Paper Group NANR 266
JW300: A Wide-Coverage Parallel Corpus for Low-Resource Languages. Corpus Creation and Analysis for Named Entity Recognition in Telugu-English Code-Mixed Social Media Data. Team Harry Friberg at SemEval-2019 Task 4: Identifying Hyperpartisan News through Editorially Defined Metatopics. 'UFAL-Oslo at MRP 2019: Garage Sale Semantic Parsing. SAIL-VOS …
JW300: A Wide-Coverage Parallel Corpus for Low-Resource Languages
| Title | JW300: A Wide-Coverage Parallel Corpus for Low-Resource Languages |
| Authors | {\v{Z}}eljko Agi{'c}, Ivan Vuli{'c} |
| Abstract | Viable cross-lingual transfer critically depends on the availability of parallel texts. Shortage of such resources imposes a development and evaluation bottleneck in multilingual processing. We introduce JW300, a parallel corpus of over 300 languages with around 100 thousand parallel sentences per language pair on average. In this paper, we present the resource and showcase its utility in experiments with cross-lingual word embedding induction and multi-source part-of-speech projection. |
| Tasks | Cross-Lingual Transfer |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1310/ |
| https://www.aclweb.org/anthology/P19-1310 | |
| PWC | https://paperswithcode.com/paper/jw300-a-wide-coverage-parallel-corpus-for-low |
| Repo | |
| Framework | |
Corpus Creation and Analysis for Named Entity Recognition in Telugu-English Code-Mixed Social Media Data
| Title | Corpus Creation and Analysis for Named Entity Recognition in Telugu-English Code-Mixed Social Media Data |
| Authors | Vamshi Krishna Srirangam, Appidi Abhinav Reddy, Vinay Singh, Manish Shrivastava |
| Abstract | Named Entity Recognition(NER) is one of the important tasks in Natural Language Processing(NLP) and also is a subtask of Information Extraction. In this paper we present our work on NER in Telugu-English code-mixed social media data. Code-Mixing, a progeny of multilingualism is a way in which multilingual people express themselves on social media by using linguistics units from different languages within a sentence or speech context. Entity Extraction from social media data such as tweets(twitter) is in general difficult due to its informal nature, code-mixed data further complicates the problem due to its informal, unstructured and incomplete information. We present a Telugu-English code-mixed corpus with the corresponding named entity tags. The named entities used to tag data are Person({}Per{'}), Organization({}Org{'}) and Location({`}Loc{'}). We experimented with the machine learning models Conditional Random Fields(CRFs), Decision Trees and BiLSTMs on our corpus which resulted in a F1-score of 0.96, 0.94 and 0.95 respectively. | |
| Tasks | Entity Extraction, Named Entity Recognition |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-2025/ |
| https://www.aclweb.org/anthology/P19-2025 | |
| PWC | https://paperswithcode.com/paper/corpus-creation-and-analysis-for-named-entity |
| Repo | |
| Framework | |
Team Harry Friberg at SemEval-2019 Task 4: Identifying Hyperpartisan News through Editorially Defined Metatopics
| Title | Team Harry Friberg at SemEval-2019 Task 4: Identifying Hyperpartisan News through Editorially Defined Metatopics |
| Authors | Nazanin Afsarmanesh, Jussi Karlgren, Peter Sumbler, Nina Viereckel |
| Abstract | This report describes the starting point for a simple rule based hypothesis testing excercise on identifying hyperpartisan news items carried out by the Harry Friberg team from Gavagai. We used manually crafted \textit{metatopics}, topics which often appear in hyperpartisan texts as rant conduits, together with tonality analysis to identify general characteristics of hyperpartisan news items. While the precision of the resulting effort is less than stellar{—} our contribution ranked 37th of the 42 successfully submitted experiments with overly high recall (95{%}) and low precision (54{%}){—}we believe we have a model which allows us to continue exploring the underlying features of what the subgenre of hyperpartisan news items is characterised by. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2174/ |
| https://www.aclweb.org/anthology/S19-2174 | |
| PWC | https://paperswithcode.com/paper/team-harry-friberg-at-semeval-2019-task-4 |
