Paper Group NANR 34
Hybrid Neural Network Alignment and Lexicon Model in Direct HMM for Statistical Machine Translation. Alternating minimization for dictionary learning with random initialization. DualNet: Learn Complementary Features for Image Recognition. A Diachronic Corpus for Romanian (RoDia). Evaluating Compound Splitters Extrinsically with Textual Entailment. …
Hybrid Neural Network Alignment and Lexicon Model in Direct HMM for Statistical Machine Translation
| Title | Hybrid Neural Network Alignment and Lexicon Model in Direct HMM for Statistical Machine Translation |
| Authors | Weiyue Wang, Tamer Alkhouli, Derui Zhu, Hermann Ney |
| Abstract | Recently, the neural machine translation systems showed their promising performance and surpassed the phrase-based systems for most translation tasks. Retreating into conventional concepts machine translation while utilizing effective neural models is vital for comprehending the leap accomplished by neural machine translation over phrase-based methods. This work proposes a direct HMM with neural network-based lexicon and alignment models, which are trained jointly using the Baum-Welch algorithm. The direct HMM is applied to rerank the n-best list created by a state-of-the-art phrase-based translation system and it provides improvements by up to 1.0{%} Bleu scores on two different translation tasks. |
| Tasks | Machine Translation, Word Alignment |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2020/ |
| https://www.aclweb.org/anthology/P17-2020 | |
| PWC | https://paperswithcode.com/paper/hybrid-neural-network-alignment-and-lexicon |
| Repo | |
| Framework | |
Alternating minimization for dictionary learning with random initialization
| Title | Alternating minimization for dictionary learning with random initialization |
| Authors | Niladri Chatterji, Peter L. Bartlett |
| Abstract | We present theoretical guarantees for an alternating minimization algorithm for the dictionary learning/sparse coding problem. The dictionary learning problem is to factorize vector samples $y^{1},y^{2},\ldots, y^{n}$ into an appropriate basis (dictionary) $A^$ and sparse vectors $x^{1},\ldots,x^{n*}$. Our algorithm is a simple alternating minimization procedure that switches between $\ell_1$ minimization and gradient descent in alternate steps. Dictionary learning and specifically alternating minimization algorithms for dictionary learning are well studied both theoretically and empirically. However, in contrast to previous theoretical analyses for this problem, we replace a condition on the operator norm (that is, the largest magnitude singular value) of the true underlying dictionary $A^*$ with a condition on the matrix infinity norm (that is, the largest magnitude term). This not only allows us to get convergence rates for the error of the estimated dictionary measured in the matrix infinity norm, but also ensures that a random initialization will provably converge to the global optimum. Our guarantees are under a reasonable generative model that allows for dictionaries with growing operator norms, and can handle an arbitrary level of overcompleteness, while having sparsity that is information theoretically optimal. We also establish upper bounds on the sample complexity of our algorithm. |
| Tasks | Dictionary Learning |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6795-alternating-minimization-for-dictionary-learning-with-random-initialization |
| http://papers.nips.cc/paper/6795-alternating-minimization-for-dictionary-learning-with-random-initialization.pdf | |
| PWC | https://paperswithcode.com/paper/alternating-minimization-for-dictionary-1 |
| Repo | |
| Framework | |
DualNet: Learn Complementary Features for Image Recognition
| Title | DualNet: Learn Complementary Features for Image Recognition |
| Authors | Saihui Hou, Xu Liu, Zilei Wang |
| Abstract | In this work we propose a novel framework named DualNet aiming at learning more accurate representation for image recognition. Here two parallel neural networks are coordinated to learn complementary features and thus a wider network is constructed. Specifically, we logically divide an end-to-end deep convolutional neural network into two functional parts, i.e., feature extractor and image classifier. The extractors of two subnetworks are placed side by side, which exactly form the feature extractor of DualNet. Then the two-stream features are aggregated to the final classifier for overall classification, while two auxiliary classifiers are appended behind the feature extractor of each subnetwork to make the separately learned features discriminative alone. The complementary constraint is imposed by weighting the three classifiers, which is indeed the key of DualNet. The corresponding training strategy is also proposed, consisting of iterative training and joint finetuning, to make the two subnetworks cooperate well with each other. Finally, DualNet based on the well-known CaffeNet, VGGNet, NIN and ResNet are thoroughly investigated and experimentally evaluated on multiple datasets including CIFAR-100, Stanford Dogs and UEC FOOD-100. The results demonstrate that DualNet can really help learn more accurate image representation, and thus result in higher accuracy for recognition. In particular, the performance on CIFAR-100 is state-of-the-art compared to the recent works. |
