Paper Group NANR 244
Prediction of a Movie’s Success From Plot Summaries Using Deep Learning Models. DynTypo: Example-Based Dynamic Text Effects Transfer. Neural Attribution for Semantic Bug-Localization in Student Programs. Ambiguity in Explicit Discourse Connectives. Balanced Self-Paced Learning for Generative Adversarial Clustering Network. A compositional view of q …
Prediction of a Movie’s Success From Plot Summaries Using Deep Learning Models
| Title | Prediction of a Movie’s Success From Plot Summaries Using Deep Learning Models |
| Authors | You Jin Kim, Yun Gyung Cheong, Jung Hoon Lee |
| Abstract | As the size of investment for movie production grows bigger, the need for predicting a movie{'}s success in early stages has increased. To address this need, various approaches have been proposed, mostly relying on movie reviews, trailer movie clips, and SNS postings. However, all of these are available only after a movie is produced and released. To enable a more earlier prediction of a movie{'}s performance, we propose a deep-learning based approach to predict the success of a movie using only its plot summary text. This paper reports the results evaluating the efficacy of the proposed method and concludes with discussions and future work. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3414/ |
| https://www.aclweb.org/anthology/W19-3414 | |
| PWC | https://paperswithcode.com/paper/prediction-of-a-movies-success-from-plot |
| Repo | |
| Framework | |
DynTypo: Example-Based Dynamic Text Effects Transfer
| Title | DynTypo: Example-Based Dynamic Text Effects Transfer |
| Authors | Yifang Men, Zhouhui Lian, Yingmin Tang, Jianguo Xiao |
| Abstract | In this paper, we present a novel approach for dynamic text effects transfer by using example-based texture synthesis. In contrast to previous works that require an input video of the target to provide motion guidance, we aim to animate a still image of the target text by transferring the desired dynamic effects from an observed exemplar. Due to the simplicity of target guidance and complexity of realistic effects, it is prone to producing temporal artifacts such as flickers and pulsations. To address the problem, our core idea is to find a common Nearest-neighbor Field (NNF) that would optimize the textural coherence across all keyframes simultaneously. With the static NNF for video sequences, we implicitly transfer motion properties from source to target. We also introduce a guided NNF search by employing the distance-based weight map and Simulated Annealing (SA) for deep direction-guided propagation to allow intense dynamic effects to be completely transferred with no semantic guidance provided. Experimental results demonstrate the effectiveness and superiority of our method in dynamic text effects transfer through extensive comparisons with state-of-the-art algorithms. We also show the potentiality of our method via multiple experiments for various application domains. |
| Tasks | Text Effects Transfer, Texture Synthesis |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Men_DynTypo_Example-Based_Dynamic_Text_Effects_Transfer_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Men_DynTypo_Example-Based_Dynamic_Text_Effects_Transfer_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/dyntypo-example-based-dynamic-text-effects |
| Repo | |
| Framework | |
Neural Attribution for Semantic Bug-Localization in Student Programs
| Title | Neural Attribution for Semantic Bug-Localization in Student Programs |
| Authors | Rahul Gupta, Aditya Kanade, Shirish Shevade |
| Abstract | Providing feedback is an integral part of teaching. Most open online courses on programming make use of automated grading systems to support programming assignments and give real-time feedback. These systems usually rely on test results to quantify the programs’ functional correctness. They return failing tests to the students as feedback. However, students may find it difficult to debug their programs if they receive no hints about where the bug is and how to fix it. In this work, we present NeuralBugLocator, a deep learning based technique, that can localize the bugs in a faulty program with respect to a failing test, without even running the program. At the heart of our technique is a novel tree convolutional neural network which is trained to predict whether a program passes or fails a given test. To localize the bugs, we analyze the trained network using a state-of-the-art neural prediction attribution technique and see which lines of the programs make it predict the test outcomes. Our experiments show that NeuralBugLocator is generally more accurate than two state-of-the-art program-spectrum based and one syntactic difference based bug-localization baselines. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9358-neural-attribution-for-semantic-bug-localization-in-student-programs |
