Paper Group NANR 267
Neural and rule-based Finnish NLP models—expectations, experiments and experiences. Quantifier-free least fixed point functions for phonology. Unbounded Stress in Subregular Phonology. On the Role of Scene Graphs in Image Captioning. Learning to Rank Proposals for Object Detection. ToothNet: Automatic Tooth Instance Segmentation and Identificatio …
Neural and rule-based Finnish NLP models—expectations, experiments and experiences
| Title | Neural and rule-based Finnish NLP models—expectations, experiments and experiences |
| Authors | Tommi A Pirinen |
| Abstract | |
| Tasks | Dependency Parsing, Language Modelling, Machine Translation |
| Published | 2019-01-01 |
| URL | https://www.aclweb.org/anthology/W19-0309/ |
| https://www.aclweb.org/anthology/W19-0309 | |
| PWC | https://paperswithcode.com/paper/neural-and-rule-based-finnish-nlp-models |
| Repo | |
| Framework | |
Quantifier-free least fixed point functions for phonology
| Title | Quantifier-free least fixed point functions for phonology |
| Authors | Ch, Jane lee, Adam Jardine |
| Abstract | |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/W19-5705/ |
| https://www.aclweb.org/anthology/W19-5705 | |
| PWC | https://paperswithcode.com/paper/quantifier-free-least-fixed-point-functions |
| Repo | |
| Framework | |
Unbounded Stress in Subregular Phonology
| Title | Unbounded Stress in Subregular Phonology |
| Authors | Yiding Hao, Samuel Andersson |
| Abstract | This paper situates culminative unbounded stress systems within the subregular hierarchy for functions. While Baek (2018) has argued that such systems can be uniformly understood as input tier-based strictly local constraints, we show here that default-to-opposite-side and default-to-same-side stress systems belong to distinct subregular classes when they are viewed as functions that assign primary stress to underlying forms. While the former system can be captured by input tier-based input strictly local functions, a subsequential function class that we define here, the latter system is not subsequential, though it is weakly deterministic according to McCollum et al.{'}s (2018) non-interaction criterion. Our results motivate the extension of recently proposed subregular language classes to subregular functions and argue in favor of McCollum et al{'}s definition of weak determinism over that of Heinz and Lai (2013). |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4216/ |
| https://www.aclweb.org/anthology/W19-4216 | |
| PWC | https://paperswithcode.com/paper/unbounded-stress-in-subregular-phonology |
| Repo | |
| Framework | |
On the Role of Scene Graphs in Image Captioning
| Title | On the Role of Scene Graphs in Image Captioning |
| Authors | Dalin Wang, Daniel Beck, Trevor Cohn |
| Abstract | Scene graphs represent semantic information in images, which can help image captioning system to produce more descriptive outputs versus using only the image as context. Recent captioning approaches rely on ad-hoc approaches to obtain graphs for images. However, those graphs introduce noise and it is unclear the effect of parser errors on captioning accuracy. In this work, we investigate to what extent scene graphs can help image captioning. Our results show that a state-of-the-art scene graph parser can boost performance almost as much as the ground truth graphs, showing that the bottleneck currently resides more on the captioning models than on the performance of the scene graph parser. |
| Tasks | Image Captioning |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6405/ |
| https://www.aclweb.org/anthology/D19-6405 | |
| PWC | https://paperswithcode.com/paper/on-the-role-of-scene-graphs-in-image |
| Repo | |
| Framework | |
Learning to Rank Proposals for Object Detection
| Title | Learning to Rank Proposals for Object Detection |
| Authors | Zhiyu Tan, Xuecheng Nie, Qi Qian, Nan Li, Hao Li |
| Abstract | Non-Maximum Suppression (NMS) is an essential step of modern object detection models for removing duplicated candidates. The efficacy of NMS heavily affects the final detection results. Prior works exploit suppression criterions relying on either the objectiveness derived from classification or the overlapness produced by regression, both of which are heuristically designed and fail to explicitly link with the suppression rank. To address this issue, in this paper, we propose a novel Learning-to-Rank (LTR) model to produce the suppression rank via a learning procedure, thus facilitating the candidate generation and lifting the detection performance. In particular, we define a ranking score based on IoU to indicate the ranks of candidates during the NMS step, where candidates with high ranking score will be reserved and the ones with low ranking score will be eliminated. We design a lightweight network to predict the ranking score. We introduce a ranking loss to supervise the generation of these ranking scores, which encourages candidates with IoU to the ground-truth to rank higher. To facilitate the training procedure, we design a novel sampling strategy via dividing candidates into different levels and select hard pairs to adopt in the training. During the inference phase, this module can be exploited as a plugin to the current object detector. The training and inference of the overall framework is end-to-end. Comprehensive experiments on benchmarks PASCAL VOC and MS COCO demonstrate the generality and effectiveness of our model for facilitating existing object detectors to state-of-the-art accuracy. |
