Paper Group NANR 36
CLUF: a Neural Model for Second Language Acquisition Modeling. Generating Image Captions in Arabic using Root-Word Based Recurrent Neural Networks and Deep Neural Networks. License Plate Detection and Recognition in Unconstrained Scenarios. Towards a Language for Natural Language Treebank Transductions. Deep Face Detector Adaptation Without Negativ …
CLUF: a Neural Model for Second Language Acquisition Modeling
| Title | CLUF: a Neural Model for Second Language Acquisition Modeling |
| Authors | Shuyao Xu, Jin Chen, Long Qin |
| Abstract | Second Language Acquisition Modeling is the task to predict whether a second language learner would respond correctly in future exercises based on their learning history. In this paper, we propose a neural network based system to utilize rich contextual, linguistic and user information. Our neural model consists of a Context encoder, a Linguistic feature encoder, a User information encoder and a Format information encoder (CLUF). Furthermore, a decoder is introduced to combine such encoded features and make final predictions. Our system ranked in first place in the English track and second place in the Spanish and French track with an AUROC score of 0.861, 0.835 and 0.854 respectively. |
| Tasks | Knowledge Tracing, Language Acquisition, Language Modelling, Machine Reading Comprehension, Machine Translation, Reading Comprehension, Sentiment Analysis, Text Classification |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0546/ |
| https://www.aclweb.org/anthology/W18-0546 | |
| PWC | https://paperswithcode.com/paper/cluf-a-neural-model-for-second-language |
| Repo | |
| Framework | |
Generating Image Captions in Arabic using Root-Word Based Recurrent Neural Networks and Deep Neural Networks
| Title | Generating Image Captions in Arabic using Root-Word Based Recurrent Neural Networks and Deep Neural Networks |
| Authors | Vasu Jindal |
| Abstract | Image caption generation has gathered widespread interest in the artificial intelligence community. Automatic generation of an image description requires both computer vision and natural language processing techniques. While, there has been advanced research in the English caption generation, research on generating Arabic descriptions of an image is extremely limited. Semitic languages like Arabic are heavily influenced by root-words. We leverage this critical dependency of Arabic to generate captions of an image directly in Arabic using root-word based Recurrent Neural Network and Deep Neural Networks. Experimental results on dataset from various Middle Eastern newspaper websites allow us to report the first BLEU score for direct Arabic caption generation. We also compare the results of our approach with BLEU score captions generated in English and translated in Arabic. Experimental results confirm that generating image captions using root-words directly in Arabic significantly outperforms the English-Arabic translated captions using state-of-the-art methods. |
| Tasks | Image Captioning, Image Classification, Information Retrieval |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-4020/ |
| https://www.aclweb.org/anthology/N18-4020 | |
| PWC | https://paperswithcode.com/paper/generating-image-captions-in-arabic-using |
| Repo | |
| Framework | |
License Plate Detection and Recognition in Unconstrained Scenarios
| Title | License Plate Detection and Recognition in Unconstrained Scenarios |
| Authors | Sergio Montazzolli Silva, Claudio Rosito Jung |
| Abstract | Despite the large number of both commercial and academic methods for Automatic License Plate Recognition (ALPR), most existing approaches are focused on a specific license plate (LP) region (e.g. European, US, Brazilian, Taiwanese, etc.), and frequently explore datasets containing approximately frontal images. This work proposes a complete ALPR system focusing on unconstrained capture scenarios, where the LP might be considerably distorted due to oblique views. Our main contribution is the introduction of a novel Convolutional Neural Network (CNN) capable of detecting and rectifying multiple distorted license plates in a single image, which are fed to an Optical Character Recognition (OCR) method to obtain the final result. As an additional contribution, we also present manual annotations for a challenging set of LP images from different regions and acquisition conditions. Our experimental results indicate that the proposed method, without any parameter adaptation or fine tuning for a specific scenario, performs similarly to state-of-the-art commercial systems in traditional datasets, and outperforms both academic and commercial approaches in challenging datasets. |
| Tasks | License Plate Recognition, Optical Character Recognition |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Sergio_Silva_License_Plate_Detection_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Sergio_Silva_License_Plate_Detection_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/license-plate-detection-and-recognition-in |
| Repo | |
| Framework | |
Towards a Language for Natural Language Treebank Transductions
| Title | Towards a Language for Natural Language Treebank Transductions |
| Authors | Carlos A. Prolo |
