Paper Group NANR 5
Feature Extraction Based Machine Learning for Human Burn Diagnosis From Burn Images. One Size Does Not Fit All: Comparing NMT Representations of Different Granularities. On Random Deep Weight-Tied Autoencoders: Exact Asymptotic Analysis, Phase Transitions, and Implications to Training. MixFeat: Mix Feature in Latent Space Learns Discriminative Spac …
Feature Extraction Based Machine Learning for Human Burn Diagnosis From Burn Images
Title | Feature Extraction Based Machine Learning for Human Burn Diagnosis From Burn Images |
Authors | D. P. YADAV, ASHISH SHARMA, MADHUSUDAN SINGH, AND AYUSH GOYAL |
Abstract | Burn is one of the serious public health problems. Usually, burn diagnoses are based on expert medical and clinical experience and it is necessary to have a medical or clinical expert to conduct an examination in restorative clinics or at emergency rooms in hospitals. But sometimes a patient may have a burn where there is no specialized facility available, and in such a case a computerized automatic burn assessment tool may aid diagnosis. Burn area, depth, and location are the critical factors in determining the severity of burns. In this paper, a classi cation model to diagnose burns is presented using automated machine learning. The objective of the research is to develop the feature extraction model to classify the burn. The proposed method based on support vector machine (SVM) is evaluated on a standard data set of burnsBIP_US database. Training is performed by classifying images into two classes, i.e., those that need grafts and those that are non-graft. The 74 images of test data set are tested with the proposed SVM based method and according to the ground truth, the accuracy of 82.43% was achieved for the SVM based model, which was higher than the 79.73% achieved in past work using the multidimensional scaling analysis (MDS) approach |
Tasks | |
Published | 2019-07-18 |
URL | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6681870/ |
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6681870/ | |
PWC | https://paperswithcode.com/paper/feature-extraction-based-machine-learning-for |
Repo | |
Framework | |
One Size Does Not Fit All: Comparing NMT Representations of Different Granularities
Title | One Size Does Not Fit All: Comparing NMT Representations of Different Granularities |
Authors | Nadir Durrani, Fahim Dalvi, Hassan Sajjad, Yonatan Belinkov, Preslav Nakov |
Abstract | Recent work has shown that contextualized word representations derived from neural machine translation are a viable alternative to such from simple word predictions tasks. This is because the internal understanding that needs to be built in order to be able to translate from one language to another is much more comprehensive. Unfortunately, computational and memory limitations as of present prevent NMT models from using large word vocabularies, and thus alternatives such as subword units (BPE and morphological segmentations) and characters have been used. Here we study the impact of using different kinds of units on the quality of the resulting representations when used to model morphology, syntax, and semantics. We found that while representations derived from subwords are slightly better for modeling syntax, character-based representations are superior for modeling morphology and are also more robust to noisy input. |
Tasks | Machine Translation |
Published | 2019-06-01 |
URL | https://www.aclweb.org/anthology/N19-1154/ |
https://www.aclweb.org/anthology/N19-1154 | |
PWC | https://paperswithcode.com/paper/one-size-does-not-fit-all-comparing-nmt |
Repo | |
Framework | |
On Random Deep Weight-Tied Autoencoders: Exact Asymptotic Analysis, Phase Transitions, and Implications to Training
Title | On Random Deep Weight-Tied Autoencoders: Exact Asymptotic Analysis, Phase Transitions, and Implications to Training |
Authors | Ping Li, Phan-Minh Nguyen |
Abstract | We study the behavior of weight-tied multilayer vanilla autoencoders under the assumption of random weights. Via an exact characterization in the limit of large dimensions, our analysis reveals interesting phase transition phenomena when the depth becomes large. This, in particular, provides quantitative answers and insights to three questions that were yet fully understood in the literature. Firstly, we provide a precise answer on how the random deep weight-tied autoencoder model performs “approximate inference” as posed by Scellier et al. (2018), and its connection to reversibility considered by several theoretical studies. Secondly, we show that deep autoencoders display a higher degree of sensitivity to perturbations in the parameters, distinct from the shallow counterparts. Thirdly, we obtain insights on pitfalls in training initialization practice, and demonstrate experimentally that it is possible to train a deep autoencoder, even with the tanh activation and a depth as large as 200 layers, without resorting to techniques such as layer-wise pre-training or batch normalization. Our analysis is not specific to any depths or any Lipschitz activations, and our analytical techniques may have broader applicability. |