| Tasks | |
| Published | 2017-10-01 |
| URL | http://openaccess.thecvf.com/content_iccv_2017/html/Hou_DualNet_Learn_Complementary_ICCV_2017_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2017/papers/Hou_DualNet_Learn_Complementary_ICCV_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/dualnet-learn-complementary-features-for |
| Repo | |
| Framework | |
A Diachronic Corpus for Romanian (RoDia)
| Title | A Diachronic Corpus for Romanian (RoDia) |
| Authors | Ludmila Malahov, C{\u{a}}t{\u{a}}lina M{\u{a}}r{\u{a}}nduc, Alex Colesnicov, ru |
| Abstract | This paper describes a Romanian Dependency Treebank, built at the Al. I. Cuza University (UAIC), and a special OCR techniques used to build it. The corpus has rich morphological and syntactic annotation. There are few annotated representative corpora in Romanian, and the existent ones are mainly focused on the contemporary Romanian standard. The corpus described below is focused on the non-standard aspects of the language, the Regional and the Old Romanian. Having the intention to participate at the PROIEL project, which aligns oldest New Testaments, we annotate the first printed Romanian New Testament (Alba Iulia, 1648). We began by applying the UAIC tools for the morphological and syntactic processing of Contemporary Romanian over the book{'}s first quarter (second edition). By carefully manually correcting the result of the automated annotation (having a modest accuracy) we obtained a sub-corpus for the training of tools for the Old Romanian processing. But the first edition of the New Testament is written in Cyrillic letters. The existence of books printed in the Old Cyrillic alphabet is a common problem for Romania and The Republic of Moldova, countries where the Romanian is spoken; a problem to solve by the joint efforts of the NLP researchers in the two countries. |
| Tasks | Information Retrieval, Optical Character Recognition, Question Answering |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-8101/ |
| http://doi.org/10.26615/978-954-452-046-5_001 | |
| PWC | https://paperswithcode.com/paper/a-diachronic-corpus-for-romanian-rodia |
| Repo | |
| Framework | |
Evaluating Compound Splitters Extrinsically with Textual Entailment
| Title | Evaluating Compound Splitters Extrinsically with Textual Entailment |
| Authors | Glorianna Jagfeld, Patrick Ziering, Lonneke van der Plas |
| Abstract | Traditionally, compound splitters are evaluated intrinsically on gold-standard data or extrinsically on the task of statistical machine translation. We explore a novel way for the extrinsic evaluation of compound splitters, namely recognizing textual entailment. Compound splitting has great potential for this novel task that is both transparent and well-defined. Moreover, we show that it addresses certain aspects that are either ignored in intrinsic evaluations or compensated for by taskinternal mechanisms in statistical machine translation. We show significant improvements using different compound splitting methods on a German textual entailment dataset. |
| Tasks | Information Retrieval, Machine Translation, Natural Language Inference, Speech Recognition |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2010/ |
| https://www.aclweb.org/anthology/P17-2010 | |
| PWC | https://paperswithcode.com/paper/evaluating-compound-splitters-extrinsically |
| Repo | |
| Framework | |
ELiRF-UPV at SemEval-2017 Task 4: Sentiment Analysis using Deep Learning
| Title | ELiRF-UPV at SemEval-2017 Task 4: Sentiment Analysis using Deep Learning |
| Authors | Jos{'e}-{'A}ngel Gonz{'a}lez, Ferran Pla, Llu{'\i}s-F. Hurtado |
| Abstract | This paper describes the participation of ELiRF-UPV team at task 4 of SemEval2017. Our approach is based on the use of convolutional and recurrent neural networks and the combination of general and specific word embeddings with polarity lexicons. We participated in all of the proposed subtasks both for English and Arabic languages using the same system with small variations. |
| Tasks | Opinion Mining, Sentiment Analysis, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2121/ |
| https://www.aclweb.org/anthology/S17-2121 | |
| PWC | https://paperswithcode.com/paper/elirf-upv-at-semeval-2017-task-4-sentiment |
| Repo | |
| Framework | |
Training Word Sense Embeddings With Lexicon-based Regularization
| Title | Training Word Sense Embeddings With Lexicon-based Regularization |
| Authors | Luis Nieto-Pi{~n}a, Richard Johansson |
