Paper Group NANR 156
A Case Study on Meaning Representation for Vietnamese. LTRC-MT Simple & Effective Hindi-English Neural Machine Translation Systems at WAT 2019. Sensitive-Sample Fingerprinting of Deep Neural Networks. User-Specified Local Differential Privacy in Unconstrained Adaptive Online Learning. Auto-FPN: Automatic Network Architecture Adaptation for Object …
A Case Study on Meaning Representation for Vietnamese
| Title | A Case Study on Meaning Representation for Vietnamese |
| Authors | Ha Linh, Huyen Nguyen |
| Abstract | This paper presents a case study on meaning representation for Vietnamese. Having introduced several existing semantic representation schemes for different languages, we select as basis for our work on Vietnamese AMR (Abstract Meaning Representation). From it, we define a meaning representation label set by adapting the English schema and taking into account the specific characteristics of Vietnamese. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3317/ |
| https://www.aclweb.org/anthology/W19-3317 | |
| PWC | https://paperswithcode.com/paper/a-case-study-on-meaning-representation-for |
| Repo | |
| Framework | |
LTRC-MT Simple & Effective Hindi-English Neural Machine Translation Systems at WAT 2019
| Title | LTRC-MT Simple & Effective Hindi-English Neural Machine Translation Systems at WAT 2019 |
| Authors | Vikrant Goyal, Dipti Misra Sharma |
| Abstract | This paper describes the Neural Machine Translation systems of IIIT-Hyderabad (LTRC-MT) for WAT 2019 Hindi-English shared task. We experimented with both Recurrent Neural Networks {&} Transformer architectures. We also show the results of our experiments of training NMT models using additional data via backtranslation. |
| Tasks | Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5216/ |
| https://www.aclweb.org/anthology/D19-5216 | |
| PWC | https://paperswithcode.com/paper/ltrc-mt-simple-textbackslash-effective-hindi |
| Repo | |
| Framework | |
Sensitive-Sample Fingerprinting of Deep Neural Networks
| Title | Sensitive-Sample Fingerprinting of Deep Neural Networks |
| Authors | Zecheng He, Tianwei Zhang, Ruby Lee |
| Abstract | Numerous cloud-based services are provided to help customers develop and deploy deep learning applications. When a customer deploys a deep learning model in the cloud and serves it to end-users, it is important to be able to verify that the deployed model has not been tampered with. In this paper, we propose a novel and practical methodology to verify the integrity of remote deep learning models, with only black-box access to the target models. Specifically, we define Sensitive-Sample fingerprints, which are a small set of human unnoticeable transformed inputs that make the model outputs sensitive to the model’s parameters. Even small model changes can be clearly reflected in the model outputs. Experimental results on different types of model integrity attacks show that we proposed approach is both effective and efficient. It can detect model integrity breaches with high accuracy (>99.95%) and guaranteed zero false positives on all evaluated attacks. Meanwhile, it only requires up to 103X fewer model inferences, compared with non-sensitive samples. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/He_Sensitive-Sample_Fingerprinting_of_Deep_Neural_Networks_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/He_Sensitive-Sample_Fingerprinting_of_Deep_Neural_Networks_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/sensitive-sample-fingerprinting-of-deep |
| Repo | |
| Framework | |
User-Specified Local Differential Privacy in Unconstrained Adaptive Online Learning
| Title | User-Specified Local Differential Privacy in Unconstrained Adaptive Online Learning |
| Authors | Dirk Van Der Hoeven |
| Abstract | Local differential privacy is a strong notion of privacy in which the provider of the data guarantees privacy by perturbing the data with random noise. In the standard application of local differential differential privacy the distribution of the noise is constant and known by the learner. In this paper we generalize this approach by allowing the provider of the data to choose the distribution of the noise without disclosing any parameters of the distribution to the learner, under the constraint that the distribution is symmetrical. We consider this problem in the unconstrained Online Convex Optimization setting with noisy feedback. In this setting the learner receives the subgradient of a loss function, perturbed by noise, and aims to achieve sublinear regret with respect to some competitor, without constraints on the norm of the competitor. We derive the first algorithms that have adaptive regret bounds in this setting, i.e. our algorithms adapt to the unknown competitor norm, unknown noise, and unknown sum of the norms of the subgradients, matching state of the art bounds in all cases. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9557-user-specified-local-differential-privacy-in-unconstrained-adaptive-online-learning |