Tasks | |
Published | 2019-05-01 |
URL | https://openreview.net/forum?id=HJx54i05tX |
https://openreview.net/pdf?id=HJx54i05tX | |
PWC | https://paperswithcode.com/paper/on-random-deep-weight-tied-autoencoders-exact |
Repo | |
Framework | |
MixFeat: Mix Feature in Latent Space Learns Discriminative Space
Title | MixFeat: Mix Feature in Latent Space Learns Discriminative Space |
Authors | Yoichi Yaguchi, Fumiyuki Shiratani, Hidekazu Iwaki |
Abstract | Deep learning methods perform well in various tasks. However, the over-fitting problem, which causes the performance to decrease for unknown data, remains. We hence propose a method named MixFeat that directly creates latent spaces in a network that can distinguish classes. MixFeat mixes two feature maps in each latent space in the network and uses unmixed labels for learning. We discuss the difference between a method that mixes only features (MixFeat) and a method that mixes both features and labels (mixup and its family). Mixing features repeatedly is effective in expanding feature diversity, but mixing labels repeatedly makes learning difficult. MixFeat makes it possible to obtain the advantages of repeated mixing by mixing only features. We report improved results obtained using existing network models with MixFeat on CIFAR-10/100 datasets. In addition, we show that MixFeat effectively reduces the over-fitting problem even when the training dataset is small or contains errors. MixFeat is easy to implement and can be added to various network models without additional computational cost in the inference phase. |
Tasks | |
Published | 2019-05-01 |
URL | https://openreview.net/forum?id=HygT9oRqFX |
https://openreview.net/pdf?id=HygT9oRqFX | |
PWC | https://paperswithcode.com/paper/mixfeat-mix-feature-in-latent-space-learns |
Repo | |
Framework | |
Accurate Monocular 3D Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving
Title | Accurate Monocular 3D Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving |
Authors | Xinzhu Ma, Zhihui Wang, Haojie Li, Pengbo Zhang, Wanli Ouyang, Xin Fan |
Abstract | In this paper, we propose a monocular 3D object detection framework in the domain of autonomous driving. Unlike previous image-based methods which focus on RGB feature extracted from 2D images, our method solves this problem in the reconstructed 3D space in order to exploit 3D contexts explicitly. To this end, we first leverage a stand-alone module to transform the input data from 2D image plane to 3D point clouds space for a better input representation, then we perform the 3D detection using PointNet backbone net to obtain objects’ 3D locations, dimensions and orientations. To enhance the discriminative capability of point clouds, we propose a multi-modal feature fusion module to embed the complementary RGB cue into the generated point clouds representation. We argue that it is more effective to infer the 3D bounding boxes from the generated 3D scene space (i.e., X,Y, Z space) compared to the image plane (i.e., R,G,B image plane). Evaluation on the challenging KITTI dataset shows that our approach boosts the performance of state-of-the-art monocular approach by a large margin. |
Tasks | 3D Object Detection, 3D Reconstruction, Autonomous Driving, Object Detection |
Published | 2019-10-01 |
URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Ma_Accurate_Monocular_3D_Object_Detection_via_Color-Embedded_3D_Reconstruction_for_ICCV_2019_paper.html |
http://openaccess.thecvf.com/content_ICCV_2019/papers/Ma_Accurate_Monocular_3D_Object_Detection_via_Color-Embedded_3D_Reconstruction_for_ICCV_2019_paper.pdf | |
PWC | https://paperswithcode.com/paper/accurate-monocular-3d-object-detection-via-1 |
Repo | |
Framework | |
Sparse Coding in Authorship Attribution for Polish Tweets
Title | Sparse Coding in Authorship Attribution for Polish Tweets |
Authors | Piotr Grzybowski, Ewa Juralewicz, Maciej Piasecki |