| Abstract | This paper describes a transduction language suitable for natural language treebank transformations and motivates its application to tasks that have been used and described in the literature. The language, which is the basis for a tree transduction tool allows for clean, precise and concise description of what has been very confusingly, ambiguously, and incompletely textually described in the literature also allowing easy non-hard-coded implementation. We also aim at getting feedback from the NLP community to eventually converge to a de facto standard for such transduction language. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1087/ |
| https://www.aclweb.org/anthology/C18-1087 | |
| PWC | https://paperswithcode.com/paper/towards-a-language-for-natural-language |
| Repo | |
| Framework | |
Deep Face Detector Adaptation Without Negative Transfer or Catastrophic Forgetting
| Title | Deep Face Detector Adaptation Without Negative Transfer or Catastrophic Forgetting |
| Authors | Muhammad Abdullah Jamal, Haoxiang Li, Boqing Gong |
| Abstract | Arguably, no single face detector fits all real-life scenarios. It is often desirable to have some built-in schemes for a face detector to automatically adapt, e.g., to a particular user’s photo album (the target domain). We propose a novel face detector adaptation approach that works as long as there are representative images of the target domain no matter they are labeled or not and, more importantly, without the need of accessing the training data of the source domain. Our approach explicitly accounts for the notorious negative transfer caveat in domain adaptation thanks to a residual loss by design. Moreover, it does not incur catastrophic interference with the knowledge learned from the source domain and, therefore, the adapted face detectors maintain about the same performance as the old detectors in the original source domain. As such, our adaption approach to face detectors is analogous to the popular interpolation techniques for language models; it may opens a new direction for progressively training the face detectors domain by domain. We report extensive experimental results to verify our approach on two massively benchmarked face detectors. |
| Tasks | Domain Adaptation |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Jamal_Deep_Face_Detector_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Jamal_Deep_Face_Detector_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-face-detector-adaptation-without |
| Repo | |
| Framework | |
Computational Models for Spatial Prepositions
| Title | Computational Models for Spatial Prepositions |
| Authors | Georgiy Platonov, Lenhart Schubert |
| Abstract | Developing computational models of spatial prepositions (such as on, in, above, etc.) is crucial for such tasks as human-machine collaboration, story understanding, and 3D model generation from descriptions. However, these prepositions are notoriously vague and ambiguous, with meanings depending on the types, shapes and sizes of entities in the argument positions, the physical and task context, and other factors. As a result truth value judgments for prepositional relations are often uncertain and variable. In this paper we treat the modeling task as calling for assignment of probabilities to such relations as a function of multiple factors, where such probabilities can be viewed as estimates of whether humans would judge the relations to hold in given circumstances. We implemented our models in a 3D blocks world and a room world in a computer graphics setting, and found that true/false judgments based on these models do not differ much more from human judgments that the latter differ from one another. However, what really matters pragmatically is not the accuracy of truth value judgments but whether, for instance, the computer models suffice for identifying objects described in terms of prepositional relations, (e.g., {``}the box to the left of the table{''}, where there are multiple boxes). For such tasks, our models achieved accuracies above 90{%} for most relations. | |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-1403/ |
| https://www.aclweb.org/anthology/W18-1403 | |
| PWC | https://paperswithcode.com/paper/computational-models-for-spatial-prepositions |
| Repo | |
| Framework | |
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Tutorial Abstracts
| Title | Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Tutorial Abstracts |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-6000/ |
| https://www.aclweb.org/anthology/N18-6000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2018-conference-of-the |
| Repo | |
| Framework | |
Compositing-aware Image Search
| Title | Compositing-aware Image Search |
| Authors | Hengshuang Zhao, Xiaohui Shen, Zhe Lin, Kalyan Sunkavalli, Brian Price, Jiaya Jia |
| Abstract | We present a new image search technique that, given a background image, returns compatible foreground objects for image compositing tasks. The compatibility of a foreground object and a background scene depends on various aspects such as semantics, surrounding context, geometry, style and color. However, existing image search techniques measure the similarities on only a few aspects, and may return many results that are not suitable for compositing. Moreover, the importance of each factor may vary for different object categories and image content, making it difficult to manually define the matching criteria. In this paper, we propose to learn feature representations for foreground objects and background scenes respectively, where image content and object category information are jointly encoded during training. As a result, the learned features can adaptively encode the most important compatibility factors. We project the features to a common embedding space, so that the compatibility scores can be easily measured using the cosine similarity, enabling very efficient search. We collect an evaluation set consisting of eight object categories commonly used in compositing tasks, on which we demonstrate that our approach significantly outperforms other search techniques. |
