Paper Group NANR 226
Neural Poetry Translation. Emotional Attention: A Study of Image Sentiment and Visual Attention. A Simple Fully Connected Network for Composing Word Embeddings from Characters. Underspecified Universal Dependency Structures as Inputs for Multilingual Surface Realisation. A Unified Framework for Extensive-Form Game Abstraction with Bounds. Exploring …
Neural Poetry Translation
| Title | Neural Poetry Translation |
| Authors | Marjan Ghazvininejad, Yejin Choi, Kevin Knight |
| Abstract | We present the first neural poetry translation system. Unlike previous works that often fail to produce any translation for fixed rhyme and rhythm patterns, our system always translates a source text to an English poem. Human evaluation of the translations ranks the quality as acceptable 78.2{%} of the time. |
| Tasks | Machine Translation |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-2011/ |
| https://www.aclweb.org/anthology/N18-2011 | |
| PWC | https://paperswithcode.com/paper/neural-poetry-translation |
| Repo | |
| Framework | |
Emotional Attention: A Study of Image Sentiment and Visual Attention
| Title | Emotional Attention: A Study of Image Sentiment and Visual Attention |
| Authors | Shaojing Fan, Zhiqi Shen, Ming Jiang, Bryan L. Koenig, Juan Xu, Mohan S. Kankanhalli, Qi Zhao |
| Abstract | Image sentiment influences visual perception. Emotion-eliciting stimuli such as happy faces and poisonous snakes are generally prioritized in human attention. However, little research has evaluated the interrelationships of image sentiment and visual saliency. In this paper, we present the first study to focus on the relation between emotional properties of an image and visual attention. We first create the EMOtional attention dataset (EMOd). It is a diverse set of emotion-eliciting images, and each image has (1) eye-tracking data collected from 16 subjects, (2) intensive image context labels including object contour, object sentiment, object semantic category, and high-level perceptual attributes such as image aesthetics and elicited emotions. We perform extensive analyses on EMOd to identify how image sentiment relates to human attention. We discover an emotion prioritization effect: for our images, emotion-eliciting content attracts human attention strongly, but such advantage diminishes dramatically after initial fixation. Aiming to model the human emotion prioritization computationally, we design a deep neural network for saliency prediction, which includes a novel subnetwork that learns the spatial and semantic context of the image scene. The proposed network outperforms the state-of-the-art on three benchmark datasets, by effectively capturing the relative importance of human attention within an image. The code, models, and dataset are available online at https://nus-sesame.top/emotionalattention/. |
| Tasks | Eye Tracking, Saliency Prediction |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Fan_Emotional_Attention_A_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Fan_Emotional_Attention_A_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/emotional-attention-a-study-of-image |
| Repo | |
| Framework | |
A Simple Fully Connected Network for Composing Word Embeddings from Characters
| Title | A Simple Fully Connected Network for Composing Word Embeddings from Characters |
| Authors | Michael Traynor, Thomas Trappenberg |
| Abstract | This work introduces a simple network for producing character aware word embeddings. Position agnostic and position aware character embeddings are combined to produce an embedding vector for each word. The learned word representations are shown to be very sparse and facilitate improved results on language modeling tasks, despite using markedly fewer parameters, and without the need to apply dropout. A final experiment suggests that weight sharing contributes to sparsity, increases performance, and prevents overfitting. |
| Tasks | Language Modelling, Word Embeddings |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=rJ8rHkWRb |
| https://openreview.net/pdf?id=rJ8rHkWRb | |
| PWC | https://paperswithcode.com/paper/a-simple-fully-connected-network-for |
| Repo | |
| Framework | |
Underspecified Universal Dependency Structures as Inputs for Multilingual Surface Realisation
| Title | Underspecified Universal Dependency Structures as Inputs for Multilingual Surface Realisation |
| Authors | Simon Mille, Anja Belz, Bernd Bohnet, Leo Wanner |
| Abstract | In this paper, we present the datasets used in the Shallow and Deep Tracks of the First Multilingual Surface Realisation Shared Task (SR{'}18). For the Shallow Track, data in ten languages has been released: Arabic, Czech, Dutch, English, Finnish, French, Italian, Portuguese, Russian and Spanish. For the Deep Track, data in three languages is made available: English, French and Spanish. We describe in detail how the datasets were derived from the Universal Dependencies V2.0, and report on an evaluation of the Deep Track input quality. In addition, we examine the motivation for, and likely usefulness of, deriving NLG inputs from annotations in resources originally developed for Natural Language Understanding (NLU), and assess whether the resulting inputs supply enough information of the right kind for the final stage in the NLG process. |
