Paper Group NAWR 5
RDF2Vec: RDF Graph Embeddings and Their Applications. Neural Networks for Efficient Bayesian Decoding of Natural Images from Retinal Neurons. Context Selection for Embedding Models. Image Super-Resolution via Deep Recursive Residual Network. Instance Weighting for Neural Machine Translation Domain Adaptation. Leveraging Linguistic Structures for Na …
RDF2Vec: RDF Graph Embeddings and Their Applications
| Title | RDF2Vec: RDF Graph Embeddings and Their Applications |
| Authors | Petar Ristoski, Jessica Rosati, Tommaso Di Noia, Renato De Leone, Heiko Paulheim |
| Abstract | Linked Open Data has been recognized as a valuable source for background information in many data mining and information retrieval tasks. However, most of the existing tools require features in propositional form, i.e., a vector of nominal or numerical features associated with an instance, while Linked Open Data sources are graphs by nature. In this paper, we present RDF2Vec, an approach that uses language modeling approaches for unsupervised feature extraction from sequences of words, and adapts them to RDF graphs.We generate sequences by leveraging local information from graph sub-structures, harvested by Weisfeiler-Lehman Subtree RDF Graph Kernels and graph walks, and learn latent numerical representations of entities in RDF graphs.We evaluate our approach on three different tasks: (i) standard machine learning tasks, (ii) entity and document modeling, and (iii) content-based recommender systems. The evaluation shows that the proposed entity embeddings outperform existing techniques, and that pre-computed feature vector representations of general knowledge graphs such as DBpedia and Wikidata can be easily reused for different tasks. |
| Tasks | Entity Embeddings, Information Retrieval, Knowledge Graph Embedding, Knowledge Graph Embeddings, Knowledge Graphs, Language Modelling, Node Classification, Recommendation Systems |
| Published | 2017-11-10 |
| URL | http://www.semantic-web-journal.net/content/rdf2vec-rdf-graph-embeddings-and-their-applications-1 |
| http://www.semantic-web-journal.net/system/files/swj1738.pdf | |
| PWC | https://paperswithcode.com/paper/rdf2vec-rdf-graph-embeddings-and-their |
| Repo | https://github.com/IBCNServices/pyRDF2Vec |
| Framework | none |
Neural Networks for Efficient Bayesian Decoding of Natural Images from Retinal Neurons
| Title | Neural Networks for Efficient Bayesian Decoding of Natural Images from Retinal Neurons |
| Authors | Nikhil Parthasarathy, Eleanor Batty, William Falcon, Thomas Rutten, Mohit Rajpal, E.J. Chichilnisky, Liam Paninski |
| Abstract | Decoding sensory stimuli from neural signals can be used to reveal how we sense our physical environment, and is valuable for the design of brain-machine interfaces. However, existing linear techniques for neural decoding may not fully reveal or exploit the fidelity of the neural signal. Here we develop a new approximate Bayesian method for decoding natural images from the spiking activity of populations of retinal ganglion cells (RGCs). We sidestep known computational challenges with Bayesian inference by exploiting artificial neural networks developed for computer vision, enabling fast nonlinear decoding that incorporates natural scene statistics implicitly. We use a decoder architecture that first linearly reconstructs an image from RGC spikes, then applies a convolutional autoencoder to enhance the image. The resulting decoder, trained on natural images and simulated neural responses, significantly outperforms linear decoding, as well as simple point-wise nonlinear decoding. These results provide a tool for the assessment and optimization of retinal prosthesis technologies, and reveal that the retina may provide a more accurate representation of the visual scene than previously appreciated. |
| Tasks | Bayesian Inference |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7222-neural-networks-for-efficient-bayesian-decoding-of-natural-images-from-retinal-neurons |
| http://papers.nips.cc/paper/7222-neural-networks-for-efficient-bayesian-decoding-of-natural-images-from-retinal-neurons.pdf | |
| PWC | https://paperswithcode.com/paper/neural-networks-for-efficient-bayesian |
| Repo | https://github.com/nikparth/visual-neural-decode |
| Framework | tf |
Context Selection for Embedding Models
| Title | Context Selection for Embedding Models |