| Abstract | We propose to improve word sense embeddings by enriching an automatic corpus-based method with lexicographic data. Information from a lexicon is introduced into the learning algorithm{'}s objective function through a regularizer. The incorporation of lexicographic data yields embeddings that are able to reflect expert-defined word senses, while retaining the robustness, high quality, and coverage of automatic corpus-based methods. These properties are observed in a manual inspection of the semantic clusters that different degrees of regularizer strength create in the vector space. Moreover, we evaluate the sense embeddings in two downstream applications: word sense disambiguation and semantic frame prediction, where they outperform simpler approaches. Our results show that a corpus-based model balanced with lexicographic data learns better representations and improve their performance in downstream tasks. |
| Tasks | Word Embeddings, Word Sense Disambiguation |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1029/ |
| https://www.aclweb.org/anthology/I17-1029 | |
| PWC | https://paperswithcode.com/paper/training-word-sense-embeddings-with-lexicon |
| Repo | |
| Framework | |
Retrieving Similar Lyrics for Music Recommendation System
| Title | Retrieving Similar Lyrics for Music Recommendation System |
| Authors | Braja Gopal Patra, Dipankar Das, B, Sivaji yopadhyay |
| Abstract | |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-7536/ |
| https://www.aclweb.org/anthology/W17-7536 | |
| PWC | https://paperswithcode.com/paper/retrieving-similar-lyrics-for-music |
| Repo | |
| Framework | |
Learning spatiotemporal piecewise-geodesic trajectories from longitudinal manifold-valued data
| Title | Learning spatiotemporal piecewise-geodesic trajectories from longitudinal manifold-valued data |
| Authors | Stéphanie Allassonniere, Juliette Chevallier, Stephane Oudard |
| Abstract | We introduce a hierarchical model which allows to estimate a group-average piecewise-geodesic trajectory in the Riemannian space of measurements and individual variability. This model falls into the well defined mixed-effect models. The subject-specific trajectories are defined through spatial and temporal transformations of the group-average piecewise-geodesic path, component by component. Thus we can apply our model to a wide variety of situations. Due to the non-linearity of the model, we use the Stochastic Approximation Expectation-Maximization algorithm to estimate the model parameters. Experiments on synthetic data validate this choice. The model is then applied to the metastatic renal cancer chemotherapy monitoring: we run estimations on RECIST scores of treated patients and estimate the time they escape from the treatment. Experiments highlight the role of the different parameters on the response to treatment. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6715-learning-spatiotemporal-piecewise-geodesic-trajectories-from-longitudinal-manifold-valued-data |
| http://papers.nips.cc/paper/6715-learning-spatiotemporal-piecewise-geodesic-trajectories-from-longitudinal-manifold-valued-data.pdf | |
| PWC | https://paperswithcode.com/paper/learning-spatiotemporal-piecewise-geodesic |
| Repo | |
| Framework | |
DUTH at SemEval-2017 Task 5: Sentiment Predictability in Financial Microblogging and News Articles
| Title | DUTH at SemEval-2017 Task 5: Sentiment Predictability in Financial Microblogging and News Articles |
| Authors | Symeon Symeonidis, John Kordonis, Dimitrios Effrosynidis, Avi Arampatzis |
| Abstract | We present the system developed by the team DUTH for the participation in Semeval-2017 task 5 - Fine-Grained Sentiment Analysis on Financial Microblogs and News, in subtasks A and B. Our approach to determine the sentiment of Microblog Messages and News Statements {&} Headlines is based on linguistic preprocessing, feature engineering, and supervised machine learning techniques. To train our model, we used Neural Network Regression, Linear Regression, Boosted Decision Tree Regression and Decision Forrest Regression classifiers to forecast sentiment scores. At the end, we present an error measure, so as to improve the performance about forecasting methods of the system. |
| Tasks | Feature Engineering, Information Retrieval, Sentiment Analysis |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2147/ |
| https://www.aclweb.org/anthology/S17-2147 | |
| PWC | https://paperswithcode.com/paper/duth-at-semeval-2017-task-5-sentiment |
| Repo | |
| Framework | |
Dense and Low-Rank Gaussian CRFs Using Deep Embeddings
| Title | Dense and Low-Rank Gaussian CRFs Using Deep Embeddings |
| Authors | Siddhartha Chandra, Nicolas Usunier, Iasonas Kokkinos |
