Paper Group NANR 164
MIPT System for World-Level Quality Estimation. Redesign of the Croatian derivational lexicon. Using Intergaelic to pre-translate and subsequently post-edit a sci-fi novel from Scottish Gaelic to Irish. Modeling Behavioral Aspects of Social Media Discourse for Moral Classification. Confusionset-guided Pointer Networks for Chinese Spelling Check. Mu …
MIPT System for World-Level Quality Estimation
| Title | MIPT System for World-Level Quality Estimation |
| Authors | Mikhail Mosyagin, Varvara Logacheva |
| Abstract | We explore different model architectures for the WMT 19 shared task on word-level quality estimation of automatic translation. We start with a model similar to Shef-bRNN, which we modify by using conditional random fields for sequence labelling. Additionally, we use a different approach for labelling gaps and source words. We further develop this model by including features from different sources such as BERT, baseline features for the task and transformer encoders. We evaluate the performance of our models on the English-German dataset for the corresponding shared task. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5408/ |
| https://www.aclweb.org/anthology/W19-5408 | |
| PWC | https://paperswithcode.com/paper/mipt-system-for-world-level-quality |
| Repo | |
| Framework | |
Redesign of the Croatian derivational lexicon
| Title | Redesign of the Croatian derivational lexicon |
| Authors | Matea Filko, Kre{\v{s}}imir {\v{S}}ojat, Vanja {\v{S}}tefanec |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8509/ |
| https://www.aclweb.org/anthology/W19-8509 | |
| PWC | https://paperswithcode.com/paper/redesign-of-the-croatian-derivational-lexicon |
| Repo | |
| Framework | |
Using Intergaelic to pre-translate and subsequently post-edit a sci-fi novel from Scottish Gaelic to Irish
| Title | Using Intergaelic to pre-translate and subsequently post-edit a sci-fi novel from Scottish Gaelic to Irish |
| Authors | Eoin P. {'O} Murch{'u} |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7303/ |
| https://www.aclweb.org/anthology/W19-7303 | |
| PWC | https://paperswithcode.com/paper/using-intergaelic-to-pre-translate-and |
| Repo | |
| Framework | |
Modeling Behavioral Aspects of Social Media Discourse for Moral Classification
| Title | Modeling Behavioral Aspects of Social Media Discourse for Moral Classification |
| Authors | Kristen Johnson, Dan Goldwasser |
| Abstract | Political discourse on social media microblogs, specifically Twitter, has become an undeniable part of mainstream U.S. politics. Given the length constraint of tweets, politicians must carefully word their statements to ensure their message is understood by their intended audience. This constraint often eliminates the context of the tweet, making automatic analysis of social media political discourse a difficult task. To overcome this challenge, we propose simultaneous modeling of high-level abstractions of political language, such as political slogans and framing strategies, with abstractions of how politicians behave on Twitter. These behavioral abstractions can be further leveraged as forms of supervision in order to increase prediction accuracy, while reducing the burden of annotation. In this work, we use Probabilistic Soft Logic (PSL) to build relational models to capture the similarities in language and behavior that obfuscate political messages on Twitter. When combined, these descriptors reveal the moral foundations underlying the discourse of U.S. politicians online, \textit{across} differing governing administrations, showing how party talking points remain cohesive or change over time. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2112/ |
| https://www.aclweb.org/anthology/W19-2112 | |
| PWC | https://paperswithcode.com/paper/modeling-behavioral-aspects-of-social-media |
| Repo | |
| Framework | |
Confusionset-guided Pointer Networks for Chinese Spelling Check
| Title | Confusionset-guided Pointer Networks for Chinese Spelling Check |
| Authors | Dingmin Wang, Yi Tay, Li Zhong |
| Abstract | This paper proposes Confusionset-guided Pointer Networks for Chinese Spell Check (CSC) task. More concretely, our approach utilizes the off-the-shelf confusionset for guiding the character generation. To this end, our novel Seq2Seq model jointly learns to copy a correct character from an input sentence through a pointer network, or generate a character from the confusionset rather than the entire vocabulary. We conduct experiments on three human-annotated datasets, and results demonstrate that our proposed generative model outperforms all competitor models by a large margin of up to 20{%} F1 score, achieving state-of-the-art performance on three datasets. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1578/ |