| http://papers.nips.cc/paper/9358-neural-attribution-for-semantic-bug-localization-in-student-programs.pdf | |
| PWC | https://paperswithcode.com/paper/neural-attribution-for-semantic-bug |
| Repo | |
| Framework | |
Ambiguity in Explicit Discourse Connectives
| Title | Ambiguity in Explicit Discourse Connectives |
| Authors | Bonnie Webber, Rashmi Prasad, Alan Lee |
| Abstract | Discourse connectives are known to be subject to both usage and sense ambiguity, as has already been discussed in the literature. But discourse connectives are no different from other linguistic expressions in being subject to other types of ambiguity as well. Four are illustrated and discussed here. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://www.aclweb.org/anthology/W19-0411/ |
| https://www.aclweb.org/anthology/W19-0411 | |
| PWC | https://paperswithcode.com/paper/ambiguity-in-explicit-discourse-connectives |
| Repo | |
| Framework | |
Balanced Self-Paced Learning for Generative Adversarial Clustering Network
| Title | Balanced Self-Paced Learning for Generative Adversarial Clustering Network |
| Authors | Kamran Ghasedi, Xiaoqian Wang, Cheng Deng, Heng Huang |
| Abstract | Clustering is an important problem in various machine learning applications, but still a challenging task when dealing with complex real data. The existing clustering algorithms utilize either shallow models with insufficient capacity for capturing the non-linear nature of data, or deep models with large number of parameters prone to overfitting. In this paper, we propose a deep Generative Adversarial Clustering Network (ClusterGAN), which tackles the problems of training of deep clustering models in unsupervised manner. ClusterGAN consists of three networks, a discriminator, a generator and a clusterer (i.e. a clustering network). We employ an adversarial game between these three players to synthesize realistic samples given discriminative latent variables via the generator, and learn the inverse mapping of the real samples to the discriminative embedding space via the clusterer. Moreover, we utilize a conditional entropy minimization loss to increase/decrease the similarity of intra/inter cluster samples. Since the ground-truth similarities are unknown in clustering task, we propose a novel balanced self-paced learning algorithm to gradually include samples into training from easy to difficult, while considering the diversity of selected samples from all clusters. Therefore, our method makes it possible to efficiently train clusterers with large depth by leveraging the proposed adversarial game and balanced self-paced learning algorithm. According our experiments, ClusterGAN achieves competitive results compared to the state-of-the-art clustering and hashing models on several datasets. |
| Tasks | Image Clustering, Image Retrieval, Unsupervised Spatial Clustering |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Ghasedi_Balanced_Self-Paced_Learning_for_Generative_Adversarial_Clustering_Network_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Ghasedi_Balanced_Self-Paced_Learning_for_Generative_Adversarial_Clustering_Network_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/balanced-self-paced-learning-for-generative |
| Repo | |
| Framework | |
A compositional view of questions
| Title | A compositional view of questions |
| Authors | Maria Boritchev, Maxime Amblard |
| Abstract | We present a research on compositional treatment of questions in neo-davidsonian event semantics style. Our work is based on (Champollion, 2011) where only declarative sentences were considered. Our research is based on complex formal examples, paving the way towards further research in this domain and further testing on real-life corpora. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3618/ |
| https://www.aclweb.org/anthology/W19-3618 | |
| PWC | https://paperswithcode.com/paper/a-compositional-view-of-questions |
| Repo | |
| Framework | |
Double Viterbi: Weight Encoding for High Compression Ratio and Fast On-Chip Reconstruction for Deep Neural Network
| Title | Double Viterbi: Weight Encoding for High Compression Ratio and Fast On-Chip Reconstruction for Deep Neural Network |
| Authors | Daehyun Ahn, Dongsoo Lee, Taesu Kim, Jae-Joon Kim |