| Repo | |
| Framework | |
'UFAL-Oslo at MRP 2019: Garage Sale Semantic Parsing
| Title | 'UFAL-Oslo at MRP 2019: Garage Sale Semantic Parsing |
| Authors | Kira Droganova, Andrey Kutuzov, Nikita Mediankin, Daniel Zeman |
| Abstract | This paper describes the {'U}FAL–Oslo system submission to the shared task on Cross-Framework Meaning Representation Parsing (MRP, Oepen et al. 2019). The submission is based on several third-party parsers. Within the official shared task results, the submission ranked 11th out of 13 participating systems. |
| Tasks | Semantic Parsing |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-2015/ |
| https://www.aclweb.org/anthology/K19-2015 | |
| PWC | https://paperswithcode.com/paper/ufal-oslo-at-mrp-2019-garage-sale-semantic |
| Repo | |
| Framework | |
SAIL-VOS: Semantic Amodal Instance Level Video Object Segmentation - A Synthetic Dataset and Baselines
| Title | SAIL-VOS: Semantic Amodal Instance Level Video Object Segmentation - A Synthetic Dataset and Baselines |
| Authors | Yuan-Ting Hu, Hong-Shuo Chen, Kexin Hui, Jia-Bin Huang, Alexander G. Schwing |
| Abstract | We introduce SAIL-VOS (Semantic Amodal Instance Level Video Object Segmentation), a new dataset aiming to stimulate semantic amodal segmentation research. Humans can effortlessly recognize partially occluded objects and reliably estimate their spatial extent beyond the visible. However, few modern computer vision techniques are capable of reasoning about occluded parts of an object. This is partly due to the fact that very few image datasets and no video dataset exist which permit development of those methods. To address this issue, we present a synthetic dataset extracted from the photo-realistic game GTA-V. Each frame is accompanied with densely annotated, pixel-accurate visible and amodal segmentation masks with semantic labels. More than 1.8M objects are annotated resulting in 100 times more annotations than existing datasets. We demonstrate the challenges of the dataset by quantifying the performance of several baselines. Data and additional material is available at http://sailvos.web.illinois.edu. |
| Tasks | Semantic Segmentation, Video Object Segmentation, Video Semantic Segmentation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Hu_SAIL-VOS_Semantic_Amodal_Instance_Level_Video_Object_Segmentation_-_A_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Hu_SAIL-VOS_Semantic_Amodal_Instance_Level_Video_Object_Segmentation_-_A_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/sail-vos-semantic-amodal-instance-level-video |
| Repo | |
| Framework | |
CX-ST-RNM at SemEval-2019 Task 3: Fusion of Recurrent Neural Networks Based on Contextualized and Static Word Representations for Contextual Emotion Detection
| Title | CX-ST-RNM at SemEval-2019 Task 3: Fusion of Recurrent Neural Networks Based on Contextualized and Static Word Representations for Contextual Emotion Detection |
| Authors | Micha{\l} Pere{\l}kiewicz |
| Abstract | In this paper, I describe a fusion model combining contextualized and static word representations for approaching the EmoContext task in the SemEval 2019 competition. The model is based on two Recurrent Neural Networks, the first one is fed with a state-of-the-art ELMo deep contextualized word representation and the second one is fed with a static Word2Vec embedding augmented with 10-dimensional affective word feature vector. The proposed model is compared with two baseline models based on a static word representation and a contextualized word representation, separately. My approach achieved officially 0.7278 microaveraged F1 score on the test dataset, ranking 47th out of 165 participants. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2028/ |
| https://www.aclweb.org/anthology/S19-2028 | |
| PWC | https://paperswithcode.com/paper/cx-st-rnm-at-semeval-2019-task-3-fusion-of |
| Repo | |
| Framework | |
Large-Scale, Metric Structure From Motion for Unordered Light Fields
| Title | Large-Scale, Metric Structure From Motion for Unordered Light Fields |
| Authors | Sotiris Nousias, Manolis Lourakis, Christos Bergeles |
