cardinality constraint. We consider this question in the streaming setting, where elements arrive over time at a fast pace and thus we need to design an efficient, low-memory algorithm. One such method, proposed by Badanidiyuru et al. (2014), always finds a 0.5-approximate solution. Can this approximation factor be improved? We answer this question affirmatively by designing a new algorithm Salsa for streaming submodular maximization. It is the first low-memory, singlepass algorithm that improves the factor 0.5, under the natural assumption that elements arrive in a random order. We also show that this assumption is necessary, i.e., that there is no such algorithm with better than 0.5-approximation when elements arrive in arbitrary order. Our experiments demonstrate that Salsa significantly outperforms the state of the art in applications related to exemplar-based clustering, social graph analysis, and recommender systems. |
Tasks | Recommendation Systems |
Published | 2018-07-01 |
URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2040 |
http://proceedings.mlr.press/v80/norouzi-fard18a/norouzi-fard18a.pdf | |
PWC | https://paperswithcode.com/paper/beyond-12-approximation-for-submodular-1 |
Repo | |
Framework | |
PizzaPal: Conversational Pizza Ordering using a High-Density Conversational AI Platform
Title | PizzaPal: Conversational Pizza Ordering using a High-Density Conversational AI Platform |
Authors | Antoine Raux, Yi Ma, Paul Yang, Felicia Wong |
Abstract | This paper describes PizzaPal, a voice-only agent for ordering pizza, as well as the Conversational AI architecture built at b4.ai. Based on the principles of high-density conversational AI, it supports natural and flexible interactions through neural conversational language understanding, robust dialog state tracking, and hierarchical task decomposition. |
Tasks | Speech Recognition |
Published | 2018-11-01 |
URL | https://www.aclweb.org/anthology/D18-2026/ |
https://www.aclweb.org/anthology/D18-2026 | |
PWC | https://paperswithcode.com/paper/pizzapal-conversational-pizza-ordering-using |
Repo | |
Framework | |
Predicting Human Metaphor Paraphrase Judgments with Deep Neural Networks
Title | Predicting Human Metaphor Paraphrase Judgments with Deep Neural Networks |
Authors | Yuri Bizzoni, Shalom Lappin |
Abstract | We propose a new annotated corpus for metaphor interpretation by paraphrase, and a novel DNN model for performing this task. Our corpus consists of 200 sets of 5 sentences, with each set containing one reference metaphorical sentence, and four ranked candidate paraphrases. Our model is trained for a binary classification of paraphrase candidates, and then used to predict graded paraphrase acceptability. It reaches an encouraging 75{%} accuracy on the binary classification task, and high Pearson (.75) and Spearman (.68) correlations on the gradient judgment prediction task. |
Tasks | Natural Language Inference, Semantic Textual Similarity |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/W18-0906/ |
https://www.aclweb.org/anthology/W18-0906 | |
PWC | https://paperswithcode.com/paper/predicting-human-metaphor-paraphrase |
Repo | |
Framework | |
Stance Detection with Hierarchical Attention Network
Title | Stance Detection with Hierarchical Attention Network |
Authors | Qingying Sun, Zhongqing Wang, Qiaoming Zhu, Guodong Zhou |
Abstract | Stance detection aims to assign a stance label (for or against) to a post toward a specific target. Recently, there is a growing interest in using neural models to detect stance of documents. Most of these works model the sequence of words to learn document representation. However, much linguistic information, such as polarity and arguments of the document, is correlated with the stance of the document, and can inspire us to explore the stance. Hence, we present a neural model to fully employ various linguistic information to construct the document representation. In addition, since the influences of different linguistic information are different, we propose a hierarchical attention network to weigh the importance of various linguistic information, and learn the mutual attention between the document and the linguistic information. The experimental results on two datasets demonstrate the effectiveness of the proposed hierarchical attention neural model. |
Tasks | Feature Engineering, Opinion Mining, Stance Detection |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/C18-1203/ |