Abstract | The study explores application of a simple Convolutional Neural Network for the problem of authorship attribution of tweets written in Polish. In our solution we use two-step compression of tweets using Byte Pair Encoding algorithm and vectorisation as an input to the distributional model generated for the large corpus of Polish tweets by word2vec algorithm. Our method achieves results comparable to the state-of-the-art approaches for the similar task on English tweets and expresses a very good performance in the classification of Polish tweets. We tested the proposed method in relation to the number of authors and tweets per author. We also juxtaposed results for authors with different topic backgrounds against each other. |
Tasks | |
Published | 2019-09-01 |
URL | https://www.aclweb.org/anthology/R19-1048/ |
https://www.aclweb.org/anthology/R19-1048 | |
PWC | https://paperswithcode.com/paper/sparse-coding-in-authorship-attribution-for |
Repo | |
Framework | |
'UFAL MRPipe at MRP 2019: UDPipe Goes Semantic in the Meaning Representation Parsing Shared Task
Title | 'UFAL MRPipe at MRP 2019: UDPipe Goes Semantic in the Meaning Representation Parsing Shared Task |
Authors | Milan Straka, Jana Strakov{'a} |
Abstract | We present a system description of our contribution to the CoNLL 2019 shared task, CrossFramework Meaning Representation Parsing (MRP 2019). The proposed architecture is our first attempt towards a semantic parsing extension of the UDPipe 2.0, a lemmatization, POS tagging and dependency parsing pipeline. For the MRP 2019, which features five formally and linguistically different approaches to meaning representation (DM, PSD, EDS, UCCA and AMR), we propose a uniform, language and framework agnostic graph-tograph neural network architecture. Without any knowledge about the graph structure, and specifically without any linguistically or framework motivated features, our system implicitly models the meaning representation graphs. After fixing a human error (we used earlier incorrect version of provided test set analyses), our submission would score third in the competition evaluation. The source code of our system is available at https://github.com/ufal/mrpipe-conll2019. |
Tasks | Dependency Parsing, Lemmatization, Semantic Parsing |
Published | 2019-11-01 |
URL | https://www.aclweb.org/anthology/K19-2012/ |
https://www.aclweb.org/anthology/K19-2012 | |
PWC | https://paperswithcode.com/paper/ufal-mrpipe-at-mrp-2019-udpipe-goes-semantic-1 |
Repo | |
Framework | |
Learning to Learn Sales Prediction with Social Media Sentiment
Title | Learning to Learn Sales Prediction with Social Media Sentiment |
Authors | Zhaojiang Lin, Andrea Madotto, Genta Indra Winata, Zihan Liu, Yan Xu, Cong Gao, Pascale Fung |
Abstract | |
Tasks | |
Published | 2019-08-01 |
URL | https://www.aclweb.org/anthology/W19-5508/ |
https://www.aclweb.org/anthology/W19-5508 | |
PWC | https://paperswithcode.com/paper/learning-to-learn-sales-prediction-with |
Repo | |
Framework | |
Corpora and Processing Tools for Non-standard Contemporary and Diachronic Balkan Slavic
Title | Corpora and Processing Tools for Non-standard Contemporary and Diachronic Balkan Slavic |
Authors | Teodora Vukovic, Nora Muheim, Olivier Winist{"o}rfer, Ivan {\v{S}}imko, Anastasia Makarova, Sanja Bradjan |
Abstract | The paper describes three corpora of different varieties of BS that are currently being developed with the goal of providing data for the analysis of the diatopic and diachronic variation in non-standard Balkan Slavic. The corpora includes spoken materials from Torlak, Macedonian dialects, as well as the manuscripts of pre-standardized Bulgarian. Apart from the texts, tools for PoS annotation and lemmatization for all varieties are being created, as well as syntactic parsing for Torlak and Bulgarian varieties. The corpora are built using a unified methodology, relying on the pest practices and state-of-the-art methods from the field. The uniform methodology allows the contrastive analysis of the data from different varieties. The corpora under construction can be considered a crucial contribution to the linguistic research on the languages in the Balkans as they provide the lacking data needed for the studies of linguistic variation in the Balkan Slavic, and enable the comparison of the said varieties with other neighbouring languages. |
Tasks | Lemmatization |
Published | 2019-09-01 |
URL | https://www.aclweb.org/anthology/R19-2010/ |
https://www.aclweb.org/anthology/R19-2010 | |
PWC | https://paperswithcode.com/paper/corpora-and-processing-tools-for-non-standard |