| Abstract | This paper presents a large scale, metric Structure from Motion (SfM) pipeline for generalised cameras with overlapping fields-of-view, and demonstrates it using Light Field (LF) images. We build on recent developments in algorithms for absolute and relative pose recovery for generalised cameras and couple them with multi-view triangulation in a robust framework that advances the state-of-the-art on 3D reconstruction from LFs in several ways. First, our framework can recover the scale of a scene. Second, it is concerned with unordered sets of LF images, meticulously determining the order in which images should be considered. Third, it can scale to datasets with hundreds of LF images. Finally, it recovers 3D scene structure while abstaining from triangulating using very small baselines. Our approach outperforms the state-of-the-art, as demonstrated by real-world experiments with variable size datasets. |
| Tasks | 3D Reconstruction |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Nousias_Large-Scale_Metric_Structure_From_Motion_for_Unordered_Light_Fields_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Nousias_Large-Scale_Metric_Structure_From_Motion_for_Unordered_Light_Fields_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/large-scale-metric-structure-from-motion-for |
| Repo | |
| Framework | |
Re-Ranking via Metric Fusion for Object Retrieval and Person Re-Identification
| Title | Re-Ranking via Metric Fusion for Object Retrieval and Person Re-Identification |
| Authors | Song Bai, Peng Tang, Philip H.S. Torr, Longin Jan Latecki |
| Abstract | This work studies the unsupervised re-ranking procedure for object retrieval and person re-identification with a specific concentration on an ensemble of multiple metrics (or similarities). While the re-ranking step is involved by running a diffusion process on the underlying data manifolds, the fusion step can leverage the complementarity of multiple metrics. We give a comprehensive summary of existing fusion with diffusion strategies, and systematically analyze their pros and cons. Based on the analysis, we propose a unified yet robust algorithm which inherits their advantages and discards their disadvantages. Hence, we call it Unified Ensemble Diffusion (UED). More interestingly, we derive that the inherited properties indeed stem from a theoretical framework, where the relevant works can be elegantly summarized as special cases of UED by imposing additional constraints on the objective function and varying the solver of similarity propagation. Extensive experiments with 3D shape retrieval, image retrieval and person re-identification demonstrate that the proposed framework outperforms the state of the arts, and at the same time suggest that re-ranking via metric fusion is a promising tool to further improve the retrieval performance of existing algorithms. |
| Tasks | 3D Shape Retrieval, Image Retrieval, Person Re-Identification |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Bai_Re-Ranking_via_Metric_Fusion_for_Object_Retrieval_and_Person_Re-Identification_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Bai_Re-Ranking_via_Metric_Fusion_for_Object_Retrieval_and_Person_Re-Identification_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/re-ranking-via-metric-fusion-for-object |
| Repo | |
| Framework | |
K For The Price Of 1: Parameter Efficient Multi-task And Transfer Learning
| Title | K For The Price Of 1: Parameter Efficient Multi-task And Transfer Learning |
| Authors | Pramod Kaushik Mudrakarta, Mark Sandler, Andrey Zhmoginov, Andrew Howard |
| Abstract | We introduce a novel method that enables parameter-efficient transfer and multitask learning. The basic approach is to allow a model patch - a small set of parameters - to specialize to each task, instead of fine-tuning the last layer or the entire network. For instance, we show that learning a set of scales and biases allows a network to learn a completely different embedding that could be used for different tasks (such as converting an SSD detection model into a 1000-class classification model while reusing 98% of parameters of the feature extractor). Similarly, we show that re-learning the existing low-parameter layers (such as depth-wise convolutions) also improves accuracy significantly. Our approach allows both simultaneous (multi-task) learning as well as sequential transfer learning wherein we adapt pretrained networks to solve new problems. For multi-task learning, despite using much fewer parameters than traditional logits-only fine-tuning, we match single-task-based performance. |
