Paper Group ANR 474
Statistical Machine Translation for Indian Languages: Mission Hindi. Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation. Joint Extraction of Events and Entities within a Document Context. Joint M-Best-Diverse Labelings as a Parametric Submodular Minimization. A Probabilistic Adaptive Search System for Exploring the F …
Statistical Machine Translation for Indian Languages: Mission Hindi
| Title | Statistical Machine Translation for Indian Languages: Mission Hindi |
| Authors | Raj Nath Patel, Prakash B. Pimpale, Sasikumar M |
| Abstract | This paper discusses Centre for Development of Advanced Computing Mumbai’s (CDACM) submission to the NLP Tools Contest on Statistical Machine Translation in Indian Languages (ILSMT) 2014 (collocated with ICON 2014). The objective of the contest was to explore the effectiveness of Statistical Machine Translation (SMT) for Indian language to Indian language and English-Hindi machine translation. In this paper, we have proposed that suffix separation and word splitting for SMT from agglutinative languages to Hindi significantly improves over the baseline (BL). We have also shown that the factored model with reordering outperforms the phrase-based SMT for English-Hindi (\enhi). We report our work on all five pairs of languages, namely Bengali-Hindi (\bnhi), Marathi-Hindi (\mrhi), Tamil-Hindi (\tahi), Telugu-Hindi (\tehi), and \enhi for Health, Tourism, and General domains. |
| Tasks | Machine Translation |
| Published | 2016-10-24 |
| URL | http://arxiv.org/abs/1610.07418v1 |
| http://arxiv.org/pdf/1610.07418v1.pdf | |
| PWC | https://paperswithcode.com/paper/statistical-machine-translation-for-indian-1 |
| Repo | |
| Framework | |
Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation
| Title | Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation |
| Authors | Alexandre Berard, Olivier Pietquin, Christophe Servan, Laurent Besacier |
| Abstract | This paper proposes a first attempt to build an end-to-end speech-to-text translation system, which does not use source language transcription during learning or decoding. We propose a model for direct speech-to-text translation, which gives promising results on a small French-English synthetic corpus. Relaxing the need for source language transcription would drastically change the data collection methodology in speech translation, especially in under-resourced scenarios. For instance, in the former project DARPA TRANSTAC (speech translation from spoken Arabic dialects), a large effort was devoted to the collection of speech transcripts (and a prerequisite to obtain transcripts was often a detailed transcription guide for languages with little standardized spelling). Now, if end-to-end approaches for speech-to-text translation are successful, one might consider collecting data by asking bilingual speakers to directly utter speech in the source language from target language text utterances. Such an approach has the advantage to be applicable to any unwritten (source) language. |
| Tasks | |
| Published | 2016-12-06 |
| URL | http://arxiv.org/abs/1612.01744v1 |
| http://arxiv.org/pdf/1612.01744v1.pdf | |
| PWC | https://paperswithcode.com/paper/listen-and-translate-a-proof-of-concept-for |
| Repo | |
| Framework | |
Joint Extraction of Events and Entities within a Document Context
| Title | Joint Extraction of Events and Entities within a Document Context |
| Authors | Bishan Yang, Tom Mitchell |
| Abstract | Events and entities are closely related; entities are often actors or participants in events and events without entities are uncommon. The interpretation of events and entities is highly contextually dependent. Existing work in information extraction typically models events separately from entities, and performs inference at the sentence level, ignoring the rest of the document. In this paper, we propose a novel approach that models the dependencies among variables of events, entities, and their relations, and performs joint inference of these variables across a document. The goal is to enable access to document-level contextual information and facilitate context-aware predictions. We demonstrate that our approach substantially outperforms the state-of-the-art methods for event extraction as well as a strong baseline for entity extraction. |
| Tasks | Entity Extraction |
| Published | 2016-09-12 |
| URL | http://arxiv.org/abs/1609.03632v1 |
| http://arxiv.org/pdf/1609.03632v1.pdf | |