| http://papers.nips.cc/paper/9557-user-specified-local-differential-privacy-in-unconstrained-adaptive-online-learning.pdf | |
| PWC | https://paperswithcode.com/paper/user-specified-local-differential-privacy-in |
| Repo | |
| Framework | |
Auto-FPN: Automatic Network Architecture Adaptation for Object Detection Beyond Classification
| Title | Auto-FPN: Automatic Network Architecture Adaptation for Object Detection Beyond Classification |
| Authors | Hang Xu, Lewei Yao, Wei Zhang, Xiaodan Liang, Zhenguo Li |
| Abstract | Abstract Neural architecture search (NAS) has shown great potential in automating the manual process of designing a good CNN architecture for image classification. In this paper, we study NAS for object detection, a core computer vision task that classifies and localizes object instances in an image. Existing works focus on transferring the searched architecture from classification task (ImageNet) to the detector backbone, while the rest of the architecture of the detector remains unchanged. However, this pipeline is not task-specific or data-oriented network search which cannot guarantee optimal adaptation to any dataset. Therefore, we propose an architecture search framework named Auto-FPN specifically designed for detection beyond simply searching a classification backbone. Specifically, we propose two auto search modules for detection: Auto-fusion to search a better fusion of the multi-level features; Auto-head to search a better structure for classification and bounding-box(bbox) regression. Instead of searching for one repeatable cell structure, we relax the constraint and allow different cells. The search space of both modules covers many popular designs of detectors and allows efficient gradient-based architecture search with resource constraint (2 days for COCO on 8 GPU cards). Extensive experiments on Pascal VOC, COCO, BDD, VisualGenome and ADE demonstrate the effectiveness of the proposed method, e.g. achieving around 5% improvement than FPN in terms of mAP while requiring around 50% fewer parameters on the searched modules. |
| Tasks | Image Classification, Neural Architecture Search, Object Detection |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Xu_Auto-FPN_Automatic_Network_Architecture_Adaptation_for_Object_Detection_Beyond_Classification_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Xu_Auto-FPN_Automatic_Network_Architecture_Adaptation_for_Object_Detection_Beyond_Classification_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/auto-fpn-automatic-network-architecture |
| Repo | |
| Framework | |
Towards Generating Math Word Problems from Equations and Topics
| Title | Towards Generating Math Word Problems from Equations and Topics |
| Authors | Qingyu Zhou, Danqing Huang |
| Abstract | A math word problem is a narrative with a specific topic that provides clues to the correct equation with numerical quantities and variables therein. In this paper, we focus on the task of generating math word problems. Previous works are mainly template-based with pre-defined rules. We propose a novel neural network model to generate math word problems from the given equations and topics. First, we design a fusion mechanism to incorporate the information of both equations and topics. Second, an entity-enforced loss is introduced to ensure the relevance between the generated math problem and the equation. Automatic evaluation results show that the proposed model significantly outperforms the baseline models. In human evaluations, the math word problems generated by our model are rated as being more relevant (in terms of solvability of the given equations and relevance to topics) and natural (i.e., grammaticality, fluency) than the baseline models. |
| Tasks | |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8661/ |
| https://www.aclweb.org/anthology/W19-8661 | |
| PWC | https://paperswithcode.com/paper/towards-generating-math-word-problems-from |
| Repo | |
| Framework | |
TMU Transformer System Using BERT for Re-ranking at BEA 2019 Grammatical Error Correction on Restricted Track