| Tasks | Multi-Task Learning, Transfer Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=BJxvEh0cFQ |
| https://openreview.net/pdf?id=BJxvEh0cFQ | |
| PWC | https://paperswithcode.com/paper/k-for-the-price-of-1-parameter-efficient-1 |
| Repo | |
| Framework | |
Outlier-robust estimation of a sparse linear model using \ell_1-penalized Huber’s M-estimator
| Title | Outlier-robust estimation of a sparse linear model using \ell_1-penalized Huber’s M-estimator |
| Authors | Arnak Dalalyan, Philip Thompson |
| Abstract | We study the problem of estimating a $p$-dimensional $s$-sparse vector in a linear model with Gaussian design. In the case where the labels are contaminated by at most $o$ adversarial outliers, we prove that the $\ell_1$-penalized Huber’s $M$-estimator based on $n$ samples attains the optimal rate of convergence $(s/n)^{1/2} + (o/n)$, up to a logarithmic factor. For more general design matrices, our results highlight the importance of two properties: the transfer principle and the incoherence property. These properties with suitable constants are shown to yield the optimal rates of robust estimation with adversarial contamination. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9477-outlier-robust-estimation-of-a-sparse-linear-model-using-ell_1-penalized-hubers-m-estimator |
| http://papers.nips.cc/paper/9477-outlier-robust-estimation-of-a-sparse-linear-model-using-ell_1-penalized-hubers-m-estimator.pdf | |
| PWC | https://paperswithcode.com/paper/outlier-robust-estimation-of-a-sparse-linear-1 |
| Repo | |
| Framework | |
Hybrid 8-bit Floating Point (HFP8) Training and Inference for Deep Neural Networks
| Title | Hybrid 8-bit Floating Point (HFP8) Training and Inference for Deep Neural Networks |
| Authors | Xiao Sun, Jungwook Choi, Chia-Yu Chen, Naigang Wang, Swagath Venkataramani, Vijayalakshmi (Viji) Srinivasan, Xiaodong Cui, Wei Zhang, Kailash Gopalakrishnan |
| Abstract | Reducing the numerical precision of data and computation is extremely effective in accelerating deep learning training workloads. Towards this end, 8-bit floating point representations (FP8) were recently proposed for DNN training. However, its applicability was demonstrated on a few selected models only and significant degradation is observed when popular networks such as MobileNet and Transformer are trained using FP8. This degradation is due to the inherent precision requirement difference in the forward and backward passes of DNN training. Using theoretical insights, we propose a hybrid FP8 (HFP8) format and DNN end-to-end distributed training procedure. We demonstrate, using HFP8, the successful training of deep learning models across a whole spectrum of applications including Image Classification, Object Detection, Language and Speech without accuracy degradation. Finally, we demonstrate that, by using the new 8 bit format, we can directly quantize a pre-trained model down to 8-bits without losing accuracy by simply fine-tuning batch normalization statistics. These novel techniques enable a new generations of 8-bit hardware that are robust for building and deploying neural network models. |
| Tasks | Image Classification, Object Detection |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8736-hybrid-8-bit-floating-point-hfp8-training-and-inference-for-deep-neural-networks |
| http://papers.nips.cc/paper/8736-hybrid-8-bit-floating-point-hfp8-training-and-inference-for-deep-neural-networks.pdf | |
| PWC | https://paperswithcode.com/paper/hybrid-8-bit-floating-point-hfp8-training-and |
| Repo | |
| Framework | |
A Logical and Computational Methodology for Exploring Systems of Phonotactic Constraints
| Title | A Logical and Computational Methodology for Exploring Systems of Phonotactic Constraints |
| Authors | Dakotah Lambert, James Rogers |
| Abstract | |
| Tasks | |
| Published | 2019-01-01 |
| URL | https://www.aclweb.org/anthology/W19-0125/ |
| https://www.aclweb.org/anthology/W19-0125 | |
| PWC | https://paperswithcode.com/paper/a-logical-and-computational-methodology-for |
