Paper Group NANR 192
Application of Post-Edited Machine Translation in Fashion eCommerce. OlloBot - Towards A Text-Based Arabic Health Conversational Agent: Evaluation and Results. Modeling language constructs with compatibility intervals. Provable Defenses against Spatially Transformed Adversarial Inputs: Impossibility and Possibility Results. Computational Analysis o …
Application of Post-Edited Machine Translation in Fashion eCommerce
| Title | Application of Post-Edited Machine Translation in Fashion eCommerce |
| Authors | Kasia Kosmaczewska, Matt Train |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6730/ |
| https://www.aclweb.org/anthology/W19-6730 | |
| PWC | https://paperswithcode.com/paper/application-of-post-edited-machine |
| Repo | |
| Framework | |
OlloBot - Towards A Text-Based Arabic Health Conversational Agent: Evaluation and Results
| Title | OlloBot - Towards A Text-Based Arabic Health Conversational Agent: Evaluation and Results |
| Authors | Ahmed Fadhil, Ahmed AbuRa{'}ed |
| Abstract | We introduce OlloBot, an Arabic conversational agent that assists physicians and supports patients with the care process. It doesn{'}t replace the physicians, instead provides health tracking and support and assists physicians with the care delivery through a conversation medium. The current model comprises healthy diet, physical activity, mental health, in addition to food logging. Not only OlloBot tracks user daily food, it also offers useful tips for healthier living. We will discuss the design, development and testing of OlloBot, and highlight the findings and limitations arose from the testing. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1034/ |
| https://www.aclweb.org/anthology/R19-1034 | |
| PWC | https://paperswithcode.com/paper/ollobot-towards-a-text-based-arabic-health |
| Repo | |
| Framework | |
Modeling language constructs with compatibility intervals
| Title | Modeling language constructs with compatibility intervals |
| Authors | Pavlo Kapustin, Michael Kapustin |
| Abstract | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1006/ |
| https://www.aclweb.org/anthology/W19-1006 | |
| PWC | https://paperswithcode.com/paper/modeling-language-constructs-with |
| Repo | |
| Framework | |
Provable Defenses against Spatially Transformed Adversarial Inputs: Impossibility and Possibility Results
| Title | Provable Defenses against Spatially Transformed Adversarial Inputs: Impossibility and Possibility Results |
| Authors | Xinyang Zhang, Yifan Huang, Chanh Nguyen, Shouling Ji, Ting Wang |
| Abstract | One intriguing property of neural networks is their inherent vulnerability to adversarial inputs, which are maliciously crafted samples to trigger target networks to misbehave. The state-of-the-art attacks generate adversarial inputs using either pixel perturbation or spatial transformation. Thus far, several provable defenses have been proposed against pixel perturbation-based attacks; yet, little is known about whether such solutions exist for spatial transformation-based attacks. This paper bridges this striking gap by conducting the first systematic study on provable defenses against spatially transformed adversarial inputs. Our findings convey mixed messages. On the impossibility side, we show that such defenses may not exist in practice: for any given networks, it is possible to find legitimate inputs and imperceptible transformations to generate adversarial inputs that force arbitrarily large errors. On the possibility side, we show that it is still feasible to construct adversarial training methods to significantly improve the resilience of networks against adversarial inputs over empirical datasets. We believe our findings provide insights for designing more effective defenses against spatially transformed adversarial inputs. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HkeWSnR5Y7 |
| https://openreview.net/pdf?id=HkeWSnR5Y7 | |
| PWC | https://paperswithcode.com/paper/provable-defenses-against-spatially |
| Repo | |
| Framework | |
Computational Analysis of Political Texts: Bridging Research Efforts Across Communities
| Title | Computational Analysis of Political Texts: Bridging Research Efforts Across Communities |
| Authors | Goran Glava{\v{s}}, Federico Nanni, Simone Paolo Ponzetto |
| Abstract | In the last twenty years, political scientists started adopting and developing natural language processing (NLP) methods more actively in order to exploit text as an additional source of data in their analyses. Over the last decade the usage of computational methods for analysis of political texts has drastically expanded in scope, allowing for a sustained growth of the text-as-data community in political science. In political science, NLP methods have been extensively used for a number of analyses types and tasks, including inferring policy position of actors from textual evidence, detecting topics in political texts, and analyzing stylistic aspects of political texts (e.g., assessing the role of language ambiguity in framing the political agenda). Just like in numerous other domains, much of the work on computational analysis of political texts has been enabled and facilitated by the development of resources such as, the topically coded electoral programmes (e.g., the Manifesto Corpus) or topically coded legislative texts (e.g., the Comparative Agenda Project). Political scientists created resources and used available NLP methods to process textual data largely in isolation from the NLP community. At the same time, NLP researchers addressed closely related tasks such as election prediction, ideology classification, and stance detection. In other words, these two communities have been largely agnostic of one another, with NLP researchers mostly unaware of interesting applications in political science and political scientists not applying cutting-edge NLP methodology to their problems. The main goal of this tutorial is to systematize and analyze the body of research work on political texts from both communities. We aim to provide a gentle, all-round introduction to methods and tasks related to computational analysis of political texts. Our vision is to bring the two research communities closer to each other and contribute to faster and more significant developments in this interdisciplinary research area. |
