Paper Group NANR 57
Workflows for kickstarting RBMT in virtually No-Resource Situation. Accelerating first order optimization algorithms. Variation between Different Discourse Types: Literate vs. Oral. Online aggression from a sociological perspective: An integrative view on determinants and possible countermeasures. Verbs in Egyptian Arabic: a case for register varia …
Workflows for kickstarting RBMT in virtually No-Resource Situation
| Title | Workflows for kickstarting RBMT in virtually No-Resource Situation |
| Authors | Tommi A Pirinen |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6803/ |
| https://www.aclweb.org/anthology/W19-6803 | |
| PWC | https://paperswithcode.com/paper/workflows-for-kickstarting-rbmt-in-virtually |
| Repo | |
| Framework | |
Accelerating first order optimization algorithms
| Title | Accelerating first order optimization algorithms |
| Authors | Ange tato, Roger nkambou |
| Abstract | There exist several stochastic optimization algorithms. However in most cases, it is difficult to tell for a particular problem which will be the best optimizer to choose as each of them are good. Thus, we present a simple and intuitive technique, when applied to first order optimization algorithms, is able to improve the speed of convergence and reaches a better minimum for the loss function compared to the original algorithms. The proposed solution modifies the update rule, based on the variation of the direction of the gradient during training. We conducted several tests with Adam and AMSGrad on two different datasets. The preliminary results show that the proposed technique improves the performance of existing optimization algorithms and works well in practice. |
| Tasks | Stochastic Optimization |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SkgCV205tQ |
| https://openreview.net/pdf?id=SkgCV205tQ | |
| PWC | https://paperswithcode.com/paper/accelerating-first-order-optimization |
| Repo | |
| Framework | |
Variation between Different Discourse Types: Literate vs. Oral
| Title | Variation between Different Discourse Types: Literate vs. Oral |
| Authors | Katrin Ortmann, Stefanie Dipper |
| Abstract | This paper deals with the automatic identification of literate and oral discourse in German texts. A range of linguistic features is selected and their role in distinguishing between literate- and oral-oriented registers is investigated, using a decision-tree classifier. It turns out that all of the investigated features are related in some way to oral conceptuality. Especially simple measures of complexity (average sentence and word length) are prominent indicators of oral and literate discourse. In addition, features of reference and deixis (realized by different types of pronouns) also prove to be very useful in determining the degree of orality of different registers. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1407/ |
| https://www.aclweb.org/anthology/W19-1407 | |
| PWC | https://paperswithcode.com/paper/variation-between-different-discourse-types |
| Repo | |
| Framework | |
Online aggression from a sociological perspective: An integrative view on determinants and possible countermeasures
| Title | Online aggression from a sociological perspective: An integrative view on determinants and possible countermeasures |
| Authors | Sebastian Weingartner, Lea Stahel |
| Abstract | The present paper introduces a theoretical model for explaining aggressive online comments from a sociological perspective. It is innovative as it combines individual, situational, and social-structural determinants of online aggression and tries to theoretically derive their interplay. Moreover, the paper suggests an empirical strategy for testing the model. The main contribution will be to match online commenting data with survey data containing rich background data of non- /aggressive online commentators. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3520/ |
| https://www.aclweb.org/anthology/W19-3520 | |
| PWC | https://paperswithcode.com/paper/online-aggression-from-a-sociological |
| Repo | |
| Framework | |
Verbs in Egyptian Arabic: a case for register variation
| Title | Verbs in Egyptian Arabic: a case for register variation |
| Authors | Michael Grant White, Deryle W. Lonsdale |
| Abstract | |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/W19-5608/ |
| https://www.aclweb.org/anthology/W19-5608 | |
| PWC | https://paperswithcode.com/paper/verbs-in-egyptian-arabic-a-case-for-register |
| Repo | |
| Framework | |
INMT: Interactive Neural Machine Translation Prediction
| Title | INMT: Interactive Neural Machine Translation Prediction |
| Authors | Sebastin Santy, D, S apat, ipan, Monojit Choudhury, Kalika Bali |
| Abstract | In this paper, we demonstrate an Interactive Machine Translation interface, that assists human translators with on-the-fly hints and suggestions. This makes the end-to-end translation process faster, more efficient and creates high-quality translations. We augment the OpenNMT backend with a mechanism to accept the user input and generate conditioned translations. |
| Tasks | Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-3018/ |
| https://www.aclweb.org/anthology/D19-3018 | |
| PWC | https://paperswithcode.com/paper/inmt-interactive-neural-machine-translation |
| Repo | |
| Framework | |
A Comparative Study of English-Chinese Translations of Court Texts by Machine and Human Translators and the Word2Vec Based Similarity Measure’s Ability To Gauge Human Evaluation Biases
| Title | A Comparative Study of English-Chinese Translations of Court Texts by Machine and Human Translators and the Word2Vec Based Similarity Measure’s Ability To Gauge Human Evaluation Biases |
| Authors | Ming Qian, Jessie Liu, Chaofeng Li, Liming Pals |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6714/ |
