Paper Group NANR 163
Development of a Universal Dependencies treebank for Welsh. Personality-dependent Neural Text Summarization. Deep Supervised Summarization: Algorithm and Application to Learning Instructions. Toward a Better Story End: Collecting Human Evaluation with Reasons. Nonparametric Contextual Bandits in Metric Spaces with Unknown Metric. Over-parameterizat …
Development of a Universal Dependencies treebank for Welsh
| Title | Development of a Universal Dependencies treebank for Welsh |
| Authors | Johannes Heinecke, Francis M. Tyers |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6904/ |
| https://www.aclweb.org/anthology/W19-6904 | |
| PWC | https://paperswithcode.com/paper/development-of-a-universal-dependencies |
| Repo | |
| Framework | |
Personality-dependent Neural Text Summarization
| Title | Personality-dependent Neural Text Summarization |
| Authors | Pablo Costa, Iv Paraboni, r{'e} |
| Abstract | In Natural Language Generation systems, personalization strategies - i.e, the use of information about a target author to generate text that (more) closely resembles human-produced language - have long been applied to improve results. The present work addresses one such strategy - namely, the use of Big Five personality information about the target author - applied to the case of abstractive text summarization using neural sequence-to-sequence models. Initial results suggest that having access to personality information does lead to more accurate (or human-like) text summaries, and paves the way for more robust systems of this kind. |
| Tasks | Abstractive Text Summarization, Text Generation, Text Summarization |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1024/ |
| https://www.aclweb.org/anthology/R19-1024 | |
| PWC | https://paperswithcode.com/paper/personality-dependent-neural-text |
| Repo | |
| Framework | |
Deep Supervised Summarization: Algorithm and Application to Learning Instructions
| Title | Deep Supervised Summarization: Algorithm and Application to Learning Instructions |
| Authors | Chengguang Xu, Ehsan Elhamifar |
| Abstract | We address the problem of finding representative points of datasets by learning from multiple datasets and their ground-truth summaries. We develop a supervised subset selection framework, based on the facility location utility function, which learns to map datasets to their ground-truth representatives. To do so, we propose to learn representations of data so that the input of transformed data to the facility location recovers their ground-truth representatives. Given the NP-hardness of the utility function, we consider its convex relaxation based on sparse representation and investigate conditions under which the solution of the convex optimization recovers ground-truth representatives of each dataset. We design a loss function whose minimization over the parameters of the data representation network leads to satisfying the theoretical conditions, hence guaranteeing recovering ground-truth summaries. Given the non-convexity of the loss function, we develop an efficient learning scheme that alternates between representation learning by minimizing our proposed loss given the current assignments of points to ground-truth representatives and updating assignments given the current data representation. By experiments on the problem of learning key-steps (subactivities) of instructional videos, we show that our proposed framework improves the state-of-the-art supervised subset selection algorithms. |
| Tasks | Representation Learning |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8395-deep-supervised-summarization-algorithm-and-application-to-learning-instructions |
| http://papers.nips.cc/paper/8395-deep-supervised-summarization-algorithm-and-application-to-learning-instructions.pdf | |
| PWC | https://paperswithcode.com/paper/deep-supervised-summarization-algorithm-and |
| Repo | |
| Framework | |
Toward a Better Story End: Collecting Human Evaluation with Reasons
| Title | Toward a Better Story End: Collecting Human Evaluation with Reasons |
| Authors | Yusuke Mori, Hiroaki Yamane, Yusuke Mukuta, Tatsuya Harada |
| Abstract | Creativity is an essential element of human nature used for many activities, such as telling a story. Based on human creativity, researchers have attempted to teach a computer to generate stories automatically or support this creative process. In this study, we undertake the task of story ending generation. This is a relatively new task, in which the last sentence of a given incomplete story is automatically generated. This is challenging because, in order to predict an appropriate ending, the generation method should comprehend the context of events. Despite the importance of this task, no clear evaluation metric has been established thus far; hence, it has remained an open problem. Therefore, we study the various elements involved in evaluating an automatic method for generating story endings. First, we introduce a baseline hierarchical sequence-to-sequence method for story ending generation. Then, we conduct a pairwise comparison against human-written endings, in which annotators choose the preferable ending. In addition to a quantitative evaluation, we conduct a qualitative evaluation by asking annotators to specify the reason for their choice. From the collected reasons, we discuss what elements the evaluation should focus on, to thereby propose effective metrics for the task. |