| https://www.aclweb.org/anthology/P19-1578 | |
| PWC | https://paperswithcode.com/paper/confusionset-guided-pointer-networks-for |
| Repo | |
| Framework | |
Multiclass Text Classification on Unbalanced, Sparse and Noisy Data
| Title | Multiclass Text Classification on Unbalanced, Sparse and Noisy Data |
| Authors | Matthias Damaschk, Tillmann D{"o}nicke, Florian Lux |
| Abstract | This paper discusses methods to improve the performance of text classification on data that is difficult to classify due to a large number of unbalanced classes with noisy examples. A variety of features are tested, in combination with three different neural-network-based methods with increasing complexity. The classifiers are applied to a songtext{–}artist dataset which is large, unbalanced and noisy. We come to the conclusion that substantial improvement can be obtained by removing unbalancedness and sparsity from the data. This fulfils a classification task unsatisfactorily{—}however, with contemporary methods, it is a practical step towards fairly satisfactory results. |
| Tasks | Text Classification |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-6207/ |
| https://www.aclweb.org/anthology/W19-6207 | |
| PWC | https://paperswithcode.com/paper/multiclass-text-classification-on-unbalanced |
| Repo | |
| Framework | |
Self-Supervised Spatiotemporal Learning via Video Clip Order Prediction
| Title | Self-Supervised Spatiotemporal Learning via Video Clip Order Prediction |
| Authors | Dejing Xu, Jun Xiao, Zhou Zhao, Jian Shao, Di Xie, Yueting Zhuang |
| Abstract | We propose a self-supervised spatiotemporal learning technique which leverages the chronological order of videos. Our method can learn the spatiotemporal representation of the video by predicting the order of shuffled clips from the video. The category of the video is not required, which gives our technique the potential to take advantage of infinite unannotated videos. There exist related works which use frames, while compared to frames, clips are more consistent with the video dynamics. Clips can help to reduce the uncertainty of orders and are more appropriate to learn a video representation. The 3D convolutional neural networks are utilized to extract features for clips, and these features are processed to predict the actual order. The learned representations are evaluated via nearest neighbor retrieval experiments. We also use the learned networks as the pre-trained models and finetune them on the action recognition task. Three types of 3D convolutional neural networks are tested in experiments, and we gain large improvements compared to existing self-supervised methods. |
| Tasks | Temporal Action Localization |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Xu_Self-Supervised_Spatiotemporal_Learning_via_Video_Clip_Order_Prediction_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Xu_Self-Supervised_Spatiotemporal_Learning_via_Video_Clip_Order_Prediction_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/self-supervised-spatiotemporal-learning-via |
| Repo | |
| Framework | |
Surprisal and Interference Effects of Case Markers in Hindi Word Order
| Title | Surprisal and Interference Effects of Case Markers in Hindi Word Order |
| Authors | Sidharth Ranjan, Sumeet Agarwal, Rajakrishnan Rajkumar |
| Abstract | Based on the Production-Distribution-Comprehension (PDC) account of language processing, we formulate two distinct hypotheses about case marking, word order choices and processing in Hindi. Our first hypothesis is that Hindi tends to optimize for processing efficiency at both lexical and syntactic levels. We quantify the role of case markers in this process. For the task of predicting the reference sentence occurring in a corpus (amidst meaning-equivalent grammatical variants) using a machine learning model, surprisal estimates from an artificial version of the language (i.e., Hindi without any case markers) result in lower prediction accuracy compared to natural Hindi. Our second hypothesis is that Hindi tends to minimize interference due to case markers while ordering preverbal constituents. We show that Hindi tends to avoid placing next to each other constituents whose heads are marked by identical case inflections. Our findings adhere to PDC assumptions and we discuss their implications for language production, learning and universals. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2904/ |
| https://www.aclweb.org/anthology/W19-2904 | |
| PWC | https://paperswithcode.com/paper/surprisal-and-interference-effects-of-case |
| Repo | |
| Framework | |