| Tasks | Image Retrieval |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Hengshuang_Zhao_Compositing-aware_Image_Search_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Hengshuang_Zhao_Compositing-aware_Image_Search_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/compositing-aware-image-search |
| Repo | |
| Framework | |
Attention Regularized Sequence-to-Sequence Learning for E2E NLG Challenge
| Title | Attention Regularized Sequence-to-Sequence Learning for E2E NLG Challenge |
| Authors | Biao Zhang, Jing Yang, Qian Lin, Jinsong Su |
| Abstract | This paper describes our system used for the end-to-end (E2E) natural language generation (NLG) challenge. The challenge collects a novel dataset for spoken dialogue system in the restaurant domain, which shows more lexical richness and syntactic variation and requires content selection (Novikova et al., 2017). To solve this challenge, we employ the CAEncoder-enhanced sequence-tosequence learning model (Zhang et al., 2017) and propose an attention regularizer to spread attention weights across input words as well as control the overfitting problem. Without any specific designation, our system yields very promising performance. Particularly, our system achieves a ROUGE-L score of 0.7083, the best result among all submitted primary systems. |
| Tasks | Data-to-Text Generation, Text Generation |
| Published | 2018-03-01 |
| URL | http://www.macs.hw.ac.uk/InteractionLab/E2E/final_papers/E2E-Zhang.pdf |
| http://www.macs.hw.ac.uk/InteractionLab/E2E/final_papers/E2E-Zhang.pdf | |
| PWC | https://paperswithcode.com/paper/attention-regularized-sequence-to-sequence |
| Repo | |
| Framework | |
A Treebank for the Healthcare Domain
| Title | A Treebank for the Healthcare Domain |
| Authors | Nganthoibi Oinam, Diwakar Mishra, Pinal Patel, Narayan Choudhary, Hitesh Desai |
| Abstract | This paper presents a treebank for the healthcare domain developed at ezDI. The treebank is created from a wide array of clinical health record documents across hospitals. The data has been de-identified and annotated for constituent syntactic structure. The treebank contains a total of 52053 sentences that have been sampled for subdomains as well as linguistic variations. The paper outlines the sampling process followed to ensure a better domain representation in the corpus, the annotation process and challenges, and corpus statistics. The Penn Treebank tagset and guidelines were largely followed, but there were many syntactic contexts that warranted adaptation of the guidelines. The treebank created was used to re-train the Berkeley parser and the Stanford parser. These parsers were also trained with the GENIA treebank for comparative quality assessment. Our treebank yielded great-er accuracy on both parsers. Berkeley parser performed better on our treebank with an average F1 measure of 91 across 5-folds. This was a significant jump from the out-of-the-box F1 score of 70 on Berkeley parser{'}s default grammar. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4916/ |
| https://www.aclweb.org/anthology/W18-4916 | |
| PWC | https://paperswithcode.com/paper/a-treebank-for-the-healthcare-domain |
| Repo | |
| Framework | |
Exploiting Partially Annotated Data in Temporal Relation Extraction
| Title | Exploiting Partially Annotated Data in Temporal Relation Extraction |
| Authors | Qiang Ning, Zhongzhi Yu, Chuchu Fan, Dan Roth |
| Abstract | Annotating temporal relations (TempRel) between events described in natural language is known to be labor intensive, partly because the total number of TempRels is quadratic in the number of events. As a result, only a small number of documents are typically annotated, limiting the coverage of various lexical/semantic phenomena. In order to improve existing approaches, one possibility is to make use of the readily available, partially annotated data (P as in partial) that cover more documents. However, missing annotations in P are known to hurt, rather than help, existing systems. This work is a case study in exploring various usages of P for TempRel extraction. Results show that despite missing annotations, P is still a useful supervision signal for this task within a constrained bootstrapping learning framework. The system described in this system is publicly available. |
| Tasks | Relation Extraction |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-2018/ |
| https://www.aclweb.org/anthology/S18-2018 | |
| PWC | https://paperswithcode.com/paper/exploiting-partially-annotated-data-in |
| Repo | |
| Framework | |
Effects of truck traffic on crash injury severity on rural highways in Wyoming using Bayesian binary logit models
| Title | Effects of truck traffic on crash injury severity on rural highways in Wyoming using Bayesian binary logit models |
| Authors | Mohamed M. Ahmed, Rebecca Franke, Khaled Ksaibati, Debbie S. Shinstine |