| Abstract | Weight pruning has been introduced as an efficient model compression technique. Even though pruning removes significant amount of weights in a network, memory requirement reduction was limited since conventional sparse matrix formats require significant amount of memory to store index-related information. Moreover, computations associated with such sparse matrix formats are slow because sequential sparse matrix decoding process does not utilize highly parallel computing systems efficiently. As an attempt to compress index information while keeping the decoding process parallelizable, Viterbi-based pruning was suggested. Decoding non-zero weights, however, is still sequential in Viterbi-based pruning. In this paper, we propose a new sparse matrix format in order to enable a highly parallel decoding process of the entire sparse matrix. The proposed sparse matrix is constructed by combining pruning and weight quantization. For the latest RNN models on PTB and WikiText-2 corpus, LSTM parameter storage requirement is compressed 19x using the proposed sparse matrix format compared to the baseline model. Compressed weight and indices can be reconstructed into a dense matrix fast using Viterbi encoders. Simulation results show that the proposed scheme can feed parameters to processing elements 20 % to 106 % faster than the case where the dense matrix values directly come from DRAM. |
| Tasks | Model Compression, Quantization |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HkfYOoCcYX |
| https://openreview.net/pdf?id=HkfYOoCcYX | |
| PWC | https://paperswithcode.com/paper/double-viterbi-weight-encoding-for-high |
| Repo | |
| Framework | |
Label super-resolution networks
| Title | Label super-resolution networks |
| Authors | Kolya Malkin, Caleb Robinson, Le Hou, Nebojsa Jojic |
| Abstract | We present a deep learning-based method for super-resolving coarse (low-resolution) labels assigned to groups of image pixels into pixel-level (high-resolution) labels, given the joint distribution between those low- and high-resolution labels. This method involves a novel loss function that minimizes the distance between a distribution determined by a set of model outputs and the corresponding distribution given by low-resolution labels over the same set of outputs. This setup does not require that the high-resolution classes match the low-resolution classes and can be used in high-resolution semantic segmentation tasks where high-resolution labeled data is not available. Furthermore, our proposed method is able to utilize both data with low-resolution labels and any available high-resolution labels, which we show improves performance compared to a network trained only with the same amount of high-resolution data. We test our proposed algorithm in a challenging land cover mapping task to super-resolve labels at a 30m resolution to a separate set of labels at a 1m resolution. We compare our algorithm with models that are trained on high-resolution data and show that 1) we can achieve similar performance using only low-resolution data; and 2) we can achieve better performance when we incorporate a small amount of high-resolution data in our training. We also test our approach on a medical imaging problem, resolving low-resolution probability maps into high-resolution segmentation of lymphocytes with accuracy equal to that of fully supervised models. |
| Tasks | Semantic Segmentation, Super-Resolution |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rkxwShA9Ym |
| https://openreview.net/pdf?id=rkxwShA9Ym | |
| PWC | https://paperswithcode.com/paper/label-super-resolution-networks |
| Repo | |
| Framework | |
Context-Aware Neural Machine Translation Decoding
| Title | Context-Aware Neural Machine Translation Decoding |
| Authors | Eva Mart{'\i}nez Garcia, Carles Creus, Cristina Espa{~n}a-Bonet |
| Abstract | This work presents a decoding architecture that fuses the information from a neural translation model and the context semantics enclosed in a semantic space language model based on word embeddings. The method extends the beam search decoding process and therefore can be applied to any neural machine translation framework. With this, we sidestep two drawbacks of current document-level systems: (i) we do not modify the training process so there is no increment in training time, and (ii) we do not require document-level an-notated data. We analyze the impact of the fusion system approach and its parameters on the final translation quality for English{–}Spanish. We obtain consistent and statistically significant improvements in terms of BLEU and METEOR and we observe how the fused systems are able to handle synonyms to propose more adequate translations as well as help the system to disambiguate among several translation candidates for a word. |