| Repo | |
| Framework | |
STUFIIT at SemEval-2019 Task 5: Multilingual Hate Speech Detection on Twitter with MUSE and ELMo Embeddings
| Title | STUFIIT at SemEval-2019 Task 5: Multilingual Hate Speech Detection on Twitter with MUSE and ELMo Embeddings |
| Authors | Michal Bojkovsk{'y}, Mat{'u}{\v{s}} Pikuliak |
| Abstract | We present a number of models used for hate speech detection for Semeval 2019 Task-5: Hateval. We evaluate the viability of multilingual learning for this task. We also experiment with adversarial learning as a means of creating a multilingual model. Ultimately our multilingual models have had worse results than their monolignual counterparts. We find that the choice of word representations (word embeddings) is very crucial for deep learning as a simple switch between MUSE and ELMo embeddings has shown a 3-4{%} increase in accuracy. This also shows the importance of context when dealing with online content. |
| Tasks | Hate Speech Detection, Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2082/ |
| https://www.aclweb.org/anthology/S19-2082 | |
| PWC | https://paperswithcode.com/paper/stufiit-at-semeval-2019-task-5-multilingual |
| Repo | |
| Framework | |
Context Dependent Semantic Parsing over Temporally Structured Data
| Title | Context Dependent Semantic Parsing over Temporally Structured Data |
| Authors | Charles Chen, Razvan Bunescu |
| Abstract | We describe a new semantic parsing setting that allows users to query the system using both natural language questions and actions within a graphical user interface. Multiple time series belonging to an entity of interest are stored in a database and the user interacts with the system to obtain a better understanding of the entity{'}s state and behavior, entailing sequences of actions and questions whose answers may depend on previous factual or navigational interactions. We design an LSTM-based encoder-decoder architecture that models context dependency through copying mechanisms and multiple levels of attention over inputs and previous outputs. When trained to predict tokens using supervised learning, the proposed architecture substantially outperforms standard sequence generation baselines. Training the architecture using policy gradient leads to further improvements in performance, reaching a sequence-level accuracy of 88.7{%} on artificial data and 74.8{%} on real data. |
| Tasks | Semantic Parsing, Time Series |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1360/ |
| https://www.aclweb.org/anthology/N19-1360 | |
| PWC | https://paperswithcode.com/paper/context-dependent-semantic-parsing-over-1 |
| Repo | |
| Framework | |
Recurrent Neural Network for (Un-)Supervised Learning of Monocular Video Visual Odometry and Depth
| Title | Recurrent Neural Network for (Un-)Supervised Learning of Monocular Video Visual Odometry and Depth |
| Authors | Rui Wang, Stephen M. Pizer, Jan-Michael Frahm |
| Abstract | Deep learning-based, single-view depth estimation methods have recently shown highly promising results. However, such methods ignore one of the most important features for determining depth in the human vision system, which is motion. We propose a learning-based, multi-view dense depth map and odometry estimation method that uses Recurrent Neural Networks (RNN) and trains utilizing multi-view image reprojection and forward-backward flow-consistency losses. Our model can be trained in a supervised or even unsupervised mode. It is designed for depth and visual odometry estimation from video where the input frames are temporally correlated. However, it also generalizes to single-view depth estimation. Our method produces superior results to the state-of-the-art approaches for single-view and multi-view learning-based depth estimation on the KITTI driving dataset. |
| Tasks | Depth Estimation, MULTI-VIEW LEARNING, Visual Odometry |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Wang_Recurrent_Neural_Network_for_Un-Supervised_Learning_of_Monocular_Video_Visual_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Recurrent_Neural_Network_for_Un-Supervised_Learning_of_Monocular_Video_Visual_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/recurrent-neural-network-for-un-supervised-1 |
| Repo | |
| Framework | |