| Abstract | Roadway safety is an integral part of a functioning infrastructure. A major use of the highway system is the transport of goods. The United States has experienced constant growth in the amount of freight transported by truck in the last few years. Wyoming is experiencing a large increase in truck traffic on its local and county roads due to an increase in oil and gas production. This study explores the involvement of heavy trucks in crashes and their significance as a predictor of crash severity and addresses the effect that large truck traffic is having on the safety of roadways for various road classifications. Studies have been done on the factors involved in and the causation of heavy truck crashes, but none address the causation and effect of roadway classifications on truck crashes. Binary Logit Models (BLM) with Bayesian inferences were utilized to classify heavy truck involvement in severe and non-severe crashes using ten years (2002–2011) of historical crash data in the State of Wyoming. From the final main effects model, various interactions proved to be significant in predicting the severity of crashes and varied depending on the roadway classification. The results indicated the odds of a severe crash increase to 2.3 and 4.5 times when a heavy truck is involved on state and interstate highways respectively. The severity of crashes is significantly increased when road conditions were not clear, icy, and during snowy weather conditions. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://sciencedirect.xilesou.top/science/article/pii/S0001457518301507 |
| https://sciencedirect.xilesou.top/science/article/pii/S0001457518301507 | |
| PWC | https://paperswithcode.com/paper/effects-of-truck-traffic-on-crash-injury |
| Repo | |
| Framework | |
A Bi-Directional Message Passing Model for Salient Object Detection
| Title | A Bi-Directional Message Passing Model for Salient Object Detection |
| Authors | Lu Zhang, Ju Dai, Huchuan Lu, You He, Gang Wang |
| Abstract | Recent progress on salient object detection is beneficial from Fully Convolutional Neural Network (FCN). The saliency cues contained in multi-level convolutional features are complementary for detecting salient objects. How to integrate multi-level features becomes an open problem in saliency detection. In this paper, we propose a novel bi-directional message passing model to integrate multi-level features for salient object detection. At first, we adopt a Multi-scale Context-aware Feature Extraction Module (MCFEM) for multi-level feature maps to capture rich context information. Then a bi-directional structure is designed to pass messages between multi-level features, and a gate function is exploited to control the message passing rate. We use the features after message passing, which simultaneously encode semantic information and spatial details, to predict saliency maps. Finally, the predicted results are efficiently combined to generate the final saliency map. Quantitative and qualitative experiments on five benchmark datasets demonstrate that our proposed model performs favorably against the state-of-the-art methods under different evaluation metrics. |
| Tasks | Object Detection, Saliency Detection, Salient Object Detection |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Zhang_A_Bi-Directional_Message_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_A_Bi-Directional_Message_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/a-bi-directional-message-passing-model-for |
| Repo | |
| Framework | |
A Speaking Atlas of the Regional Languages of France
| Title | A Speaking Atlas of the Regional Languages of France |
| Authors | Philippe Boula de Mare{"u}il, Albert Rilliard, Fr{'e}d{'e}ric Vernier |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1652/ |
| https://www.aclweb.org/anthology/L18-1652 | |
| PWC | https://paperswithcode.com/paper/a-speaking-atlas-of-the-regional-languages-of |
| Repo | |
| Framework | |
Entropy-SGD optimizes the prior of a PAC-Bayes bound: Data-dependent PAC-Bayes priors via differential privacy
| Title | Entropy-SGD optimizes the prior of a PAC-Bayes bound: Data-dependent PAC-Bayes priors via differential privacy |
| Authors | Gintare Karolina Dziugaite, Daniel M. Roy |
| Abstract | We show that Entropy-SGD (Chaudhari et al., 2017), when viewed as a learning algorithm, optimizes a PAC-Bayes bound on the risk of a Gibbs (posterior) classifier, i.e., a randomized classifier obtained by a risk-sensitive perturbation of the weights of a learned classifier. Entropy-SGD works by optimizing the bound’s prior, violating the hypothesis of the PAC-Bayes theorem that the prior is chosen independently of the data. Indeed, available implementations of Entropy-SGD rapidly obtain zero training error on random labels and the same holds of the Gibbs posterior. In order to obtain a valid generalization bound, we show that an ε-differentially private prior yields a valid PAC-Bayes bound, a straightforward consequence of results connecting generalization with differential privacy. Using stochastic gradient Langevin dynamics (SGLD) to approximate the well-known exponential release mechanism, we observe that generalization error on MNIST (measured on held out data) falls within the (empirically nonvacuous) bounds computed under the assumption that SGLD produces perfect samples. In particular, Entropy-SGLD can be configured to yield relatively tight generalization bounds and still fit real labels, although these same settings do not obtain state-of-the-art performance. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=ry9tUX_6- |
| https://openreview.net/pdf?id=ry9tUX_6- | |
| PWC | https://paperswithcode.com/paper/entropy-sgd-optimizes-the-prior-of-a-pac-1 |
| Repo | |
| Framework | |