SegEQA: Video Segmentation Based Visual Attention for Embodied Question Answering
| Title | SegEQA: Video Segmentation Based Visual Attention for Embodied Question Answering |
| Authors | Haonan Luo, Guosheng Lin, Zichuan Liu, Fayao Liu, Zhenmin Tang, Yazhou Yao |
| Abstract | Embodied Question Answering (EQA) is a newly defined research area where an agent is required to answer the user’s questions by exploring the real world environment. It has attracted increasing research interests due to its broad applications in automatic driving system, in-home robots, and personal assistants. Most of the existing methods perform poorly in terms of answering and navigation accuracy due to the absence of local details and vulnerability to the ambiguity caused by complicated vision conditions. To tackle these problems, we propose a segmentation based visual attention mechanism for Embodied Question Answering. Firstly, We extract the local semantic features by introducing a novel high-speed video segmentation framework. Then by the guide of extracted semantic features, a bottom-up visual attention mechanism is proposed for the Visual Question Answering (VQA) sub-task. Further, a feature fusion strategy is proposed to guide the training of the navigator without much additional computational cost. The ablation experiments show that our method boosts the performance of VQA module by 4.2% (68.99% vs 64.73%) and leads to 3.6% (48.59% vs 44.98%) overall improvement in EQA accuracy. |
| Tasks | Embodied Question Answering, Question Answering, Video Semantic Segmentation, Visual Question Answering |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Luo_SegEQA_Video_Segmentation_Based_Visual_Attention_for_Embodied_Question_Answering_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Luo_SegEQA_Video_Segmentation_Based_Visual_Attention_for_Embodied_Question_Answering_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/segeqa-video-segmentation-based-visual |
| Repo | |
| Framework | |
Deep Single Image Camera Calibration With Radial Distortion
| Title | Deep Single Image Camera Calibration With Radial Distortion |
| Authors | Manuel Lopez, Roger Mari, Pau Gargallo, Yubin Kuang, Javier Gonzalez-Jimenez, Gloria Haro |
| Abstract | Single image calibration is the problem of predicting the camera parameters from one image. This problem is of importance when dealing with images collected in uncontrolled conditions by non-calibrated cameras, such as crowd-sourced applications. In this work we propose a method to predict extrinsic (tilt and roll) and intrinsic (focal length and radial distortion) parameters from a single image. We propose a parameterization for radial distortion that is better suited for learning than directly predicting the distortion parameters. Moreover, predicting additional heterogeneous variables exacerbates the problem of loss balancing. We propose a new loss function based on point projections to avoid having to balance heterogeneous loss terms. Our method is, to our knowledge, the first to jointly estimate the tilt, roll, focal length, and radial distortion parameters from a single image. We thoroughly analyze the performance of the proposed method and the impact of the improvements and compare with previous approaches for single image radial distortion correction. |
| Tasks | Calibration |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Lopez_Deep_Single_Image_Camera_Calibration_With_Radial_Distortion_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Lopez_Deep_Single_Image_Camera_Calibration_With_Radial_Distortion_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-single-image-camera-calibration-with |
| Repo | |
| Framework | |
How Many Users Are Enough? Exploring Semi-Supervision and Stylometric Features to Uncover a Russian Troll Farm
| Title | How Many Users Are Enough? Exploring Semi-Supervision and Stylometric Features to Uncover a Russian Troll Farm |
| Authors | Nayeema Nasrin, Kim-Kwang Raymond Choo, Myung Ko, Anthony Rios |
| Abstract | Social media has reportedly been (ab)used by Russian troll farms to promote political agendas. Specifically, state-affiliated actors disguise themselves as native citizens of the United States to promote discord and promote their political motives. Therefore, developing methods to automatically detect Russian trolls can ensure fair elections and possibly reduce political extremism by stopping trolls that produce discord. While data exists for some troll organizations (e.g., Internet Research Agency), it is challenging to collect ground-truth accounts for new troll farms in a timely fashion. In this paper, we study the impact the number of labeled troll accounts has on detection performance. We analyze the use of self-supervision with less than 100 troll accounts as training data. We improve classification performance by nearly 4{%} F1. Furthermore, in combination with self-supervision, we also explore novel features for troll detection grounded in stylometry. Intuitively, we assume that the writing style is consistent across troll accounts because a single troll organization employee may control multiple user accounts. Overall, we improve on models based on words features by {\textasciitilde}9{%} F1. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5003/ |