| Tasks | |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8646/ |
| https://www.aclweb.org/anthology/W19-8646 | |
| PWC | https://paperswithcode.com/paper/toward-a-better-story-end-collecting-human |
| Repo | |
| Framework | |
Nonparametric Contextual Bandits in Metric Spaces with Unknown Metric
| Title | Nonparametric Contextual Bandits in Metric Spaces with Unknown Metric |
| Authors | Nirandika Wanigasekara, Christina Yu |
| Abstract | Consider a nonparametric contextual multi-arm bandit problem where each arm $a \in [K]$ is associated to a nonparametric reward function $f_a: [0,1] \to \mathbb{R}$ mapping from contexts to the expected reward. Suppose that there is a large set of arms, yet there is a simple but unknown structure amongst the arm reward functions, e.g. finite types or smooth with respect to an unknown metric space. We present a novel algorithm which learns data-driven similarities amongst the arms, in order to implement adaptive partitioning of the context-arm space for more efficient learning. We provide regret bounds along with simulations that highlight the algorithm’s dependence on the local geometry of the reward functions. |
| Tasks | Multi-Armed Bandits |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9609-nonparametric-contextual-bandits-in-metric-spaces-with-unknown-metric |
| http://papers.nips.cc/paper/9609-nonparametric-contextual-bandits-in-metric-spaces-with-unknown-metric.pdf | |
| PWC | https://paperswithcode.com/paper/nonparametric-contextual-bandits-in-metric |
| Repo | |
| Framework | |
Over-parameterization Improves Generalization in the XOR Detection Problem
| Title | Over-parameterization Improves Generalization in the XOR Detection Problem |
| Authors | Alon Brutzkus, Amir Globerson |
| Abstract | Empirical evidence suggests that neural networks with ReLU activations generalize better with over-parameterization. However, there is currently no theoretical analysis that explains this observation. In this work, we study a simplified learning task with over-parameterized convolutional networks that empirically exhibits the same qualitative phenomenon. For this setting, we provide a theoretical analysis of the optimization and generalization performance of gradient descent. Specifically, we prove data-dependent sample complexity bounds which show that over-parameterization improves the generalization performance of gradient descent. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HyGLy2RqtQ |
| https://openreview.net/pdf?id=HyGLy2RqtQ | |
| PWC | https://paperswithcode.com/paper/over-parameterization-improves-generalization |
| Repo | |
| Framework | |
FEVER Breaker’s Run of Team NbAuzDrLqg
| Title | FEVER Breaker’s Run of Team NbAuzDrLqg |
| Authors | Youngwoo Kim, James Allan |
| Abstract | We describe our submission for the Breaker phase of the second Fact Extraction and VERification (FEVER) Shared Task. Our adversarial data can be explained by two perspectives. First, we aimed at testing model{'}s ability to retrieve evidence, when appropriate query terms could not be easily generated from the claim. Second, we test model{'}s ability to precisely understand the implications of the texts, which we expect to be rare in FEVER 1.0 dataset. Overall, we suggested six types of adversarial attacks. The evaluation on the submitted systems showed that the systems were only able get both the evidence and label correct in 20{%} of the data. We also demonstrate our adversarial run analysis in the data development process. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6615/ |
| https://www.aclweb.org/anthology/D19-6615 | |
| PWC | https://paperswithcode.com/paper/fever-breakers-run-of-team-nbauzdrlqg |
| Repo | |
| Framework | |
SeerNet: Predicting Convolutional Neural Network Feature-Map Sparsity Through Low-Bit Quantization
| Title | SeerNet: Predicting Convolutional Neural Network Feature-Map Sparsity Through Low-Bit Quantization |
| Authors | Shijie Cao, Lingxiao Ma, Wencong Xiao, Chen Zhang, Yunxin Liu, Lintao Zhang, Lanshun Nie, Zhi Yang |
| Abstract | In this paper we present a novel and general method to accelerate convolutional neural network (CNN) inference by taking advantage of feature map sparsity. We experimentally demonstrate that a highly quantized version of the original network is sufficient in predicting the output sparsity accurately, and verify that leveraging such sparsity in inference incurs negligible accuracy drop compared with the original network. To accelerate inference, for each convolution layer our approach first obtains a binary sparsity mask of the output feature maps by running inference on a quantized version of the original network layer, and then conducts a full-precision sparse convolution to find out the precise values of the non-zero outputs. Compared with existing work, our approach avoids the overhead of training additional auxiliary networks, while is still applicable to general CNN networks without being limited to certain application domains. |