| Tasks | Learning-To-Rank, Object Detection |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Tan_Learning_to_Rank_Proposals_for_Object_Detection_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Tan_Learning_to_Rank_Proposals_for_Object_Detection_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-rank-proposals-for-object |
| Repo | |
| Framework | |
ToothNet: Automatic Tooth Instance Segmentation and Identification From Cone Beam CT Images
| Title | ToothNet: Automatic Tooth Instance Segmentation and Identification From Cone Beam CT Images |
| Authors | Zhiming Cui, Changjian Li, Wenping Wang |
| Abstract | This paper proposes a method that uses deep convolutional neural networks to achieve automatic and accurate tooth instance segmentation and identification from CBCT (cone beam CT) images for digital dentistry. The core of our method is a two-stage network. In the first stage, an edge map is extracted from the input CBCT image to enhance image contrast along shape boundaries. Then this edge map and the input images are passed to the second stage. In the second stage, we build our network upon the 3D region proposal network (RPN) with a novel learned-similarity matrix to help efficiently remove redundant proposals, speed up training and save GPU memory. To resolve the ambiguity in the identification task, we encode teeth spatial relationships as an additional feature input in the identification task, which helps to remarkably improve the identification accuracy. Our evaluation, comparison and comprehensive ablation studies demonstrate that our method produces accurate instance segmentation and identification results automatically and outperforms the state-of-the-art approaches. To the best of our knowledge, our method is the first to use neural networks to achieve automatic tooth segmentation and identification from CBCT images. |
| Tasks | Instance Segmentation, Semantic Segmentation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Cui_ToothNet_Automatic_Tooth_Instance_Segmentation_and_Identification_From_Cone_Beam_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Cui_ToothNet_Automatic_Tooth_Instance_Segmentation_and_Identification_From_Cone_Beam_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/toothnet-automatic-tooth-instance |
| Repo | |
| Framework | |
Authorship Recognition with Short-Text using Graph-based Techniques
| Title | Authorship Recognition with Short-Text using Graph-based Techniques |
| Authors | Laura Cruz |
| Abstract | In recent years, studies of authorship recognition has aroused great interest in graph-based analysis. Modeling the writing style of each author using a network of co-occurrence words. However, short texts can generate some changes in the topology of network that cause impact on techniques of feature extraction based on graph topology. In this work, we evaluate the robustness of global-strategy and local-strategy based on complex network measurements comparing with graph2vec a graph embedding technique based on skip-gram model. The experiment consists of evaluating how each modification in the length of text affects the accuracy of authorship recognition on both techniques using cross-validation and machine learning techniques. |
| Tasks | Graph Embedding |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3649/ |
| https://www.aclweb.org/anthology/W19-3649 | |
| PWC | https://paperswithcode.com/paper/authorship-recognition-with-short-text-using |
| Repo | |
| Framework | |
Amrita School of Engineering - CSE at SemEval-2019 Task 6: Manipulating Attention with Temporal Convolutional Neural Network for Offense Identification and Classification
| Title | Amrita School of Engineering - CSE at SemEval-2019 Task 6: Manipulating Attention with Temporal Convolutional Neural Network for Offense Identification and Classification |
| Authors | Murali Sridharan, Swapna TR |
| Abstract | With the proliferation and ubiquity of smart gadgets and smart devices, across the world, data generated by them has been growing at exponential rates; in particular social media platforms like Facebook, Twitter and Instagram have been generating voluminous data on a daily basis. According to Twitter{'}s usage statistics, about 500 million tweets are generated each day. While the tweets reflect the users{'} opinions on several events across the world, there are tweets which are offensive in nature that need to be tagged under the hateful conduct policy of Twitter. Offensive tweets have to be identified, captured and processed further, for a variety of reasons, which include i) identifying offensive tweets in order to prevent violent/abusive behavior in Twitter (or any social media for that matter), ii) creating and maintaining a history of offensive tweets for individual users (would be helpful in creating meta-data for user profile), iii) inferring the sentiment of the users on particular event/issue/topic . We have employed neural network models which manipulate attention with Temporal Convolutional Neural Network for the three shared sub-tasks i) ATT-TCN (ATTention based Temporal Convolutional Neural Network) employed for shared sub-task A that yielded a best macro-F1 score of 0.46, ii) SAE-ATT-TCN(Self Attentive Embedding-ATTention based Temporal Convolutional Neural Network) employed for shared sub-task B and sub-task C that yielded best macro-F1 score of 0.61 and 0.51 respectively. Among the two variants ATT-TCN and SAE-ATT-TCN, the latter performed better. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2097/ |