| Tasks | Language Modelling, Machine Translation, Word Embeddings |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6502/ |
| https://www.aclweb.org/anthology/D19-6502 | |
| PWC | https://paperswithcode.com/paper/context-aware-neural-machine-translation-2 |
| Repo | |
| Framework | |
Visualizing and Understanding the Semantics of Embedding Spaces via Algebraic Formulae
| Title | Visualizing and Understanding the Semantics of Embedding Spaces via Algebraic Formulae |
| Authors | Piero Molino, Yang Wang, Jiawei Zhang |
| Abstract | Embeddings are a fundamental component of many modern machine learning and natural language processing models. Understanding them and visualizing them is essential for gathering insights about the information they capture and the behavior of the models. State of the art in analyzing embeddings consists in projecting them in two-dimensional planes without any interpretable semantics associated to the axes of the projection, which makes detailed analyses and comparison among multiple sets of embeddings challenging. In this work, we propose to use explicit axes defined as algebraic formulae over embeddings to project them into a lower dimensional, but semantically meaningful subspace, as a simple yet effective analysis and visualization methodology. This methodology assigns an interpretable semantics to the measures of variability and the axes of visualizations, allowing for both comparisons among different sets of embeddings and fine-grained inspection of the embedding spaces. We demonstrate the power of the proposed methodology through a series of case studies that make use of visualizations constructed around the underlying methodology and through a user study. The results show how the methodology is effective at providing more profound insights than classical projection methods and how it is widely applicable to many other use cases. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=Skz3Q2CcFX |
| https://openreview.net/pdf?id=Skz3Q2CcFX | |
| PWC | https://paperswithcode.com/paper/visualizing-and-understanding-the-semantics |
| Repo | |
| Framework | |
Towards a Resource Grammar for Runyankore and Rukiga
| Title | Towards a Resource Grammar for Runyankore and Rukiga |
| Authors | David Bamutura, Peter Ljungl{"o}f |
| Abstract | Currently, there is a lack of computational grammar resources for many under-resourced languages which limits the ability to develop Natural Language Processing (NLP) tools and applications such as Multilingual Document Authoring, Computer-Assisted Language Learning (CALL) and Low-Coverage Machine Translation (MT) for these languages. In this paper, we present our attempt to formalise the grammar of two such languages: Runyankore and Rukiga. For this formalisation we use the Grammatical Framework (GF) and its Resource Grammar Library (GF-RGL). |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3602/ |
| https://www.aclweb.org/anthology/W19-3602 | |
| PWC | https://paperswithcode.com/paper/towards-a-resource-grammar-for-runyankore-and |
| Repo | |
| Framework | |
Cross-Domain Sentiment Classification using Vector Embedded Domain Representations
| Title | Cross-Domain Sentiment Classification using Vector Embedded Domain Representations |
| Authors | Nicolaj Filrup Rasmussen, Kristian N{\o}rgaard Jensen, Marco Placenti, Thai Wang |
| Abstract | Due to the differences between reviews in different product categories, creating a general model for cross-domain sentiment classification can be a difficult task. This paper proposes an architecture that incorporates domain knowledge into a neural sentiment classification model. In addition to providing a cross-domain model, this also provides a quantifiable representation of the domains as numeric vectors. We show that it is possible to cluster the domain vectors and provide qualitative insights into the inter-domain relations. We also a) present a new data set for sentiment classification that includes a domain parameter and preprocessed data points, and b) perform an ablation study in order to determine whether some word groups impact performance. |
| Tasks | Sentiment Analysis |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-6206/ |
| https://www.aclweb.org/anthology/W19-6206 | |
| PWC | https://paperswithcode.com/paper/cross-domain-sentiment-classification-using |
| Repo | |
| Framework | |
Are Training Samples Correlated? Learning to Generate Dialogue Responses with Multiple References
| Title | Are Training Samples Correlated? Learning to Generate Dialogue Responses with Multiple References |
| Authors | Lisong Qiu, Juntao Li, Wei Bi, Dongyan Zhao, Rui Yan |