| PWC | https://paperswithcode.com/paper/joint-extraction-of-events-and-entities |
| Repo | |
| Framework | |
Joint M-Best-Diverse Labelings as a Parametric Submodular Minimization
| Title | Joint M-Best-Diverse Labelings as a Parametric Submodular Minimization |
| Authors | Alexander Kirillov, Alexander Shekhovtsov, Carsten Rother, Bogdan Savchynskyy |
| Abstract | We consider the problem of jointly inferring the M-best diverse labelings for a binary (high-order) submodular energy of a graphical model. Recently, it was shown that this problem can be solved to a global optimum, for many practically interesting diversity measures. It was noted that the labelings are, so-called, nested. This nestedness property also holds for labelings of a class of parametric submodular minimization problems, where different values of the global parameter $\gamma$ give rise to different solutions. The popular example of the parametric submodular minimization is the monotonic parametric max-flow problem, which is also widely used for computing multiple labelings. As the main contribution of this work we establish a close relationship between diversity with submodular energies and the parametric submodular minimization. In particular, the joint M-best diverse labelings can be obtained by running a non-parametric submodular minimization (in the special case - max-flow) solver for M different values of $\gamma$ in parallel, for certain diversity measures. Importantly, the values for $\gamma$ can be computed in a closed form in advance, prior to any optimization. These theoretical results suggest two simple yet efficient algorithms for the joint M-best diverse problem, which outperform competitors in terms of runtime and quality of results. In particular, as we show in the paper, the new methods compute the exact M-best diverse labelings faster than a popular method of Batra et al., which in some sense only obtains approximate solutions. |
| Tasks | |
| Published | 2016-06-22 |
| URL | http://arxiv.org/abs/1606.07015v2 |
| http://arxiv.org/pdf/1606.07015v2.pdf | |
| PWC | https://paperswithcode.com/paper/joint-m-best-diverse-labelings-as-a |
| Repo | |
| Framework | |
A Probabilistic Adaptive Search System for Exploring the Face Space
| Title | A Probabilistic Adaptive Search System for Exploring the Face Space |
| Authors | Andres G. Abad, Luis I. Reyes Castro |
| Abstract | Face recall is a basic human cognitive process performed routinely, e.g., when meeting someone and determining if we have met that person before. Assisting a subject during face recall by suggesting candidate faces can be challenging. One of the reasons is that the search space - the face space - is quite large and lacks structure. A commercial application of face recall is facial composite systems - such as Identikit, PhotoFIT, and CD-FIT - where a witness searches for an image of a face that resembles his memory of a particular offender. The inherent uncertainty and cost in the evaluation of the objective function, the large size and lack of structure of the search space, and the unavailability of the gradient concept makes this problem inappropriate for traditional optimization methods. In this paper we propose a novel evolutionary approach for searching the face space that can be used as a facial composite system. The approach is inspired by methods of Bayesian optimization and differs from other applications in the use of the skew-normal distribution as its acquisition function. This choice of acquisition function provides greater granularity, with regularized, conservative, and realistic results. |
| Tasks | |
| Published | 2016-04-28 |
| URL | http://arxiv.org/abs/1604.08524v1 |
| http://arxiv.org/pdf/1604.08524v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-probabilistic-adaptive-search-system-for |
| Repo | |
| Framework | |
Syntactic Structures and Code Parameters
| Title | Syntactic Structures and Code Parameters |
| Authors | Kevin Shu, Matilde Marcolli |
| Abstract | We assign binary and ternary error-correcting codes to the data of syntactic structures of world languages and we study the distribution of code points in the space of code parameters. We show that, while most codes populate the lower region approximating a superposition of Thomae functions, there is a substantial presence of codes above the Gilbert-Varshamov bound and even above the asymptotic bound and the Plotkin bound. We investigate the dynamics induced on the space of code parameters by spin glass models of language change, and show that, in the presence of entailment relations between syntactic parameters the dynamics can sometimes improve the code. For large sets of languages and syntactic data, one can gain information on the spin glass dynamics from the induced dynamics in the space of code parameters. |