Repo | |
Framework | |
The Chinese/English Political Interpreting Corpus (CEPIC): A New Electronic Resource for Translators and Interpreters
Title | The Chinese/English Political Interpreting Corpus (CEPIC): A New Electronic Resource for Translators and Interpreters |
Authors | Jun Pan |
Abstract | The Chinese/English Political Interpreting Corpus (CEPIC) is a new electronic and open access resource developed for translators and interpreters, especially those working with political text types. Over 6 million word tokens in size, the online corpus consists of transcripts of Chinese (Cantonese {&} Putonghua) / English political speeches and their translated and interpreted texts. It includes rich meta-data and is POS-tagged and annotated with prosodic and paralinguistic features that are of concern to spoken language and interpreting. The online platform of the CEPIC features main functions including Keyword Search, Word Collocation and Expanded Keyword in Context, which are illustrated in the paper. The CEPIC can shed light on online translation and interpreting corpora development in the future. |
Tasks | |
Published | 2019-09-01 |
URL | https://www.aclweb.org/anthology/W19-8710/ |
https://www.aclweb.org/anthology/W19-8710 | |
PWC | https://paperswithcode.com/paper/the-chineseenglish-political-interpreting |
Repo | |
Framework | |
Natural Language Generation for Effective Knowledge Distillation
Title | Natural Language Generation for Effective Knowledge Distillation |
Authors | Raphael Tang, Yao Lu, Jimmy Lin |
Abstract | Knowledge distillation can effectively transfer knowledge from BERT, a deep language representation model, to traditional, shallow word embedding-based neural networks, helping them approach or exceed the quality of other heavyweight language representation models. As shown in previous work, critical to this distillation procedure is the construction of an unlabeled transfer dataset, which enables effective knowledge transfer. To create transfer set examples, we propose to sample from pretrained language models fine-tuned on task-specific text. Unlike previous techniques, this directly captures the purpose of the transfer set. We hypothesize that this principled, general approach outperforms rule-based techniques. On four datasets in sentiment classification, sentence similarity, and linguistic acceptability, we show that our approach improves upon previous methods. We outperform OpenAI GPT, a deep pretrained transformer, on three of the datasets, while using a single-layer bidirectional LSTM that runs at least ten times faster. |
Tasks | Linguistic Acceptability, Sentiment Analysis, Text Generation, Transfer Learning |
Published | 2019-11-01 |
URL | https://www.aclweb.org/anthology/D19-6122/ |
https://www.aclweb.org/anthology/D19-6122 | |
PWC | https://paperswithcode.com/paper/natural-language-generation-for-effective |
Repo | |
Framework | |
Word and Document Embedding with vMF-Mixture Priors on Context Word Vectors
Title | Word and Document Embedding with vMF-Mixture Priors on Context Word Vectors |
Authors | Shoaib Jameel, Steven Schockaert |
Abstract | Word embedding models typically learn two types of vectors: target word vectors and context word vectors. These vectors are normally learned such that they are predictive of some word co-occurrence statistic, but they are otherwise unconstrained. However, the words from a given language can be organized in various natural groupings, such as syntactic word classes (e.g. nouns, adjectives, verbs) and semantic themes (e.g. sports, politics, sentiment). Our hypothesis in this paper is that embedding models can be improved by explicitly imposing a cluster structure on the set of context word vectors. To this end, our model relies on the assumption that context word vectors are drawn from a mixture of von Mises-Fisher (vMF) distributions, where the parameters of this mixture distribution are jointly optimized with the word vectors. We show that this results in word vectors which are qualitatively different from those obtained with existing word embedding models. We furthermore show that our embedding model can also be used to learn high-quality document representations. |
Tasks | Document Embedding |
Published | 2019-07-01 |
URL | https://www.aclweb.org/anthology/P19-1321/ |
https://www.aclweb.org/anthology/P19-1321 | |
PWC | https://paperswithcode.com/paper/word-and-document-embedding-with-vmf-mixture |
Repo | |
Framework | |
Blood Pressure Estimation from Photoplethysmogram Using a Spectro-Temporal Deep Neural Network