| Tasks | Stance Detection |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-4004/ |
| https://www.aclweb.org/anthology/P19-4004 | |
| PWC | https://paperswithcode.com/paper/computational-analysis-of-political-texts |
| Repo | |
| Framework | |
Paraphrase Generation for Semi-Supervised Learning in NLU
| Title | Paraphrase Generation for Semi-Supervised Learning in NLU |
| Authors | Eunah Cho, He Xie, William M. Campbell |
| Abstract | Semi-supervised learning is an efficient way to improve performance for natural language processing systems. In this work, we propose Para-SSL, a scheme to generate candidate utterances using paraphrasing and methods from semi-supervised learning. In order to perform paraphrase generation in the context of a dialog system, we automatically extract paraphrase pairs to create a paraphrase corpus. Using this data, we build a paraphrase generation system and perform one-to-many generation, followed by a validation step to select only the utterances with good quality. The paraphrase-based semi-supervised learning is applied to five functionalities in a natural language understanding system. Our proposed method for semi-supervised learning using paraphrase generation does not require user utterances and can be applied prior to releasing a new functionality to a system. Experiments show that we can achieve up to 19{%} of relative slot error reduction without an access to user utterances, and up to 35{%} when leveraging live traffic utterances. |
| Tasks | Paraphrase Generation |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2306/ |
| https://www.aclweb.org/anthology/W19-2306 | |
| PWC | https://paperswithcode.com/paper/paraphrase-generation-for-semi-supervised |
| Repo | |
| Framework | |
Sufficient Conditions for Robustness to Adversarial Examples: a Theoretical and Empirical Study with Bayesian Neural Networks
| Title | Sufficient Conditions for Robustness to Adversarial Examples: a Theoretical and Empirical Study with Bayesian Neural Networks |
| Authors | Yarin Gal, Lewis Smith |
| Abstract | We prove, under two sufficient conditions, that idealised models can have no adversarial examples. We discuss which idealised models satisfy our conditions, and show that idealised Bayesian neural networks (BNNs) satisfy these. We continue by studying near-idealised BNNs using HMC inference, demonstrating the theoretical ideas in practice. We experiment with HMC on synthetic data derived from MNIST for which we know the ground-truth image density, showing that near-perfect epistemic uncertainty correlates to density under image manifold, and that adversarial images lie off the manifold in our setting. This suggests why MC dropout, which can be seen as performing approximate inference, has been observed to be an effective defence against adversarial examples in practice; We highlight failure-cases of non-idealised BNNs relying on dropout, suggesting a new attack for dropout models and a new defence as well. Lastly, we demonstrate the defence on a cats-vs-dogs image classification task with a VGG13 variant. |
| Tasks | Image Classification |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=B1eZRiC9YX |
| https://openreview.net/pdf?id=B1eZRiC9YX | |
| PWC | https://paperswithcode.com/paper/sufficient-conditions-for-robustness-to |
| Repo | |
| Framework | |
Shape Reconstruction Using Differentiable Projections and Deep Priors
| Title | Shape Reconstruction Using Differentiable Projections and Deep Priors |
| Authors | Matheus Gadelha, Rui Wang, Subhransu Maji |
| Abstract | We investigate the problem of reconstructing shapes from noisy and incomplete projections in the presence of viewpoint uncertainities. The problem is cast as an optimization over the shape given measurements obtained by a projection operator and a prior. We present differentiable projection operators for a number of reconstruction problems which when combined with the deep image prior or shape prior allows efficient inference through gradient descent. We apply our method on a variety of reconstruction problems, such as tomographic reconstruction from a few samples, visual hull reconstruction incorporating view uncertainties, and 3D shape reconstruction from noisy depth maps. Experimental results show that our approach is effective for such shape reconstruction problems, without requiring any task-specific training. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Gadelha_Shape_Reconstruction_Using_Differentiable_Projections_and_Deep_Priors_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Gadelha_Shape_Reconstruction_Using_Differentiable_Projections_and_Deep_Priors_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/shape-reconstruction-using-differentiable |
| Repo | |
| Framework | |
Code-switching in Irish tweets: A preliminary analysis