| https://www.aclweb.org/anthology/S19-2097 | |
| PWC | https://paperswithcode.com/paper/amrita-school-of-engineering-cse-at-semeval |
| Repo | |
| Framework | |
PostAc : A Visual Interactive Search, Exploration, and Analysis Platform for PhD Intensive Job Postings
| Title | PostAc : A Visual Interactive Search, Exploration, and Analysis Platform for PhD Intensive Job Postings |
| Authors | Chenchen Xu, Inger Mewburn, Will J Grant, Hanna Suominen |
| Abstract | Over 60{%} of Australian PhD graduates land their first job after graduation outside academia, but this job market remains largely hidden to these job seekers. Employers{'} low awareness and interest in attracting PhD graduates means that the term {}PhD{''} is rarely used as a keyword in job advertisements; 80{\%} of companies looking to employ similar researchers do not specifically ask for a PhD qualification. As a result, typing in {}PhD{''} to a job search engine tends to return mostly academic jobs. We set out to make the market for advanced research skills more visible to job seekers. In this paper, we present PostAc, an online platform of authentic job postings that helps PhD graduates sharpen their career thinking. The platform is underpinned by research on the key factors that identify what an employer is looking for when they want to hire a highly skilled researcher. Its ranking model leverages the free-form text embedded in the job description to quantify the most sought-after PhD skills and educate information seekers about the Australian job-market appetite for PhD skills. The platform makes visible the geographic location, industry sector, job title, working hours, continuity, and wage of the research intensive jobs. This is the first data-driven exploration in this field. Both empirical results and online platform will be presented in this paper. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-3008/ |
| https://www.aclweb.org/anthology/P19-3008 | |
| PWC | https://paperswithcode.com/paper/postac-a-visual-interactive-search |
| Repo | |
| Framework | |
Discriminative Feature Learning With Consistent Attention Regularization for Person Re-Identification
| Title | Discriminative Feature Learning With Consistent Attention Regularization for Person Re-Identification |
| Authors | Sanping Zhou, Fei Wang, Zeyi Huang, Jinjun Wang |
| Abstract | Person re-identification (Re-ID) has undergone a rapid development with the blooming of deep neural network. Most methods are very easily affected by target misalignment and background clutter in the training process. In this paper, we propose a simple yet effective feedforward attention network to address the two mentioned problems, in which a novel consistent attention regularizer and an improved triplet loss are designed to learn foreground attentive features for person Re-ID. Specifically, the consistent attention regularizer aims to keep the deduced foreground masks similar from the low-level, mid-level and high-level feature maps. As a result, the network will focus on the foreground regions at the lower layers, which is benefit to learn discriminative features from the foreground regions at the higher layers. Last but not least, the improved triplet loss is introduced to enhance the feature learning capability, which can jointly minimize the intra-class distance and maximize the inter-class distance in each triplet unit. Experimental results on the Market1501, DukeMTMC-reID and CUHK03 datasets have shown that our method outperforms most of the state-of-the-art approaches. |
| Tasks | Person Re-Identification |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Zhou_Discriminative_Feature_Learning_With_Consistent_Attention_Regularization_for_Person_Re-Identification_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Zhou_Discriminative_Feature_Learning_With_Consistent_Attention_Regularization_for_Person_Re-Identification_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/discriminative-feature-learning-with-1 |
| Repo | |
| Framework | |
An Approach to Summarize Concordancers’ Lists Visually to Support Language Learners in UnderstandingWord Usages
| Title | An Approach to Summarize Concordancers’ Lists Visually to Support Language Learners in UnderstandingWord Usages |
| Authors | Yo Ehara |
| Abstract | |
| Tasks | |
| Published | 2019-01-01 |
| URL | https://www.aclweb.org/anthology/W19-8407/ |
| https://www.aclweb.org/anthology/W19-8407 | |
| PWC | https://paperswithcode.com/paper/an-approach-to-summarize-concordancers-lists |
| Repo | |
| Framework | |
incom.py - A Toolbox for Calculating Linguistic Distances and Asymmetries between Related Languages
| Title | incom.py - A Toolbox for Calculating Linguistic Distances and Asymmetries between Related Languages |