| Authors | Liping Liu, Francisco Ruiz, Susan Athey, David Blei |
| Abstract | Word embeddings are an effective tool to analyze language. They have been recently extended to model other types of data beyond text, such as items in recommendation systems. Embedding models consider the probability of a target observation (a word or an item) conditioned on the elements in the context (other words or items). In this paper, we show that conditioning on all the elements in the context is not optimal. Instead, we model the probability of the target conditioned on a learned subset of the elements in the context. We use amortized variational inference to automatically choose this subset. Compared to standard embedding models, this method improves predictions and the quality of the embeddings. |
| Tasks | Recommendation Systems, Word Embeddings |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7067-context-selection-for-embedding-models |
| http://papers.nips.cc/paper/7067-context-selection-for-embedding-models.pdf | |
| PWC | https://paperswithcode.com/paper/context-selection-for-embedding-models |
| Repo | https://github.com/blei-lab/context-selection-embedding |
| Framework | tf |
Image Super-Resolution via Deep Recursive Residual Network
| Title | Image Super-Resolution via Deep Recursive Residual Network |
| Authors | Ying Tai, Jian Yang, Xiaoming Liu |
| Abstract | Recently, Convolutional Neural Network (CNN) based models have achieved great success in Single Image Super-Resolution (SISR). Owing to the strength of deep networks, these CNN models learn an effective nonlinear mapping from the low-resolution input image to the high-resolution target image, at the cost of requiring enormous parameters. This paper proposes a very deep CNN model (up to 52 convolutional layers) named Deep Recursive Residual Network (DRRN) that strives for deep yet concise networks. Specifically, residual learning is adopted, both in global and local manners, to mitigate the difficulty of training very deep networks; recursive learning is used to control the model parameters while increasing the depth. Extensive benchmark evaluation shows that DRRN significantly outperforms state of the art in SISR, while utilizing far fewer parameters. Code is available at https://github.com/tyshiwo/DRRN_CVPR17. |
| Tasks | Image Super-Resolution, Super-Resolution |
| Published | 2017-07-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2017/html/Tai_Image_Super-Resolution_via_CVPR_2017_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2017/papers/Tai_Image_Super-Resolution_via_CVPR_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/image-super-resolution-via-deep-recursive |
| Repo | https://github.com/tyshiwo/DRRN_CVPR17 |
| Framework | pytorch |
Instance Weighting for Neural Machine Translation Domain Adaptation
| Title | Instance Weighting for Neural Machine Translation Domain Adaptation |
| Authors | Rui Wang, Masao Utiyama, Lemao Liu, Kehai Chen, Eiichiro Sumita |
| Abstract | Instance weighting has been widely applied to phrase-based machine translation domain adaptation. However, it is challenging to be applied to Neural Machine Translation (NMT) directly, because NMT is not a linear model. In this paper, two instance weighting technologies, i.e., sentence weighting and domain weighting with a dynamic weight learning strategy, are proposed for NMT domain adaptation. Empirical results on the IWSLT English-German/French tasks show that the proposed methods can substantially improve NMT performance by up to 2.7-6.7 BLEU points, outperforming the existing baselines by up to 1.6-3.6 BLEU points. |
| Tasks | Domain Adaptation, Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1155/ |
| https://www.aclweb.org/anthology/D17-1155 | |
| PWC | https://paperswithcode.com/paper/instance-weighting-for-neural-machine |
| Repo | https://github.com/wangruinlp/nmt_instance_weighting |
| Framework | none |
Leveraging Linguistic Structures for Named Entity Recognition with Bidirectional Recursive Neural Networks
| Title | Leveraging Linguistic Structures for Named Entity Recognition with Bidirectional Recursive Neural Networks |
| Authors | Peng-Hsuan Li, Ruo-Ping Dong, Yu-Siang Wang, Ju-Chieh Chou, Wei-Yun Ma |