| Title | Code-switching in Irish tweets: A preliminary analysis |
| Authors | Teresa Lynn, Kevin Scannell |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6905/ |
| https://www.aclweb.org/anthology/W19-6905 | |
| PWC | https://paperswithcode.com/paper/code-switching-in-irish-tweets-a-preliminary |
| Repo | |
| Framework | |
Quantifying the morphosyntactic content of Brown Clusters
| Title | Quantifying the morphosyntactic content of Brown Clusters |
| Authors | Manuel R. Ciosici, Leon Derczynski, Ira Assent |
| Abstract | Brown and Exchange word clusters have long been successfully used as word representations in Natural Language Processing (NLP) systems. Their success has been attributed to their seeming ability to represent both semantic and syntactic information. Using corpora representing several language families, we test the hypothesis that Brown and Exchange word clusters are highly effective at encoding morphosyntactic information. Our experiments show that word clusters are highly capable at distinguishing Parts of Speech. We show that increases in Average Mutual Information, the clustering algorithms{'} optimization goal, are highly correlated with improvements in encoding of morphosyntactic information. Our results provide empirical evidence that downstream NLP systems addressing tasks dependent on morphosyntactic information can benefit from word cluster features. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1157/ |
| https://www.aclweb.org/anthology/N19-1157 | |
| PWC | https://paperswithcode.com/paper/quantifying-the-morphosyntactic-content-of |
| Repo | |
| Framework | |
DeriNet 2.0: Towards an All-in-One Word-Formation Resource
| Title | DeriNet 2.0: Towards an All-in-One Word-Formation Resource |
| Authors | Jon{'a}{\v{s}} Vidra, Zden{\v{e}}k {\v{Z}}abokrtsk{'y}, Magda {\v{S}}ev{\v{c}}{'\i}kov{'a}, Luk{'a}{\v{s}} Kyj{'a}nek |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8510/ |
| https://www.aclweb.org/anthology/W19-8510 | |
| PWC | https://paperswithcode.com/paper/derinet-20-towards-an-all-in-one-word |
| Repo | |
| Framework | |
Modeling Extreme Events in Time Series Prediction
| Title | Modeling Extreme Events in Time Series Prediction |
| Authors | Daizong Ding (Fudan University);Mi Zhang (Fudan University);Xudong Pan (Fudan University);Min Yang (School of Computer Science, Fudan University);Xiangnan He (University of Science and Technology of China); |
| Abstract | Time series prediction is an intensively studied topic in data mining. In spite of the considerable improvements, recent deep learning-based methods overlook the existence of extreme events, which result in weak performance when applying them to real time series. Extreme events are rare and random, but do play a critical role in many real applications, such as the forecasting of financial crisis and natural disasters. In this paper, we explore the central theme of improving the ability of deep learning on modeling extreme events for time series prediction. Through the lens of formal analysis, we first find that the weakness of deep learning methods roots in the conventional form of quadratic loss. To address this issue, we take inspirations from the Extreme Value Theory, developing a new form of loss called Extreme Value Loss (EVL) for detecting the future occurrence of extreme events. Furthermore, we propose to employ Memory Network in order to memorize extreme events in historical records.By incorporating EVL with an adapted memory network module, we achieve an end-to-end framework for time series prediction with extreme events. Through extensive experiments on synthetic data and two real datasets of stock and climate, we empirically validate the effectiveness of our framework. Besides, we also provide a proper choice for hyper-parameters in our proposed framework by conducting several additional experiments. |
| Tasks | Time Series, Time Series Prediction |
| Published | 2019-08-08 |
| URL | https://www.kdd.org/kdd2019/accepted-papers/view/modeling-extreme-events-in-time-series-prediction |
| https://www.kdd.org/kdd2019/accepted-papers/view/modeling-extreme-events-in-time-series-prediction | |
| PWC | https://paperswithcode.com/paper/modeling-extreme-events-in-time-series |
| Repo | |
| Framework | |
A Character-Level LSTM Network Model for Tokenizing the Old Irish text of the W"urzburg Glosses on the Pauline Epistles
| Title | A Character-Level LSTM Network Model for Tokenizing the Old Irish text of the W"urzburg Glosses on the Pauline Epistles |
| Authors | Adrian Doyle, John P. McCrae, Clodagh Downey |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6910/ |
| https://www.aclweb.org/anthology/W19-6910 | |
| PWC | https://paperswithcode.com/paper/a-character-level-lstm-network-model-for |
| Repo | |
| Framework | |
Automatization of subprocesses in subtitling
| Title | Automatization of subprocesses in subtitling |
| Authors | Anke Tardel, Silvia Hansen-Schirra, Silke Gutermuth, Moritz Schaeffer |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7010/ |
| https://www.aclweb.org/anthology/W19-7010 | |
| PWC | https://paperswithcode.com/paper/automatization-of-subprocesses-in-subtitling |
| Repo | |
| Framework | |
Correlating Metaphors to Behavioural Data: A CRITT TPR-DB-based Study
| Title | Correlating Metaphors to Behavioural Data: A CRITT TPR-DB-based Study |
| Authors | Faustino Dardi |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7011/ |
| https://www.aclweb.org/anthology/W19-7011 | |
| PWC | https://paperswithcode.com/paper/correlating-metaphors-to-behavioural-data-a |
| Repo | |
| Framework | |