| https://www.aclweb.org/anthology/W19-6714 | |
| PWC | https://paperswithcode.com/paper/a-comparative-study-of-english-chinese |
| Repo | |
| Framework | |
Initial Experiments In Cross-Lingual Morphological Analysis Using Morpheme Segmentation
| Title | Initial Experiments In Cross-Lingual Morphological Analysis Using Morpheme Segmentation |
| Authors | Vladislav Mikhailov, Lorenzo Tosi, Anastasia Khorosheva, Oleg Serikov |
| Abstract | The paper describes initial experiments in data-driven cross-lingual morphological analysis of open-category words using a combination of unsupervised morpheme segmentation, annotation projection and an LSTM encoder-decoder model with attention. Our algorithm provides lemmatisation and morphological analysis generation for previously unseen low-resource language surface forms with only annotated data on the related languages given. Despite the inherently lossy annotation projection, we achieved the best lemmatisation F1-score in the VarDial 2019 Shared Task on Cross-Lingual Morphological Analysis for both Karachay-Balkar (Turkic languages, agglutinative morphology) and Sardinian (Romance languages, fusional morphology). |
| Tasks | Morphological Analysis |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1415/ |
| https://www.aclweb.org/anthology/W19-1415 | |
| PWC | https://paperswithcode.com/paper/initial-experiments-in-cross-lingual |
| Repo | |
| Framework | |
A Survey of the Perceived Text Adaptation Needs of Adults with Autism
| Title | A Survey of the Perceived Text Adaptation Needs of Adults with Autism |
| Authors | Victoria Yaneva, Constantin Orasan, Le An Ha, Natalia Ponomareva |
| Abstract | NLP approaches to automatic text adaptation often rely on user-need guidelines which are generic and do not account for the differences between various types of target groups. One such group are adults with high-functioning autism, who are usually able to read long sentences and comprehend difficult words but whose comprehension may be impeded by other linguistic constructions. This is especially challenging for real-world user-generated texts such as product reviews, which cannot be controlled editorially and are thus a particularly good applcation for automatic text adaptation systems. In this paper we present a mixed-methods survey conducted with 24 adult web-users diagnosed with autism and an age-matched control group of 33 neurotypical participants. The aim of the survey was to identify whether the group with autism experienced any barriers when reading online reviews, what these potential barriers were, and what NLP methods would be best suited to improve the accessibility of online reviews for people with autism. The group with autism consistently reported significantly greater difficulties with understanding online product reviews compared to the control group and identified issues related to text length, poor topic organisation, and the use of irony and sarcasm. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1155/ |
| https://www.aclweb.org/anthology/R19-1155 | |
| PWC | https://paperswithcode.com/paper/a-survey-of-the-perceived-text-adaptation |
| Repo | |
| Framework | |
Unsupervised Procedure Learning via Joint Dynamic Summarization
| Title | Unsupervised Procedure Learning via Joint Dynamic Summarization |
| Authors | Ehsan Elhamifar, Zwe Naing |
| Abstract | We address the problem of unsupervised procedure learning from unconstrained instructional videos. Our goal is to produce a summary of the procedure key-steps and their ordering needed to perform a given task, as well as localization of the key-steps in videos. We develop a collaborative sequential subset selection framework, where we build a dynamic model on videos by learning states and transitions between them, where states correspond to different subactivities, including background and procedure steps. To extract procedure key-steps, we develop an optimization framework that finds a sequence of a small number of states that well represents all videos and is compatible with the state transition model. Given that our proposed optimization is non-convex and NP-hard, we develop a fast greedy algorithm whose complexity is linear in the length of the videos and the number of states of the dynamic model, hence, scales to large datasets. Under appropriate conditions on the transition model, our proposed formulation is approximately submodular, hence, comes with performance guarantees. We also present ProceL, a new multimodal dataset of 47.3 hours of videos and their transcripts from diverse tasks, for procedure learning evaluation. By extensive experiments, we show that our framework significantly improves the state of the art performance. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Elhamifar_Unsupervised_Procedure_Learning_via_Joint_Dynamic_Summarization_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Elhamifar_Unsupervised_Procedure_Learning_via_Joint_Dynamic_Summarization_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-procedure-learning-via-joint |
| Repo | |
| Framework | |
Face Alignment With Kernel Density Deep Neural Network
| Title | Face Alignment With Kernel Density Deep Neural Network |
| Authors | Lisha Chen, Hui Su, Qiang Ji |