| Tasks | Quantization |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Cao_SeerNet_Predicting_Convolutional_Neural_Network_Feature-Map_Sparsity_Through_Low-Bit_Quantization_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Cao_SeerNet_Predicting_Convolutional_Neural_Network_Feature-Map_Sparsity_Through_Low-Bit_Quantization_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/seernet-predicting-convolutional-neural |
| Repo | |
| Framework | |
Recurrent Neural Networks With Intra-Frame Iterations for Video Deblurring
| Title | Recurrent Neural Networks With Intra-Frame Iterations for Video Deblurring |
| Authors | Seungjun Nah, Sanghyun Son, Kyoung Mu Lee |
| Abstract | Recurrent neural networks (RNNs) are widely used for sequential data processing. Recent state-of-the-art video deblurring methods bank on convolutional recurrent neural network architectures to exploit the temporal relationship between neighboring frames. In this work, we aim to improve the accuracy of recurrent models by adapting the hidden states transferred from past frames to the frame being processed so that the relations between video frames could be better used. We iteratively update the hidden state via re-using RNN cell parameters before predicting an output deblurred frame. Since we use existing parameters to update the hidden state, our method improves accuracy without additional modules. As the architecture remains the same regardless of iteration number, fewer iteration models can be considered as a partial computational path of the models with more iterations. To take advantage of this property, we employ a stochastic method to optimize our iterative models better. At training time, we randomly choose the iteration number on the fly and apply a regularization loss that favors less computation unless there are considerable reconstruction gains. We show that our method exhibits state-of-the-art video deblurring performance while operating in real-time speed. |
| Tasks | Deblurring |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Nah_Recurrent_Neural_Networks_With_Intra-Frame_Iterations_for_Video_Deblurring_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Nah_Recurrent_Neural_Networks_With_Intra-Frame_Iterations_for_Video_Deblurring_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/recurrent-neural-networks-with-intra-frame |
| Repo | |
| Framework | |
The Summary Evaluation Task in the MultiLing - RANLP 2019 Workshop
| Title | The Summary Evaluation Task in the MultiLing - RANLP 2019 Workshop |
| Authors | George Giannakopoulos, Nikiforos Pittaras |
| Abstract | This report covers the summarization evaluation task, proposed to the summarization community via the MultiLing 2019 Workshop of the RANLP 2019 conference. The task aims to encourage the development of automatic summarization evaluation methods closely aligned with manual, human-authored summary grades and judgements. A multilingual setting is adopted, building upon a corpus of Wikinews articles across 6 languages (English, Arabic, Romanian, Greek, Spanish and Czech). The evaluation utilizes human (golden) and machine-generated (peer) summaries, which have been assigned human evaluation scores from previous MultiLing tasks. Using these resources, the original corpus is augmented with synthetic data, combining summary texts under three different strategies (reorder, merge and replace), each engineered to introduce noise in the summary in a controlled and quantifiable way. We estimate that the utilization of such data can extract and highlight useful attributes of summary quality estimation, aiding the creation of data-driven automatic methods with an increased correlation to human summary evaluations across domains and languages. This paper provides a brief description of the summary evaluation task, the data generation protocol and the resources made available by the MultiLing community, towards improving automatic summarization evaluation. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8903/ |
| https://www.aclweb.org/anthology/W19-8903 | |
| PWC | https://paperswithcode.com/paper/the-summary-evaluation-task-in-the-multiling |
| Repo | |
| Framework | |
An annotated dataset of literary entities
| Title | An annotated dataset of literary entities |
| Authors | David Bamman, Sejal Popat, Sheng Shen |
| Abstract | We present a new dataset comprised of 210,532 tokens evenly drawn from 100 different English-language literary texts annotated for ACE entity categories (person, location, geo-political entity, facility, organization, and vehicle). These categories include non-named entities (such as {}the boy{''}, {}the kitchen{''}) and nested structure (such as [[the cook]{'}s sister]). In contrast to existing datasets built primarily on news (focused on geo-political entities and organizations), literary texts offer strikingly different distributions of entity categories, with much stronger emphasis on people and description of settings. We present empirical results demonstrating the performance of nested entity recognition models in this domain; training natively on in-domain literary data yields an improvement of over 20 absolute points in F-score (from 45.7 to 68.3), and mitigates a disparate impact in performance for male and female entities present in models trained on news data. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1220/ |