Title | Blood Pressure Estimation from Photoplethysmogram Using a Spectro-Temporal Deep Neural Network |
Authors | Gašper Slapničar, Nejc Mlakar, Mitja Luštrek |
Abstract | Blood pressure (BP) is a direct indicator of hypertension, a dangerous and potentially deadly condition. Regular monitoring of BP is thus important, but many people have aversion towards cuff-based devices, and their limitation is that they can only be used at rest. Using just a photoplethysmogram (PPG) to estimate BP is a potential solution investigated in our study. We analyzed the MIMIC III database for high-quality PPG and arterial BP waveforms, resulting in over 700 h of signals after preprocessing, belonging to 510 subjects. We then used the PPG alongside its first and second derivative as inputs into a novel spectro-temporal deep neural network with residual connections. We have shown in a leave-one-subject-out experiment that the network is able to model the dependency between PPG and BP, achieving mean absolute errors of 9.43 for systolic and 6.88 for diastolic BP. Additionally we have shown that personalization of models is important and substantially improves the results, while deriving a good general predictive model is difficult. We have made crucial parts of our study, especially the list of used subjects and our neural network code, publicly available, in an effort to provide a solid baseline and simplify potential comparison between future studies on an explicit MIMIC III subset. |
Tasks | Blood pressure estimation, Photoplethysmography (PPG) |
Published | 2019-08-04 |
URL | https://doi.org/10.3390/s19153420 |
https://www.mdpi.com/1424-8220/19/15/3420/pdf | |
PWC | https://paperswithcode.com/paper/blood-pressure-estimation-from |
Repo | |
Framework | |
Rotational Unit of Memory: A Novel Representation Unit for RNNs with Scalable Applications
Title | Rotational Unit of Memory: A Novel Representation Unit for RNNs with Scalable Applications |
Authors | Rumen Dangovski, Li Jing, Preslav Nakov, Mi{'c}o Tatalovi{'c}, Marin Solja{\v{c}}i{'c} |
Abstract | Stacking long short-term memory (LSTM) cells or gated recurrent units (GRUs) as part of a recurrent neural network (RNN) has become a standard approach to solving a number of tasks ranging from language modeling to text summarization. Although LSTMs and GRUs were designed to model long-range dependencies more accurately than conventional RNNs, they nevertheless have problems copying or recalling information from the long distant past. Here, we derive a phase-coded representation of the memory state, Rotational Unit of Memory (RUM), that unifies the concepts of unitary learning and associative memory. We show experimentally that RNNs based on RUMs can solve basic sequential tasks such as memory copying and memory recall much better than LSTMs/GRUs. We further demonstrate that by replacing LSTM/GRU with RUM units we can apply neural networks to real-world problems such as language modeling and text summarization, yielding results comparable to the state of the art. |
Tasks | Language Modelling, Text Summarization |
Published | 2019-03-01 |
URL | https://www.aclweb.org/anthology/Q19-1008/ |
https://www.aclweb.org/anthology/Q19-1008 | |
PWC | https://paperswithcode.com/paper/rotational-unit-of-memory-a-novel |
Repo | |
Framework | |
Learning-Based Frequency Estimation Algorithms
Title | Learning-Based Frequency Estimation Algorithms |
Authors | Chen-Yu Hsu, Piotr Indyk, Dina Katabi, Ali Vakilian |
Abstract | Estimating the frequencies of elements in a data stream is a fundamental task in data analysis and machine learning. The problem is typically addressed using streaming algorithms which can process very large data using limited storage. Today’s streaming algorithms, however, cannot exploit patterns in their input to improve performance. We propose a new class of algorithms that automatically learn relevant patterns in the input data and use them to improve its frequency estimates. The proposed algorithms combine the benefits of machine learning with the formal guarantees available through algorithm theory. We prove that our learning-based algorithms have lower estimation errors than their non-learning counterparts. We also evaluate our algorithms on two real-world datasets and demonstrate empirically their performance gains. |
Tasks | |
Published | 2019-05-01 |
URL | https://openreview.net/forum?id=r1lohoCqY7 |
https://openreview.net/pdf?id=r1lohoCqY7 | |
PWC | https://paperswithcode.com/paper/learning-based-frequency-estimation |
Repo | |
Framework | |