| Tasks | Text Generation |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6527/ |
| https://www.aclweb.org/anthology/W18-6527 | |
| PWC | https://paperswithcode.com/paper/underspecified-universal-dependency |
| Repo | |
| Framework | |
A Unified Framework for Extensive-Form Game Abstraction with Bounds
| Title | A Unified Framework for Extensive-Form Game Abstraction with Bounds |
| Authors | Christian Kroer, Tuomas Sandholm |
| Abstract | Abstraction has long been a key component in the practical solving of large-scale extensive-form games. Despite this, abstraction remains poorly understood. There have been some recent theoretical results but they have been confined to specific assumptions on abstraction structure and are specific to various disjoint types of abstraction, and specific solution concepts, for example, exact Nash equilibria or strategies with bounded immediate regret. In this paper we present a unified framework for analyzing abstractions that can express all types of abstractions and solution concepts used in prior papers with performance guarantees—while maintaining comparable bounds on abstraction quality. Moreover, our framework gives an exact decomposition of abstraction error in a much broader class of games, albeit only in an ex-post sense, as our results depend on the specific strategy chosen. Nonetheless, we use this ex-post decomposition along with slightly weaker assumptions than prior work to derive generalizations of prior bounds on abstraction quality. We also show, via counterexample, that such assumptions are necessary for some games. Finally, we prove the first bounds for how $\epsilon$-Nash equilibria computed in abstractions perform in the original game. This is important because often one cannot afford to compute an exact Nash equilibrium in the abstraction. All our results apply to general-sum n-player games. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7342-a-unified-framework-for-extensive-form-game-abstraction-with-bounds |
| http://papers.nips.cc/paper/7342-a-unified-framework-for-extensive-form-game-abstraction-with-bounds.pdf | |
| PWC | https://paperswithcode.com/paper/a-unified-framework-for-extensive-form-game |
| Repo | |
| Framework | |
Exploring Optimism and Pessimism in Twitter Using Deep Learning
| Title | Exploring Optimism and Pessimism in Twitter Using Deep Learning |
| Authors | Cornelia Caragea, Liviu P. Dinu, Bogdan Dumitru |
| Abstract | Identifying optimistic and pessimistic viewpoints and users from Twitter is useful for providing better social support to those who need such support, and for minimizing the negative influence among users and maximizing the spread of positive attitudes and ideas. In this paper, we explore a range of deep learning models to predict optimism and pessimism in Twitter at both tweet and user level and show that these models substantially outperform traditional machine learning classifiers used in prior work. In addition, we show evidence that a sentiment classifier would not be sufficient for accurately predicting optimism and pessimism in Twitter. Last, we study the verb tense usage as well as the presence of polarity words in optimistic and pessimistic tweets. |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1067/ |
| https://www.aclweb.org/anthology/D18-1067 | |
| PWC | https://paperswithcode.com/paper/exploring-optimism-and-pessimism-in-twitter |
| Repo | |
| Framework | |
CLARIN’s Key Resource Families
| Title | CLARIN’s Key Resource Families |
| Authors | Darja Fi{\v{s}}er, Jakob Lenardi{\v{c}}, Toma{\v{z}} Erjavec |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1210/ |
| https://www.aclweb.org/anthology/L18-1210 | |
| PWC | https://paperswithcode.com/paper/clarinas-key-resource-families |
| Repo | |
| Framework | |
AI-Enhanced 3D RF Representation Using Low-Cost mmWave Radar
| Title | AI-Enhanced 3D RF Representation Using Low-Cost mmWave Radar |
| Authors | Shiwei Fang, Shahriar Nirjon |
| Abstract | This paper introduces a system that takes radio frequency (RF) signals from an off-the-shelf, low-cost, 77 GHz mm Wave radar and produces an enhanced 3D RF representation of a scene. Such a system can be used in scenarios where camera and other types of sensors do not work, or their performance is impacted due to bad lighting conditions and occlusions, or an alternate RF sensing system like synthetic aperture radar (SAR) is too large, inconvenient, and costly. The enhanced RF representation can be used in numerous applications such as robot navigation, human-computer interaction, and patient monitoring. We use off-the-shelf parts to capture RF signals and collect our own data set for training and testing of the approach. The novelty of the system lies in its use of AI to generate a fine-grained 3D representation of an RF scene from its sparse RF representation which a mm Wave radar of the same class cannot achieve. |