| Abstract | In this paper, we utilize the linguistic structures of texts to improve named entity recognition by BRNN-CNN, a special bidirectional recursive network attached with a convolutional network. Motivated by the observation that named entities are highly related to linguistic constituents, we propose a constituent-based BRNN-CNN for named entity recognition. In contrast to classical sequential labeling methods, the system first identifies which text chunks are possible named entities by whether they are linguistic constituents. Then it classifies these chunks with a constituency tree structure by recursively propagating syntactic and semantic information to each constituent node. This method surpasses current state-of-the-art on OntoNotes 5.0 with automatically generated parses. |
| Tasks | Named Entity Recognition |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1282/ |
| https://www.aclweb.org/anthology/D17-1282 | |
| PWC | https://paperswithcode.com/paper/leveraging-linguistic-structures-for-named |
| Repo | https://github.com/jacobvsdanniel/tf_rnn |
| Framework | tf |
Transition-Based Disfluency Detection using LSTMs
| Title | Transition-Based Disfluency Detection using LSTMs |
| Authors | Shaolei Wang, Wanxiang Che, Yue Zhang, Meishan Zhang, Ting Liu |
| Abstract | In this paper, we model the problem of disfluency detection using a transition-based framework, which incrementally constructs and labels the disfluency chunk of input sentences using a new transition system without syntax information. Compared with sequence labeling methods, it can capture non-local chunk-level features; compared with joint parsing and disfluency detection methods, it is free for noise in syntax. Experiments show that our model achieves state-of-the-art f-score of 87.5{%} on the commonly used English Switchboard test set, and a set of in-house annotated Chinese data. |
| Tasks | Information Retrieval |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1296/ |
| https://www.aclweb.org/anthology/D17-1296 | |
| PWC | https://paperswithcode.com/paper/transition-based-disfluency-detection-using |
| Repo | https://github.com/hitwsl/transition_disfluency |
| Framework | none |
Toward Automated Early Sepsis Alerting: Identifying Infection Patients from Nursing Notes
| Title | Toward Automated Early Sepsis Alerting: Identifying Infection Patients from Nursing Notes |
| Authors | Emilia Apostolova, Tom Velez |
| Abstract | Severe sepsis and septic shock are conditions that affect millions of patients and have close to 50{%} mortality rate. Early identification of at-risk patients significantly improves outcomes. Electronic surveillance tools have been developed to monitor structured Electronic Medical Records and automatically recognize early signs of sepsis. However, many sepsis risk factors (e.g. symptoms and signs of infection) are often captured only in free text clinical notes. In this study, we developed a method for automatic monitoring of nursing notes for signs and symptoms of infection. We utilized a creative approach to automatically generate an annotated dataset. The dataset was used to create a Machine Learning model that achieved an F1-score ranging from 79 to 96{%}. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2332/ |
| https://www.aclweb.org/anthology/W17-2332 | |
| PWC | https://paperswithcode.com/paper/toward-automated-early-sepsis-alerting |
| Repo | https://github.com/ema-/antibiotic-dictionary |
| Framework | none |
Filter Flow Made Practical: Massively Parallel and Lock-Free
| Title | Filter Flow Made Practical: Massively Parallel and Lock-Free |
| Authors | Sathya N. Ravi, Yunyang Xiong, Lopamudra Mukherjee, Vikas Singh |
| Abstract | This paper is inspired by a relatively recent work of Seitz and Baker which introduced the so-called Filter Flow model. Filter flow finds the transformation relating a pair of (or multiple) images by identifying a large set of local linear filters; imposing additional constraints on certain structural properties of these filters enables Filter Flow to serve as a general “one stop” construction for a spectrum of problems in vision: from optical flow to defocus to stereo to affine alignment. The idea is beautiful yet the benefits are not borne out in practice because of significant computational challenges. This issue makes most (if not all) deployments for practical vision problems out of reach. The key thrust of our work is to identify mathematically (near) equivalent reformulations of this model that can eliminate this serious limitation. We demonstrate via a detailed optimization-focused development that Filter Flow can indeed be solved fairly efficiently for a wide range of instantiations. We derive efficient algorithms, perform extensive theoretical analysis focused on convergence and parallelization and show how results competitive with the state of the art for many applications can be achieved with negligible application specific adjustments or post-processing. The actual numerical scheme is easy to understand and, implement (30 lines in Matlab) – this development will enable Filter Flow to be a viable general solver and testbed for numerous applications in the community, going forward. |