https://www.aclweb.org/anthology/C18-1203 | |
PWC | https://paperswithcode.com/paper/stance-detection-with-hierarchical-attention |
Repo | |
Framework | |
Lexical Conceptual Structure of Literal and Metaphorical Spatial Language: A Case Study of ``Push’’
Title | Lexical Conceptual Structure of Literal and Metaphorical Spatial Language: A Case Study of ``Push’’ | |
Authors | Bonnie Dorr, Mari Olsen |
Abstract | Prior methodologies for understanding spatial language have treated literal expressions such as {}Mary pushed the car over the edge{''} differently from metaphorical extensions such as { }Mary{'}s job pushed her over the edge{''}. We demonstrate a methodology for standardizing literal and metaphorical meanings, by building on work in Lexical Conceptual Structure (LCS), a general-purpose representational component used in machine translation. We argue that spatial predicates naturally extend into other fields (e.g., circumstantial or temporal), and that LCS provides both a framework for distinguishing spatial from non-spatial, and a system for finding metaphorical meaning extensions. We start with MetaNet (MN), a large repository of conceptual metaphors, condensing 197 spatial entries into sixteen top-level categories of motion frames. Using naturally occurring instances of English push , and expansions of MN frames, we demonstrate that literal and metaphorical extensions exhibit patterns predicted and represented by the LCS model. |
Tasks | Machine Translation, Visual Reasoning |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/W18-1404/ |
https://www.aclweb.org/anthology/W18-1404 | |
PWC | https://paperswithcode.com/paper/lexical-conceptual-structure-of-literal-and |
Repo | |
Framework | |
Representing Spatial Relations in FrameNet
Title | Representing Spatial Relations in FrameNet |
Authors | Miriam R. L. Petruck, Michael J. Ellsworth |
Abstract | While humans use natural language to express spatial relations between and across entities in the world with great facility, natural language systems have a facility that depends on that human facility. This position paper presents approach to representing spatial relations in language, and advocates its adoption for representing the meaning of spatial language. This work shows the importance of axis-orientation systems for capturing the complexity of spatial relations, which FrameNet encodes with semantic types. |
Tasks | |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/W18-1405/ |
https://www.aclweb.org/anthology/W18-1405 | |
PWC | https://paperswithcode.com/paper/representing-spatial-relations-in-framenet |
Repo | |
Framework | |
SemEval-2018 Task 7: Semantic Relation Extraction and Classification in Scientific Papers
Title | SemEval-2018 Task 7: Semantic Relation Extraction and Classification in Scientific Papers |
Authors | Kata G{'a}bor, Davide Buscaldi, Anne-Kathrin Schumann, Behrang QasemiZadeh, Ha{"\i}fa Zargayouna, Thierry Charnois |
Abstract | This paper describes the first task on semantic relation extraction and classification in scientific paper abstracts at SemEval 2018. The challenge focuses on domain-specific semantic relations and includes three different subtasks. The subtasks were designed so as to compare and quantify the effect of different pre-processing steps on the relation classification results. We expect the task to be relevant for a broad range of researchers working on extracting specialized knowledge from domain corpora, for example but not limited to scientific or bio-medical information extraction. The task attracted a total of 32 participants, with 158 submissions across different scenarios. |
Tasks | Keyword Extraction, Relation Classification, Relation Extraction |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/S18-1111/ |
https://www.aclweb.org/anthology/S18-1111 | |
PWC | https://paperswithcode.com/paper/semeval-2018-task-7-semantic-relation |
Repo | |
Framework | |
Proceedings of the Australasian Language Technology Association Workshop 2018
Title | Proceedings of the Australasian Language Technology Association Workshop 2018 |
Authors | |
Abstract | |
Tasks | |
Published | 2018-12-01 |
URL | https://www.aclweb.org/anthology/U18-1000/ |
https://www.aclweb.org/anthology/U18-1000 | |
PWC | https://paperswithcode.com/paper/proceedings-of-the-australasian-language-1 |
Repo | |
Framework | |