| Tasks | RF-based Pose Estimation, Robot Navigation |
| Published | 2018-11-04 |
| URL | https://doi.org/10.1145/3274783.3275210 |
| https://www.semanticscholar.org/paper/AI-Enhanced-3D-RF-Representation-Using-Low-Cost-Fang-Nirjon/36075af2129b590dfa128f5de5a159395952549e | |
| PWC | https://paperswithcode.com/paper/ai-enhanced-3d-rf-representation-using-low |
| Repo | |
| Framework | |
Memory, Show the Way: Memory Based Few Shot Word Representation Learning
| Title | Memory, Show the Way: Memory Based Few Shot Word Representation Learning |
| Authors | Jingyuan Sun, Shaonan Wang, Chengqing Zong |
| Abstract | Distributional semantic models (DSMs) generally require sufficient examples for a word to learn a high quality representation. This is in stark contrast with human who can guess the meaning of a word from one or a few referents only. In this paper, we propose Mem2Vec, a memory based embedding learning method capable of acquiring high quality word representations from fairly limited context. Our method directly adapts the representations produced by a DSM with a longterm memory to guide its guess of a novel word. Based on a pre-trained embedding space, the proposed method delivers impressive performance on two challenging few-shot word similarity tasks. Embeddings learned with our method also lead to considerable improvements over strong baselines on NER and sentiment classification. |
| Tasks | Representation Learning, Sentiment Analysis |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1173/ |
| https://www.aclweb.org/anthology/D18-1173 | |
| PWC | https://paperswithcode.com/paper/memory-show-the-way-memory-based-few-shot |
| Repo | |
| Framework | |
Image forgery detection for high resolution images using SIFT and RANSAC algorithm
| Title | Image forgery detection for high resolution images using SIFT and RANSAC algorithm |
| Authors | S.B.G. Tilak Babu, Ch. Srinivasa Rao |
| Abstract | Cloning (copy-move forgery) is a malicious tampering attack with digital images where a part of image is copied and pasted within the image to conceal the important details of image without any obvious traces of manipulation. This type of tampering attacks leaves a big question of authenticity of images to the forensics. Many techniques are proposed in the past few years after powerful software’s are developed to manipulate the image. The proposed scheme is involved with both the block based and feature point extraction based techniques to extract the forged regions more accurately. The proposed algorithm mainly involves in matching the tentacles of same features extracted from each block by computing the dot product between the unit vectors. Random Sample Consensus (RANSAC) algorithm is used to extract the matched regions. The experimental result of the algorithm which is proposed indicates that, it can extract more accurate results compared with existing forgery detection methods. |
| Tasks | |
| Published | 2018-03-22 |
| URL | https://ieeexplore.ieee.org/document/8321205 |
| https://www.researchgate.net/publication/323952930_Image_forgery_detection_for_high_resolution_images_using_SIFT_and_RANSAC_algorithm | |
| PWC | https://paperswithcode.com/paper/image-forgery-detection-for-high-resolution |
| Repo | |
| Framework | |
Language Model Based Grammatical Error Correction without Annotated Training Data
| Title | Language Model Based Grammatical Error Correction without Annotated Training Data |
| Authors | Christopher Bryant, Ted Briscoe |
| Abstract | Since the end of the CoNLL-2014 shared task on grammatical error correction (GEC), research into language model (LM) based approaches to GEC has largely stagnated. In this paper, we re-examine LMs in GEC and show that it is entirely possible to build a simple system that not only requires minimal annotated data (∼1000 sentences), but is also fairly competitive with several state-of-the-art systems. This approach should be of particular interest for languages where very little annotated training data exists, although we also hope to use it as a baseline to motivate future research. |
| Tasks | Grammatical Error Correction, Language Modelling, Machine Translation |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0529/ |
| https://www.aclweb.org/anthology/W18-0529 | |
| PWC | https://paperswithcode.com/paper/language-model-based-grammatical-error |
| Repo | |
| Framework | |
Dependent Bidirectional RNN with Extended-long Short-term Memory