| Title | TMU Transformer System Using BERT for Re-ranking at BEA 2019 Grammatical Error Correction on Restricted Track |
| Authors | Masahiro Kaneko, Kengo Hotate, Satoru Katsumata, Mamoru Komachi |
| Abstract | We introduce our system that is submitted to the restricted track of the BEA 2019 shared task on grammatical error correction1 (GEC). It is essential to select an appropriate hypothesis sentence from the candidates list generated by the GEC model. A re-ranker can evaluate the naturalness of a corrected sentence using language models trained on large corpora. On the other hand, these language models and language representations do not explicitly take into account the grammatical errors written by learners. Thus, it is not straightforward to utilize language representations trained from a large corpus, such as Bidirectional Encoder Representations from Transformers (BERT), in a form suitable for the learner{'}s grammatical errors. Therefore, we propose to fine-tune BERT on learner corpora with grammatical errors for re-ranking. The experimental results of the W{&}I+LOCNESS development dataset demonstrate that re-ranking using BERT can effectively improve the correction performance. |
| Tasks | Grammatical Error Correction |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4422/ |
| https://www.aclweb.org/anthology/W19-4422 | |
| PWC | https://paperswithcode.com/paper/tmu-transformer-system-using-bert-for-re |
| Repo | |
| Framework | |
Joint Multi-Label Attention Networks for Social Text Annotation
| Title | Joint Multi-Label Attention Networks for Social Text Annotation |
| Authors | Hang Dong, Wei Wang, Kaizhu Huang, Frans Coenen |
| Abstract | We propose a novel attention network for document annotation with user-generated tags. The network is designed according to the human reading and annotation behaviour. Usually, users try to digest the title and obtain a rough idea about the topic first, and then read the content of the document. Present research shows that the title metadata could largely affect the social annotation. To better utilise this information, we design a framework that separates the title from the content of a document and apply a title-guided attention mechanism over each sentence in the content. We also propose two semantic-based loss regularisers that enforce the output of the network to conform to label semantics, i.e. similarity and subsumption. We analyse each part of the proposed system with two real-world open datasets on publication and question annotation. The integrated approach, Joint Multi-label Attention Network (JMAN), significantly outperformed the Bidirectional Gated Recurrent Unit (Bi-GRU) by around 13{%}-26{%} and the Hierarchical Attention Network (HAN) by around 4{%}-12{%} on both datasets, with around 10{%}-30{%} reduction of training time. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1136/ |
| https://www.aclweb.org/anthology/N19-1136 | |
| PWC | https://paperswithcode.com/paper/joint-multi-label-attention-networks-for |
| Repo | |
| Framework | |
Beyond Context: A New Perspective for Word Embeddings
| Title | Beyond Context: A New Perspective for Word Embeddings |
| Authors | Yichu Zhou, Vivek Srikumar |
| Abstract | Most word embeddings today are trained by optimizing a language modeling goal of scoring words in their context, modeled as a multi-class classification problem. In this paper, we argue that, despite the successes of this assumption, it is incomplete: in addition to its context, orthographical or morphological aspects of words can offer clues about their meaning. We define a new modeling framework for training word embeddings that captures this intuition. Our framework is based on the well-studied problem of multi-label classification and, consequently, exposes several design choices for featurizing words and contexts, loss functions for training and score normalization. Indeed, standard models such as CBOW and fasttext are specific choices along each of these axes. We show via experiments that by combining feature engineering with embedding learning, our method can outperform CBOW using only 10{%} of the training data in both the standard word embedding evaluations and also text classification experiments. |
| Tasks | Feature Engineering, Language Modelling, Multi-Label Classification, Text Classification, Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-1003/ |
| https://www.aclweb.org/anthology/S19-1003 | |
| PWC | https://paperswithcode.com/paper/beyond-context-a-new-perspective-for-word |
| Repo | |
| Framework | |
Learning spatiotemporal representations for human fall detection in surveillance video