| https://www.aclweb.org/anthology/D19-5003 | |
| PWC | https://paperswithcode.com/paper/how-many-users-are-enough-exploring-semi |
| Repo | |
| Framework | |
Large-Scale Few-Shot Learning: Knowledge Transfer With Class Hierarchy
| Title | Large-Scale Few-Shot Learning: Knowledge Transfer With Class Hierarchy |
| Authors | Aoxue Li, Tiange Luo, Zhiwu Lu, Tao Xiang, Liwei Wang |
| Abstract | Recently, large-scale few-shot learning (FSL) becomes topical. It is discovered that, for a large-scale FSL problem with 1,000 classes in the source domain, a strong baseline emerges, that is, simply training a deep feature embedding model using the aggregated source classes and performing nearest neighbor (NN) search using the learned features on the target classes. The state-of-the-art large-scale FSL methods struggle to beat this baseline, indicating intrinsic limitations on scalability. To overcome the challenge, we propose a novel large-scale FSL model by learning transferable visual features with the class hierarchy which encodes the semantic relations between source and target classes. Extensive experiments show that the proposed model significantly outperforms not only the NN baseline but also the state-of-the-art alternatives. Furthermore, we show that the proposed model can be easily extended to the large-scale zero-shot learning (ZSL) problem and also achieves the state-of-the-art results. |
| Tasks | Few-Shot Learning, Transfer Learning, Zero-Shot Learning |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Li_Large-Scale_Few-Shot_Learning_Knowledge_Transfer_With_Class_Hierarchy_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Li_Large-Scale_Few-Shot_Learning_Knowledge_Transfer_With_Class_Hierarchy_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/large-scale-few-shot-learning-knowledge |
| Repo | |
| Framework | |
DeepCO3: Deep Instance Co-Segmentation by Co-Peak Search and Co-Saliency Detection
| Title | DeepCO3: Deep Instance Co-Segmentation by Co-Peak Search and Co-Saliency Detection |
| Authors | Kuang-Jui Hsu, Yen-Yu Lin, Yung-Yu Chuang |
| Abstract | In this paper, we address a new task called instance co-segmentation. Given a set of images jointly covering object instances of a specific category, instance co-segmentation aims to identify all of these instances and segment each of them, i.e. generating one mask for each instance. This task is important since instance-level segmentation is preferable for humans and many vision applications. It is also challenging because no pixel-wise annotated training data are available and the number of instances in each image is unknown. We solve this task by dividing it into two sub-tasks, co-peak search and instance mask segmentation. In the former sub-task, we develop a CNN-based network to detect the co-peaks as well as co-saliency maps for a pair of images. A co-peak has two endpoints, one in each image, that are local maxima in the response maps and similar to each other. Thereby, the two endpoints are potentially covered by a pair of instances of the same category. In the latter subtask, we design a ranking function that takes the detected co-peaks and co-saliency maps as inputs and can select the object proposals to produce the final results. Our method for instance co-segmentation and its variant for object colocalization are evaluated on four datasets, and achieve favorable performance against the state-of-the-art methods. The source codes and the collected datasets are available at https://github.com/KuangJuiHsu/DeepCO3/ |
| Tasks | Co-Saliency Detection, Saliency Detection |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Hsu_DeepCO3_Deep_Instance_Co-Segmentation_by_Co-Peak_Search_and_Co-Saliency_Detection_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Hsu_DeepCO3_Deep_Instance_Co-Segmentation_by_Co-Peak_Search_and_Co-Saliency_Detection_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deepco3-deep-instance-co-segmentation-by-co |
| Repo | |
| Framework | |
Applications of Natural Language Processing in Clinical Research and Practice