| Title | Dependent Bidirectional RNN with Extended-long Short-term Memory |
| Authors | Yuanhang Su, Yuzhong Huang, C.-C. Jay Kuo |
| Abstract | In this work, we first conduct mathematical analysis on the memory, which is defined as a function that maps an element in a sequence to the current output, of three RNN cells; namely, the simple recurrent neural network (SRN), the long short-term memory (LSTM) and the gated recurrent unit (GRU). Based on the analysis, we propose a new design, called the extended-long short-term memory (ELSTM), to extend the memory length of a cell. Next, we present a multi-task RNN model that is robust to previous erroneous predictions, called the dependent bidirectional recurrent neural network (DBRNN), for the sequence-in-sequenceout (SISO) problem. Finally, the performance of the DBRNN model with the ELSTM cell is demonstrated by experimental results. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=r1AMITFaW |
| https://openreview.net/pdf?id=r1AMITFaW | |
| PWC | https://paperswithcode.com/paper/dependent-bidirectional-rnn-with-extended |
| Repo | |
| Framework | |
Dynamic Conditional Networks for Few-Shot Learning
| Title | Dynamic Conditional Networks for Few-Shot Learning |
| Authors | Fang Zhao, Jian Zhao, Shuicheng Yan, Jiashi Feng |
| Abstract | This paper proposes a novel Dynamic Conditional Convolutional Network (DCCN) to handle conditional few-shot learning, i.e, only a few training samples are available for each condition. DCCN consists of dual subnets: DyConvNet contains a dynamic convolutional layer with a bank of basis filters; CondiNet predicts a set of adaptive weights from conditional inputs to linearly combine the basis filters. In this manner, a specific convolutional kernel can be dynamically obtained for each conditional input. The filter bank is shared between all conditions thus only a low-dimension weight vector needs to be learned. This significantly facilitates the parameter learning across different conditions when training data are limited. We evaluate DCCN on four tasks which can be formulated as conditional model learning, including specific object counting, multi-modal image classification, phrase grounding and identity based face generation. Extensive experiments demonstrate the superiority of the proposed model in the conditional few-shot learning setting. |
| Tasks | Face Generation, Few-Shot Learning, Image Classification, Object Counting, Phrase Grounding |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Fang_Zhao_Dynamic_Conditional_Networks_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Fang_Zhao_Dynamic_Conditional_Networks_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-conditional-networks-for-few-shot |
| Repo | |
| Framework | |
SimLex-999 for Polish
| Title | SimLex-999 for Polish |
| Authors | Agnieszka Mykowiecka, Ma{\l}gorzata Marciniak, Piotr Rychlik |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1381/ |
| https://www.aclweb.org/anthology/L18-1381 | |
| PWC | https://paperswithcode.com/paper/simlex-999-for-polish |
| Repo | |
| Framework | |
MiCT: Mixed 3D/2D Convolutional Tube for Human Action Recognition
| Title | MiCT: Mixed 3D/2D Convolutional Tube for Human Action Recognition |
| Authors | Yizhou Zhou, Xiaoyan Sun, Zheng-Jun Zha, Wenjun Zeng |
| Abstract | Human actions in videos are three-dimensional (3D) signals. Recent attempts use 3D convolutional neural networks (CNNs) to explore spatio-temporal information for human action recognition. Though promising, 3D CNNs have not achieved high performanceon on this task with respect to their well-established two-dimensional (2D) counterparts for visual recognition in still images. We argue that the high training complexity of spatio-temporal fusion and the huge memory cost of 3D convolution hinder current 3D CNNs, which stack 3D convolutions layer by layer, by outputting deeper feature maps that are crucial for high-level tasks. We thus propose a Mixed Convolutional Tube (MiCT) that integrates 2D CNNs with the 3D convolution module to generate deeper and more informative feature maps, while reducing training complexity in each round of spatio-temporal fusion. A new end-to-end trainable deep 3D network, MiCT-Net, is also proposed based on the MiCT to better explore spatio-temporal information in human actions. Evaluations on three well-known benchmark datasets (UCF101, Sport-1M and HMDB-51) show that the proposed MiCT-Net significantly outperforms the original 3D CNNs. Compared with state-of-the-art approaches for action recognition on UCF101 and HMDB51, our MiCT-Net yields the best performance. |
| Tasks | Temporal Action Localization |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Zhou_MiCT_Mixed_3D2D_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhou_MiCT_Mixed_3D2D_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/mict-mixed-3d2d-convolutional-tube-for-human |
| Repo | |
| Framework | |