| Abstract | In this work we introduce a structured prediction model that endows the Deep Gaussian Conditional Random Field (G-CRF) with a densely connected graph structure. We keep memory and computational complexity under control by expressing the pairwise interactions as inner products of low-dimensional, learnable embeddings. The G-CRF system matrix is therefore low-rank, allowing us to solve the resulting system in a few milliseconds on the GPU by using conjugate gradients. As in G-CRF, inference is exact, the unary and pairwise terms are jointly trained end-to-end by using analytic expressions for the gradients, while we also develop even faster, Potts-type variants of our embeddings. We show that the learned embeddings capture pixel-to-pixel affinities in a task-specific manner, while our approach achieves state of the art results on three challenging benchmarks, namely semantic segmentation, human part segmentation, and saliency estimation. Our implementation is fully GPU based, built on top of the Caffe library, and is available at https://github.com/siddharthachandra/gcrf-v2.0 |
| Tasks | Human Part Segmentation, Saliency Prediction, Semantic Segmentation, Structured Prediction |
| Published | 2017-10-01 |
| URL | http://openaccess.thecvf.com/content_iccv_2017/html/Chandra_Dense_and_Low-Rank_ICCV_2017_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2017/papers/Chandra_Dense_and_Low-Rank_ICCV_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/dense-and-low-rank-gaussian-crfs-using-deep |
| Repo | |
| Framework | |
Collecting Telemetry Data Privately
| Title | Collecting Telemetry Data Privately |
| Authors | Bolin Ding, Janardhan Kulkarni, Sergey Yekhanin |
| Abstract | The collection and analysis of telemetry data from user’s devices is routinely performed by many software companies. Telemetry collection leads to improved user experience but poses significant risks to users’ privacy. Locally differentially private (LDP) algorithms have recently emerged as the main tool that allows data collectors to estimate various population statistics, while preserving privacy. The guarantees provided by such algorithms are typically very strong for a single round of telemetry collection, but degrade rapidly when telemetry is collected regularly. In particular, existing LDP algorithms are not suitable for repeated collection of counter data such as daily app usage statistics. In this paper, we develop new LDP mechanisms geared towards repeated collection of counter data, with formal privacy guarantees even after being executed for an arbitrarily long period of time. For two basic analytical tasks, mean estimation and histogram estimation, our LDP mechanisms for repeated data collection provide estimates with comparable or even the same accuracy as existing single-round LDP collection mechanisms. We conduct empirical evaluation on real-world counter datasets to verify our theoretical results. Our mechanisms have been deployed by Microsoft to collect telemetry across millions of devices. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6948-collecting-telemetry-data-privately |
| http://papers.nips.cc/paper/6948-collecting-telemetry-data-privately.pdf | |
| PWC | https://paperswithcode.com/paper/collecting-telemetry-data-privately |
| Repo | |
| Framework | |
Classifier Stacking for Native Language Identification
| Title | Classifier Stacking for Native Language Identification |
| Authors | Wen Li, Liang Zou |
| Abstract | This paper reports our contribution (team WLZ) to the NLI Shared Task 2017 (essay track). We first extract lexical and syntactic features from the essays, perform feature weighting and selection, and train linear support vector machine (SVM) classifiers each on an individual feature type. The output of base classifiers, as probabilities for each class, are then fed into a multilayer perceptron to predict the native language of the author. We also report the performance of each feature type, as well as the best features of a type. Our system achieves an accuracy of 86.55{%}, which is among the best performing systems of this shared task. |
| Tasks | Language Acquisition, Language Identification, Native Language Identification, Text Classification |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5044/ |
| https://www.aclweb.org/anthology/W17-5044 | |
| PWC | https://paperswithcode.com/paper/classifier-stacking-for-native-language |
| Repo | |
| Framework | |
Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications
| Title | Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5000/ |
| https://www.aclweb.org/anthology/W17-5000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-12th-workshop-on |
| Repo | |
| Framework | |
Finite state intensional semantics
| Title | Finite state intensional semantics |
| Authors | Mats Rooth |
| Abstract | |
| Tasks | |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-6815/ |
| https://www.aclweb.org/anthology/W17-6815 | |
| PWC | https://paperswithcode.com/paper/finite-state-intensional-semantics |
| Repo | |
| Framework | |