| Abstract | Due to its potential applications, open-domain dialogue generation has become popular and achieved remarkable progress in recent years, but sometimes suffers from generic responses. Previous models are generally trained based on 1-to-1 mapping from an input query to its response, which actually ignores the nature of 1-to-n mapping in dialogue that there may exist multiple valid responses corresponding to the same query. In this paper, we propose to utilize the multiple references by considering the correlation of different valid responses and modeling the 1-to-n mapping with a novel two-step generation architecture. The first generation phase extracts the common features of different responses which, combined with distinctive features obtained in the second phase, can generate multiple diverse and appropriate responses. Experimental results show that our proposed model can effectively improve the quality of response and outperform existing neural dialogue models on both automatic and human evaluations. |
| Tasks | Dialogue Generation |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1372/ |
| https://www.aclweb.org/anthology/P19-1372 | |
| PWC | https://paperswithcode.com/paper/are-training-samples-correlated-learning-to |
| Repo | |
| Framework | |
Learning from the Experience of Doctors: Automated Diagnosis of Appendicitis Based on Clinical Notes
| Title | Learning from the Experience of Doctors: Automated Diagnosis of Appendicitis Based on Clinical Notes |
| Authors | Steven Kester Yuwono, Hwee Tou Ng, Kee Yuan Ngiam |
| Abstract | The objective of this work is to develop an automated diagnosis system that is able to predict the probability of appendicitis given a free-text emergency department (ED) note and additional structured information (e.g., lab test results). Our clinical corpus consists of about 180,000 ED notes based on ten years of patient visits to the Accident and Emergency (A{&}E) Department of the National University Hospital (NUH), Singapore. We propose a novel neural network approach that learns to diagnose acute appendicitis based on doctors{'} free-text ED notes without any feature engineering. On a test set of 2,000 ED notes with equal number of appendicitis (positive) and non-appendicitis (negative) diagnosis and in which all the negative ED notes only consist of abdominal-related diagnosis, our model is able to achieve a promising F{_}0.5-score of 0.895 while ED doctors achieve F{_}0.5-score of 0.900. Visualization shows that our model is able to learn important features, signs, and symptoms of patients from unstructured free-text ED notes, which will help doctors to make better diagnosis. |
| Tasks | Feature Engineering |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5002/ |
| https://www.aclweb.org/anthology/W19-5002 | |
| PWC | https://paperswithcode.com/paper/learning-from-the-experience-of-doctors |
| Repo | |
| Framework | |
3D Shape Reconstruction From Images in the Frequency Domain
| Title | 3D Shape Reconstruction From Images in the Frequency Domain |
| Authors | Weichao Shen, Yunde Jia, Yuwei Wu |
| Abstract | Reconstructing the high-resolution volumetric 3D shape from images is challenging due to the cubic growth of computational cost. In this paper, we propose a Fourier-based method that reconstructs a 3D shape from images in a 2D space by predicting slices in the frequency domain. According to the Fourier slice projection theorem, we introduce a thickness map to bridge the domain gap between images in the spatial domain and slices in the frequency domain. The thickness map is the 2D spatial projection of the 3D shape, which is easily predicted from the input image by a general convolutional neural network. Each slice in the frequency domain is the Fourier transform of the corresponding thickness map. All slices constitute a 3D descriptor and the 3D shape is the inverse Fourier transform of the descriptor. Using slices in the frequency domain, our method can transfer the 3D shape reconstruction from the 3D space into the 2D space, which significantly reduces the computational cost. The experiment results on the ShapeNet dataset demonstrate that our method achieves competitive reconstruction accuracy and computational efficiency compared with the state-of-the-art reconstruction methods. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Shen_3D_Shape_Reconstruction_From_Images_in_the_Frequency_Domain_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Shen_3D_Shape_Reconstruction_From_Images_in_the_Frequency_Domain_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/3d-shape-reconstruction-from-images-in-the |
| Repo | |
| Framework | |