| Authors | Marius Mosbach, Irina Stenger, Tania Avgustinova, Dietrich Klakow |
| Abstract | Languages may be differently distant from each other and their mutual intelligibility may be asymmetric. In this paper we introduce incom.py, a toolbox for calculating linguistic distances and asymmetries between related languages. incom.py allows linguist experts to quickly and easily perform statistical analyses and compare those with experimental results. We demonstrate the efficacy of incom.py in an incomprehension experiment on two Slavic languages: Bulgarian and Russian. Using incom.py we were able to validate three methods to measure linguistic distances and asymmetries: Levenshtein distance, word adaptation surprisal, and conditional entropy as predictors of success in a reading intercomprehension experiment. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1094/ |
| https://www.aclweb.org/anthology/R19-1094 | |
| PWC | https://paperswithcode.com/paper/incompy-a-toolbox-for-calculating-linguistic |
| Repo | |
| Framework | |
Challenges of Annotating a Code-Switching Treebank
| Title | Challenges of Annotating a Code-Switching Treebank |
| Authors | {"O}zlem {\c{C}}etino{\u{g}}lu, {\c{C}}a{\u{g}}r{\i} {\c{C}}{"o}ltekin |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7809/ |
| https://www.aclweb.org/anthology/W19-7809 | |
| PWC | https://paperswithcode.com/paper/challenges-of-annotating-a-code-switching |
| Repo | |
| Framework | |
Jointly Extracting Multiple Triplets with Multilayer Translation Constraints
| Title | Jointly Extracting Multiple Triplets with Multilayer Translation Constraints |
| Authors | Zhen Tan, Xiang Zhao, Wei Wang, Weidong Xiao |
| Abstract | Triplets extraction is an essential and pivotal step in automatic knowledge base construction, which captures structural information from unstructured text corpus. Conventional extraction models use a pipeline of named entity recognition and relation classification to extract entities and relations, respectively, which ignore the connection between the two tasks. Recently, several neural network-based models were proposed to tackle the problem, and achieved state-of-the-art performance. However, most of them are unable to extract multiple triplets from a single sentence, which are yet commonly seen in real-life scenarios. To close the gap, we propose in this paper a joint neural extraction model for multitriplets, namely, TME, which is capable of adaptively discovering multiple triplets simultaneously in a sentence via ranking with translation mechanism. In experiment, TME exhibits superior performance and achieves an improvement of 37.6% on F1 score over state-of-the-art competitors. |
| Tasks | Named Entity Recognition, Relation Classification, Relation Extraction |
| Published | 2019-07-17 |
| URL | https://aaai.org/ojs/index.php/AAAI/article/view/4689 |
| https://aaai.org/ojs/index.php/AAAI/article/view/4689/4567 | |
| PWC | https://paperswithcode.com/paper/jointly-extracting-multiple-triplets-with |
| Repo | |
| Framework | |
Compressing Convolutional Neural Networks via Factorized Convolutional Filters
| Title | Compressing Convolutional Neural Networks via Factorized Convolutional Filters |
| Authors | Tuanhui Li, Baoyuan Wu, Yujiu Yang, Yanbo Fan, Yong Zhang, Wei Liu |
| Abstract | This work studies the model compression for deep convolutional neural networks (CNNs) via filter pruning. The workflow of a traditional pruning consists of three sequential stages: pre-training the original model, selecting the pre-trained filters via ranking according to a manually designed criterion (e.g., the norm of filters), and learning the remained filters via fine-tuning. Most existing works follow this pipeline and focus on designing different ranking criteria for filter selection. However, it is difficult to control the performance due to the separation of filter selection and filter learning. In this work, we propose to conduct filter selection and filter learning simultaneously, in a unified model. To this end, we define a factorized convolutional filter (FCF), consisting of a standard real-valued convolutional filter and a binary scalar, as well as a dot-product operator between them. We train a CNN model with factorized convolutional filters (CNN-FCF) by updating the standard filter using back-propagation, while updating the binary scalar using the alternating direction method of multipliers (ADMM) based optimization method. With this trained CNN-FCF model, we only keep the standard filters corresponding to the 1-valued scalars, while all other filters and all binary scalars are discarded, to obtain a compact CNN model. Extensive experiments on CIFAR-10 and ImageNet demonstrate the superiority of the proposed method over state-of-the-art filter pruning methods. |
| Tasks | Model Compression |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Li_Compressing_Convolutional_Neural_Networks_via_Factorized_Convolutional_Filters_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Li_Compressing_Convolutional_Neural_Networks_via_Factorized_Convolutional_Filters_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/compressing-convolutional-neural-networks-via |
| Repo | |
| Framework | |