| Abstract | Deep neural networks achieve good performance in many computer vision problems such as face alignment. However, when the testing image is challenging due to low resolution, occlusion or adversarial attacks, the accuracy of a deep neural network suffers greatly. Therefore, it is important to quantify the uncertainty in its predictions. A probabilistic neural network with Gaussian distribution over the target is typically used to quantify uncertainty for regression problems. However, in real-world problems especially computer vision tasks, the Gaussian assumption is too strong. To model more general distributions, such as multi-modal or asymmetric distributions, we propose to develop a kernel density deep neural network. Specifically, for face alignment, we adapt state-of-the-art hourglass neural network into a probabilistic neural network framework with landmark probability map as its output. The model is trained by maximizing the conditional log likelihood. To exploit the output probability map, we extend the model to multi-stage so that the logits map from the previous stage can feed into the next stage to progressively improve the landmark detection accuracy. Extensive experiments on benchmark datasets against state-of-the-art unconstrained deep learning method demonstrate that the proposed kernel density network achieves comparable or superior performance in terms of prediction accuracy. It further provides aleatoric uncertainty estimation in predictions. |
| Tasks | Face Alignment |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Chen_Face_Alignment_With_Kernel_Density_Deep_Neural_Network_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Chen_Face_Alignment_With_Kernel_Density_Deep_Neural_Network_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/face-alignment-with-kernel-density-deep |
| Repo | |
| Framework | |
Efficient Smooth Non-Convex Stochastic Compositional Optimization via Stochastic Recursive Gradient Descent
| Title | Efficient Smooth Non-Convex Stochastic Compositional Optimization via Stochastic Recursive Gradient Descent |
| Authors | Huizhuo Yuan, Xiangru Lian, Chris Junchi Li, Ji Liu, Wenqing Hu |
| Abstract | Stochastic compositional optimization arises in many important machine learning tasks such as reinforcement learning and portfolio management. The objective function is the composition of two expectations of stochastic functions, and is more challenging to optimize than vanilla stochastic optimization problems. In this paper, we investigate the stochastic compositional optimization in the general smooth non-convex setting. We employ a recently developed idea of \textit{Stochastic Recursive Gradient Descent} to design a novel algorithm named SARAH-Compositional, and prove a sharp Incremental First-order Oracle (IFO) complexity upper bound for stochastic compositional optimization: $\mathcal{O}((n+m)^{1/2} \varepsilon^{-2})$ in the finite-sum case and $\mathcal{O}(\varepsilon^{-3})$ in the online case. Such a complexity is known to be the best one among IFO complexity results for non-convex stochastic compositional optimization. Numerical experiments validate the superior performance of our algorithm and theory. |
| Tasks | Stochastic Optimization |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8916-efficient-smooth-non-convex-stochastic-compositional-optimization-via-stochastic-recursive-gradient-descent |
| http://papers.nips.cc/paper/8916-efficient-smooth-non-convex-stochastic-compositional-optimization-via-stochastic-recursive-gradient-descent.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-smooth-non-convex-stochastic |
| Repo | |
| Framework | |
TwistBytes - Identification of Cuneiform Languages and German Dialects at VarDial 2019
| Title | TwistBytes - Identification of Cuneiform Languages and German Dialects at VarDial 2019 |
| Authors | Fern Benites, o, Pius von D{"a}niken, Mark Cieliebak |
| Abstract | We describe our approaches for the German Dialect Identification (GDI) and the Cuneiform Language Identification (CLI) tasks at the VarDial Evaluation Campaign 2019. The goal was to identify dialects of Swiss German in GDI and Sumerian and Akkadian in CLI. In GDI, the system should distinguish four dialects from the German-speaking part of Switzerland. Our system for GDI achieved third place out of 6 teams, with a macro averaged F-1 of 74.6{%}. In CLI, the system should distinguish seven languages written in cuneiform script. Our system achieved third place out of 8 teams, with a macro averaged F-1 of 74.7{%}. |
| Tasks | Language Identification |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1421/ |
| https://www.aclweb.org/anthology/W19-1421 | |
| PWC | https://paperswithcode.com/paper/twistbytes-identification-of-cuneiform |
| Repo | |
| Framework | |
DTeam @ VarDial 2019: Ensemble based on skip-gram and triplet loss neural networks for Moldavian vs. Romanian cross-dialect topic identification
| Title | DTeam @ VarDial 2019: Ensemble based on skip-gram and triplet loss neural networks for Moldavian vs. Romanian cross-dialect topic identification |
| Authors | Diana Tudoreanu |
| Abstract | This paper presents the solution proposed by DTeam in the VarDial 2019 Evaluation Campaign for the Moldavian vs. Romanian cross-topic identification task. The solution proposed is a Support Vector Machines (SVM) ensemble composed of a two character-level neural networks. The first network is a skip-gram classification model formed of an embedding layer, three convolutional layers and two fully-connected layers. The second network has a similar architecture, but is trained using the triplet loss function. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1422/ |
| https://www.aclweb.org/anthology/W19-1422 | |
| PWC | https://paperswithcode.com/paper/dteam-vardial-2019-ensemble-based-on-skip |
| Repo | |
| Framework | |
Automatic Translation for Software with Safe Velocity
| Title | Automatic Translation for Software with Safe Velocity |
| Authors | Dag Schmidtke, Declan Groves |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6729/ |
| https://www.aclweb.org/anthology/W19-6729 | |
| PWC | https://paperswithcode.com/paper/automatic-translation-for-software-with-safe |
| Repo | |
| Framework | |