| https://www.aclweb.org/anthology/N19-1220 | |
| PWC | https://paperswithcode.com/paper/an-annotated-dataset-of-literary-entities |
| Repo | |
| Framework | |
Representation Learning and Dynamic Programming for Arc-Hybrid Parsing
| Title | Representation Learning and Dynamic Programming for Arc-Hybrid Parsing |
| Authors | Joseph Le Roux, Antoine Rozenknop, Mathieu Lacroix |
| Abstract | We present a new method for transition-based parsing where a solution is a pair made of a dependency tree and a derivation graph describing the construction of the former. From this representation we are able to derive an efficient parsing algorithm and design a neural network that learns vertex representations and arc scores. Experimentally, although we only train via local classifiers, our approach improves over previous arc-hybrid systems and reach state-of-the-art parsing accuracy. |
| Tasks | Representation Learning |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1023/ |
| https://www.aclweb.org/anthology/K19-1023 | |
| PWC | https://paperswithcode.com/paper/representation-learning-and-dynamic |
| Repo | |
| Framework | |
On the Convergence and Robustness of Batch Normalization
| Title | On the Convergence and Robustness of Batch Normalization |
| Authors | Yongqiang Cai, Qianxiao Li, Zuowei Shen |
| Abstract | Despite its empirical success, the theoretical underpinnings of the stability, convergence and acceleration properties of batch normalization (BN) remain elusive. In this paper, we attack this problem from a modelling approach, where we perform thorough theoretical analysis on BN applied to simplified model: ordinary least squares (OLS). We discover that gradient descent on OLS with BN has interesting properties, including a scaling law, convergence for arbitrary learning rates for the weights, asymptotic acceleration effects, as well as insensitivity to choice of learning rates. We then demonstrate numerically that these findings are not specific to the OLS problem and hold qualitatively for more complex supervised learning problems. This points to a new direction towards uncovering the mathematical principles that underlies batch normalization. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SJg7IsC5KQ |
| https://openreview.net/pdf?id=SJg7IsC5KQ | |
| PWC | https://paperswithcode.com/paper/on-the-convergence-and-robustness-of-batch-1 |
| Repo | |
| Framework | |
Stochastic Exposure Coding for Handling Multi-ToF-Camera Interference
| Title | Stochastic Exposure Coding for Handling Multi-ToF-Camera Interference |
| Authors | Jongho Lee, Mohit Gupta |
| Abstract | As continuous-wave time-of-flight (C-ToF) cameras become popular in 3D imaging applications, they need to contend with the problem of multi-camera interference (MCI). In a multi-camera environment, a ToF camera may receive light from the sources of other cameras, resulting in large depth errors. In this paper, we propose stochastic exposure coding (SEC), a novel approach for mitigating. SEC involves dividing a camera’s integration time into multiple slots, and switching the camera off and on stochastically during each slot. This approach has two benefits. First, by appropriately choosing the on probability for each slot, the camera can effectively filter out both the AC and DC components of interfering signals, thereby mitigating depth errors while also maintaining high signal-to-noise ratio. This enables high accuracy depth recovery with low power consumption. Second, this approach can be implemented without modifying the C-ToF camera’s coding functions, and thus, can be used with a wide range of cameras with minimal changes. We demonstrate the performance benefits of SEC with theoretical analysis, simulations and real experiments, across a wide range of imaging scenarios. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Lee_Stochastic_Exposure_Coding_for_Handling_Multi-ToF-Camera_Interference_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Lee_Stochastic_Exposure_Coding_for_Handling_Multi-ToF-Camera_Interference_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-exposure-coding-for-handling-multi |
| Repo | |
| Framework | |
On the Importance of Distinguishing Word Meaning Representations: A Case Study on Reverse Dictionary Mapping
| Title | On the Importance of Distinguishing Word Meaning Representations: A Case Study on Reverse Dictionary Mapping |
| Authors | Mohammad Taher Pilehvar |
| Abstract | Meaning conflation deficiency is one of the main limiting factors of word representations which, given their widespread use at the core of many NLP systems, can lead to inaccurate semantic understanding of the input text and inevitably hamper the performance. Sense representations target this problem. However, their potential impact has rarely been investigated in downstream NLP applications. Through a set of experiments on a state-of-the-art reverse dictionary system based on neural networks, we show that a simple adjustment aimed at addressing the meaning conflation deficiency can lead to substantial improvements. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1222/ |
| https://www.aclweb.org/anthology/N19-1222 | |
| PWC | https://paperswithcode.com/paper/on-the-importance-of-distinguishing-word |
| Repo | |
| Framework | |