| Tasks | Optical Flow Estimation |
| Published | 2017-07-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2017/html/Ravi_Filter_Flow_Made_CVPR_2017_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2017/papers/Ravi_Filter_Flow_Made_CVPR_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/filter-flow-made-practical-massively-parallel |
| Repo | https://github.com/sravi-uwmadison/fast_filter_flow |
| Framework | none |
Combining Graph Degeneracy and Submodularity for Unsupervised Extractive Summarization
| Title | Combining Graph Degeneracy and Submodularity for Unsupervised Extractive Summarization |
| Authors | Antoine Tixier, Polykarpos Meladianos, Michalis Vazirgiannis |
| Abstract | We present a fully unsupervised, extractive text summarization system that leverages a submodularity framework introduced by past research. The framework allows summaries to be generated in a greedy way while preserving near-optimal performance guarantees. Our main contribution is the novel coverage reward term of the objective function optimized by the greedy algorithm. This component builds on the graph-of-words representation of text and the k-core decomposition algorithm to assign meaningful scores to words. We evaluate our approach on the AMI and ICSI meeting speech corpora, and on the DUC2001 news corpus. We reach state-of-the-art performance on all datasets. Results indicate that our method is particularly well-suited to the meeting domain. |
| Tasks | Document Summarization, Information Retrieval, Keyword Extraction, Sentence Compression, Text Summarization |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4507/ |
| https://www.aclweb.org/anthology/W17-4507 | |
| PWC | https://paperswithcode.com/paper/combining-graph-degeneracy-and-submodularity |
| Repo | https://github.com/Tixierae/EMNLP2017_NewSum |
| Framework | none |
Detecting Dementia through Retrospective Analysis of Routine Blog Posts by Bloggers with Dementia
| Title | Detecting Dementia through Retrospective Analysis of Routine Blog Posts by Bloggers with Dementia |
| Authors | Vaden Masrani, Gabriel Murray, Thalia Field, Giuseppe Carenini |
| Abstract | We investigate if writers with dementia can be automatically distinguished from those without by analyzing linguistic markers in written text, in the form of blog posts. We have built a corpus of several thousand blog posts, some by people with dementia and others by people with loved ones with dementia. We use this dataset to train and test several machine learning methods, and achieve prediction performance at a level far above the baseline. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2329/ |
| https://www.aclweb.org/anthology/W17-2329 | |
| PWC | https://paperswithcode.com/paper/detecting-dementia-through-retrospective |
| Repo | https://github.com/vadmas/blog_corpus |
| Framework | none |
Benchmark for Complex Answer Retrieval
| Title | Benchmark for Complex Answer Retrieval |
| Authors | Federico Nanni, Bhaskar Mitra, Matt Magnusson and Laura Dietz |
| Abstract | Retrieving paragraphs to populate a Wikipedia article is a challenging task. The new TREC Complex Answer Retrieval (TREC CAR) track introduces a comprehensive dataset that targets this retrieval scenario. We present early results from a variety of approaches – from standard information retrieval methods (e.g., tf-idf) to complex systems that using query expansion using knowledge bases and deep neural networks. The goal is to offer future participants of this track an overview of some promising approaches to tackle this problem. |
| Tasks | Information Retrieval, Passage Re-Ranking |
| Published | 2017-10-01 |
| URL | https://arxiv.org/abs/1705.04803 |
| https://arxiv.org/pdf/1705.04803.pdf | |
| PWC | https://paperswithcode.com/paper/benchmark-for-complex-answer-retrieval |