| Title | Learning spatiotemporal representations for human fall detection in surveillance video |
| Authors | Yongqiang Kong, Jianhui Huang, Shanshan Huang, Zhengang Wei, Shengke Wang |
| Abstract | In this paper, a computer vision based framework is proposed that detects falls from surveillance videos. Firstly, we employ background subtraction and rank pooling to model spatial and temporal representations in videos, respectively. We then introduce a novel three-stream Convolutional Neural Networks as an event classifier. Silhouettes and their motion history images serve as input to the first two streams, while dynamic images whose temporal duration is equal to motion history images, are used as input to the third stream. Finally, we apply voting on the results of event classification to perform multicamera fall detection. The main novelty of our method against the conventional ones is that highquality spatiotemporal representations in different levels are learned to take full advantage of the appearance and motion information. Extensive experiments have been conducted on two widely used fall datasets. The results have shown to demonstrate the effectiveness of the proposed method. |
| Tasks | |
| Published | 2019-01-12 |
| URL | https://doi.org/10.1016/j.jvcir.2019.01.024 |
| https://arxiv.org/pdf/1806.11230.pdf | |
| PWC | https://paperswithcode.com/paper/learning-spatiotemporal-representations-for |
| Repo | |
| Framework | |
Bilinear Attention Networks for Person Retrieval
| Title | Bilinear Attention Networks for Person Retrieval |
| Authors | Pengfei Fang, Jieming Zhou, Soumava Kumar Roy, Lars Petersson, Mehrtash Harandi |
| Abstract | This paper investigates a novel Bilinear attention (Bi-attention) block, which discovers and uses second order statistical information in an input feature map, for the purpose of person retrieval. The Bi-attention block uses bilinear pooling to model the local pairwise feature interactions along each channel, while preserving the spatial structural information. We propose an Attention in Attention (AiA) mechanism to build inter-dependency among the second order local and global features with the intent to make better use of, or pay more attention to, such higher order statistical relationships. The proposed network, equipped with the proposed Bi-attention is referred to as Bilinear ATtention network (BAT-net). Our approach outperforms current state-of-the-art by a considerable margin across the standard benchmark datasets (e.g., CUHK03, Market-1501, DukeMTMC-reID and MSMT17). |
| Tasks | Person Retrieval |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Fang_Bilinear_Attention_Networks_for_Person_Retrieval_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Fang_Bilinear_Attention_Networks_for_Person_Retrieval_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/bilinear-attention-networks-for-person |
| Repo | |
| Framework | |
Relation Prediction for Unseen-Entities Using Entity-Word Graphs
| Title | Relation Prediction for Unseen-Entities Using Entity-Word Graphs |
| Authors | Yuki Tagawa, Motoki Taniguchi, Yasuhide Miura, Tomoki Taniguchi, Tomoko Ohkuma, Takayuki Yamamoto, Keiichi Nemoto |
| Abstract | Knowledge graphs (KGs) are generally used for various NLP tasks. However, as KGs still miss some information, it is necessary to develop Knowledge Graph Completion (KGC) methods. Most KGC researches do not focus on the Out-of-KGs entities (Unseen-entities), we need a method that can predict the relation for the entity pairs containing Unseen-entities to automatically add new entities to the KGs. In this study, we focus on relation prediction and propose a method to learn entity representations via a graph structure that uses Seen-entities, Unseen-entities and words as nodes created from the descriptions of all entities. In the experiments, our method shows a significant improvement in the relation prediction for the entity pairs containing Unseen-entities. |
| Tasks | Knowledge Graph Completion, Knowledge Graphs |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5302/ |
| https://www.aclweb.org/anthology/D19-5302 | |
| PWC | https://paperswithcode.com/paper/relation-prediction-for-unseen-entities-using |
| Repo | |
| Framework | |
Parallel Corpus Filtering Based on Fuzzy String Matching
| Title | Parallel Corpus Filtering Based on Fuzzy String Matching |
| Authors | Sukanta Sen, Asif Ekbal, Pushpak Bhattacharyya |