| Title | Applications of Natural Language Processing in Clinical Research and Practice |
| Authors | Yanshan Wang, Ahmad Tafti, Sunghwan Sohn, Rui Zhang |
| Abstract | Rapid growth in adoption of electronic health records (EHRs) has led to an unprecedented expansion in the availability of large longitudinal datasets. Large initiatives such as the Electronic Medical Records and Genomics (eMERGE) Network, the Patient-Centered Outcomes Research Network (PCORNet), and the Observational Health Data Science and Informatics (OHDSI) consortium, have been established and have reported successful applications of secondary use of EHRs in clinical research and practice. In these applications, natural language processing (NLP) technologies have played a crucial role as much of detailed patient information in EHRs is embedded in narrative clinical documents. Meanwhile, a number of clinical NLP systems, such as MedLEE, MetaMap/MetaMap Lite, cTAKES, and MedTagger have been developed and utilized to extract useful information from diverse types of clinical text, such as clinical notes, radiology reports, and pathology reports. Success stories in applying these tools have been reported widely. Despite the demonstrated success of NLP in the clinical domain, methodologies and tools developed for the clinical NLP are still underknown and underutilized by students and experts in the general NLP domain, mainly due to the limited exposure to EHR data. Through this tutorial, we would like to introduce NLP methodologies and tools developed in the clinical domain, and showcase the real-world NLP applications in clinical research and practice at Mayo Clinic (the No. 1 national hospital ranked by the U.S. News {&} World Report) and the University of Minnesota (the No. 41 best global universities ranked by the U.S. News {&} World Report). We will review NLP techniques in solving clinical problems and facilitating clinical research, the state-of-the art clinical NLP tools, and share collaboration experience with clinicians, as well as publicly available EHR data and medical resources, and finally conclude the tutorial with vast opportunities and challenges of clinical NLP. The tutorial will provide an overview of clinical backgrounds, and does not presume knowledge in medicine or health care. The goal of this tutorial is to encourage NLP researchers in the general domain (as opposed to the specialized clinical domain) to contribute to this burgeoning area. In this tutorial, we will first present an overview of clinical NLP. We will then dive into two subareas of clinical NLP in clinical research, including big data infrastructure for large-scale clinical NLP and advances of NLP in clinical research, and two subareas in clinical practice, including clinical information extraction and patient cohort retrieval using EHRs. Around 70{%} of the tutorial will review clinical problems, cutting-edge methodologies, and real-world clinical NLP tools while another 30{%} introduce use cases at Mayo Clinic and the University of Minnesota. Finally, we will conclude the tutorial with challenges and opportunities in this rapidly developing domain. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-5006/ |
| https://www.aclweb.org/anthology/N19-5006 | |
| PWC | https://paperswithcode.com/paper/applications-of-natural-language-processing |
| Repo | |
| Framework | |
An Open, Extendible, and Fast Turkish Morphological Analyzer
| Title | An Open, Extendible, and Fast Turkish Morphological Analyzer |
| Authors | Olcay Taner Y{\i}ld{\i}z, Beg{"u}m Avar, G{"o}khan Ercan |
| Abstract | In this paper, we present a two-level morphological analyzer for Turkish. The morphological analyzer consists of five main components: finite state transducer, rule engine for suffixation, lexicon, trie data structure, and LRU cache. We use Java language to implement finite state machine logic and rule engine, Xml language to describe the finite state transducer rules of the Turkish language, which makes the morphological analyzer both easily extendible and easily applicable to other languages. Empowered with the comprehensiveness of a lexicon of 54,000 bare-forms including 19,000 proper nouns, our morphological analyzer presents one of the most reliable analyzers produced so far. The analyzer is compared with Turkish morphological analyzers in the literature. By using LRU cache and a trie data structure, the system can analyze 100,000 words per second, which enables users to analyze huge corpora in a few hours. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1156/ |
| https://www.aclweb.org/anthology/R19-1156 | |
| PWC | https://paperswithcode.com/paper/an-open-extendible-and-fast-turkish |
| Repo | |
| Framework | |