| Repo | https://github.com/bmitra-msft/NDRM |
| Framework | none |
Amodal Detection of 3D Objects: Inferring 3D Bounding Boxes From 2D Ones in RGB-Depth Images
| Title | Amodal Detection of 3D Objects: Inferring 3D Bounding Boxes From 2D Ones in RGB-Depth Images |
| Authors | Zhuo Deng, Longin Jan Latecki |
| Abstract | This paper addresses the problem of amodal perception of 3D object detection. The task is to not only find object localizations in the 3D world, but also estimate their physical sizes and poses, even if only parts of them are visible in the RGB-D image. Recent approaches have attempted to harness point cloud from depth channel to exploit 3D features directly in the 3D space and demonstrated the superiority over traditional 2.5D representation approaches. We revisit the amodal 3D detection problem by sticking to the 2.5D representation framework, and directly relate 2.5D visual appearance to 3D objects. We propose a novel 3D object detection system that simultaneously predicts objects’ 3D locations, physical sizes, and orientations in indoor scenes. Experiments on the NYUV2 dataset show our algorithm significantly outperforms the state-of-the-art and indicates 2.5D representation is capable of encoding features for 3D amodal object detection. All source code and data is on https://github.com/phoenixnn/Amodal3Det. |
| Tasks | 3D Object Detection, Object Detection |
| Published | 2017-07-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2017/html/Deng_Amodal_Detection_of_CVPR_2017_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2017/papers/Deng_Amodal_Detection_of_CVPR_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/amodal-detection-of-3d-objects-inferring-3d |
| Repo | https://github.com/phoenixnn/Amodal3Det |
| Framework | none |
SubUNets: End-To-End Hand Shape and Continuous Sign Language Recognition
| Title | SubUNets: End-To-End Hand Shape and Continuous Sign Language Recognition |
| Authors | Necati Cihan Camgoz, Simon Hadfield, Oscar Koller, Richard Bowden |
| Abstract | We propose a novel deep learning approach to solve simultaneous alignment and recognition problems (referred to as “Sequence-to-sequence” learning). We decompose the problem into a series of specialised expert systems referred to as SubUNets. The spatio-temporal relationships between these SubUNets are then modelled to solve the task, while remaining trainable end-to-end. The approach mimics human learning and educational techniques, and has a number of significant advantages. SubUNets allow us to inject domain-specific expert knowledge into the system regarding suitable intermediate representations. They also allow us to implicitly perform transfer learning between different interrelated tasks, which also allows us to exploit a wider range of more varied data sources. In our experiments we demonstrate that each of these properties serves to significantly improve the performance of the overarching recognition system, by better constraining the learning problem. The proposed techniques are demonstrated in the challenging domain of sign language recognition. We demonstrate state-of-the-art performance on hand-shape recognition outperforming previous techniques by more than 30%). Furthermore, we are able to obtain comparable sign recognition rates to previous research, without the need for an alignment step to segment out the signs for recognition. |
| Tasks | Sign Language Recognition, Transfer Learning |
| Published | 2017-10-01 |
| URL | http://openaccess.thecvf.com/content_iccv_2017/html/Camgoz_SubUNets_End-To-End_Hand_ICCV_2017_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2017/papers/Camgoz_SubUNets_End-To-End_Hand_ICCV_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/subunets-end-to-end-hand-shape-and-continuous |
| Repo | https://github.com/neccam/SubUNets |
| Framework | tf |
Class Disjointness Constraints as Specific Objective Functions in Neural Network Classifiers
| Title | Class Disjointness Constraints as Specific Objective Functions in Neural Network Classifiers |
| Authors | Fran{\c{c}}ois Scharffe |
| Abstract | |
| Tasks | Object Classification, Object Detection |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-7303/ |
| https://www.aclweb.org/anthology/W17-7303 | |
| PWC | https://paperswithcode.com/paper/class-disjointness-constraints-as-specific |
| Repo | https://github.com/OpenAxon/constrained-nn |
| Framework | tf |