| Abstract | In this paper, we describe the IIT Patna{'}s submission to WMT 2019 shared task on parallel corpus filtering. This shared task asks the participants to develop methods for scoring each parallel sentence from a given noisy parallel corpus. Quality of the scoring method is judged based on the quality of SMT and NMT systems trained on smaller set of high-quality parallel sentences sub-sampled from the original noisy corpus. This task has two language pairs. We submit for both the Nepali-English and Sinhala-English language pairs. We define fuzzy string matching score between English and the translated (into English) source based on Levenshtein distance. Based on the scores, we sub-sample two sets (having 1 million and 5 millions English tokens) of parallel sentences from each parallel corpus, and train SMT systems for development purpose only. The organizers publish the official evaluation using both SMT and NMT on the final official test set. Total 10 teams participated in the shared task and according the official evaluation, our scoring method obtains 2nd position in the team ranking for 1-million NepaliEnglish NMT and 5-million Sinhala-English NMT categories. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5440/ |
| https://www.aclweb.org/anthology/W19-5440 | |
| PWC | https://paperswithcode.com/paper/parallel-corpus-filtering-based-on-fuzzy |
| Repo | |
| Framework | |
A user study to compare two conversational assistants designed for people with hearing impairments
| Title | A user study to compare two conversational assistants designed for people with hearing impairments |
| Authors | Anja Virkkunen, Juri Lukkarila, Kalle Palom{"a}ki, Mikko Kurimo |
| Abstract | Participating in conversations can be difficult for people with hearing loss, especially in acoustically challenging environments. We studied the preferences the hearing impaired have for a personal conversation assistant based on automatic speech recognition (ASR) technology. We created two prototypes which were evaluated by hearing impaired test users. This paper qualitatively compares the two based on the feedback obtained from the tests. The first prototype was a proof-of-concept system running real-time ASR on a laptop. The second prototype was developed for a mobile device with the recognizer running on a separate server. In the mobile device, augmented reality (AR) was used to help the hearing impaired observe gestures and lip movements of the speaker simultaneously with the transcriptions. Several testers found the systems useful enough to use in their daily lives, with majority preferring the mobile AR version. The biggest concern of the testers was the accuracy of the transcriptions and the lack of speaker identification. |
| Tasks | Speaker Identification, Speech Recognition |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1701/ |
| https://www.aclweb.org/anthology/W19-1701 | |
| PWC | https://paperswithcode.com/paper/a-user-study-to-compare-two-conversational |
| Repo | |
| Framework | |
Feedback Adversarial Learning: Spatial Feedback for Improving Generative Adversarial Networks
| Title | Feedback Adversarial Learning: Spatial Feedback for Improving Generative Adversarial Networks |
| Authors | Minyoung Huh, Shao-Hua Sun, Ning Zhang |
| Abstract | We propose feedback adversarial learning (FAL) framework that can improve existing generative adversarial networks by leveraging spatial feedback from the discriminator. We formulate the generation task as a recurrent framework, in which the discriminator’s feedback is integrated into the feedforward path of the generation process. Specifically, the generator conditions on the discriminator’s spatial output response, and its previous generation to improve generation quality over time - allowing the generator to attend and fix its previous mistakes. To effectively utilize the feedback, we propose an adaptive spatial transform layer, which learns to spatially modulate feature maps from its previous generation and the error signal from the discriminator. We demonstrate that one can easily adapt FAL to existing adversarial learning frameworks on a wide range of tasks, including image generation, image-to-image translation, and voxel generation. |
| Tasks | Image Generation, Image-to-Image Translation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Huh_Feedback_Adversarial_Learning_Spatial_Feedback_for_Improving_Generative_Adversarial_Networks_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Huh_Feedback_Adversarial_Learning_Spatial_Feedback_for_Improving_Generative_Adversarial_Networks_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/feedback-adversarial-learning-spatial |
| Repo | |
| Framework | |