| Tasks | |
| Published | 2016-10-02 |
| URL | http://arxiv.org/abs/1610.00311v1 |
| http://arxiv.org/pdf/1610.00311v1.pdf | |
| PWC | https://paperswithcode.com/paper/syntactic-structures-and-code-parameters |
| Repo | |
| Framework | |
Forest Floor Visualizations of Random Forests
| Title | Forest Floor Visualizations of Random Forests |
| Authors | Soeren H. Welling, Hanne H. F. Refsgaard, Per B. Brockhoff, Line H. Clemmensen |
| Abstract | We propose a novel methodology, forest floor, to visualize and interpret random forest (RF) models. RF is a popular and useful tool for non-linear multi-variate classification and regression, which yields a good trade-off between robustness (low variance) and adaptiveness (low bias). Direct interpretation of a RF model is difficult, as the explicit ensemble model of hundreds of deep trees is complex. Nonetheless, it is possible to visualize a RF model fit by its mapping from feature space to prediction space. Hereby the user is first presented with the overall geometrical shape of the model structure, and when needed one can zoom in on local details. Dimensional reduction by projection is used to visualize high dimensional shapes. The traditional method to visualize RF model structure, partial dependence plots, achieve this by averaging multiple parallel projections. We suggest to first use feature contributions, a method to decompose trees by splitting features, and then subsequently perform projections. The advantages of forest floor over partial dependence plots is that interactions are not masked by averaging. As a consequence, it is possible to locate interactions, which are not visualized in a given projection. Furthermore, we introduce: a goodness-of-visualization measure, use of colour gradients to identify interactions and an out-of-bag cross validated variant of feature contributions. |
| Tasks | |
| Published | 2016-05-30 |
| URL | http://arxiv.org/abs/1605.09196v3 |
| http://arxiv.org/pdf/1605.09196v3.pdf | |
| PWC | https://paperswithcode.com/paper/forest-floor-visualizations-of-random-forests |
| Repo | |
| Framework | |
Sparsey: Event Recognition via Deep Hierarchical Spare Distributed Codes
| Title | Sparsey: Event Recognition via Deep Hierarchical Spare Distributed Codes |
| Authors | Gerard J. Rinkus |
| Abstract | Visual cortex’s hierarchical, multi-level organization is captured in many biologically inspired computational vision models, the general idea being that progressively larger scale, more complex spatiotemporal features are represented in progressively higher areas. However, most earlier models use localist representations (codes) in each representational field, which we equate with the cortical macrocolumn (mac), at each level. In localism, each represented feature/event (item) is coded by a single unit. Our model, Sparsey, is also hierarchical but crucially, uses sparse distributed coding (SDC) in every mac in all levels. In SDC, each represented item is coded by a small subset of the mac’s units. SDCs of different items can overlap and the size of overlap between items can represent their similarity. The difference between localism and SDC is crucial because SDC allows the two essential operations of associative memory, storing a new item and retrieving the best-matching stored item, to be done in fixed time for the life of the model. Since the model’s core algorithm, which does both storage and retrieval (inference), makes a single pass over all macs on each time step, the overall model’s storage/retrieval operation is also fixed-time, a criterion we consider essential for scalability to huge datasets. A 2010 paper described a nonhierarchical version of this model in the context of purely spatial pattern processing. Here, we elaborate a fully hierarchical model (arbitrary numbers of levels and macs per level), describing novel model principles like progressive critical periods, dynamic modulation of principal cells’ activation functions based on a mac-level familiarity measure, representation of multiple simultaneously active hypotheses, a novel method of time warp invariant recognition, and we report results showing learning/recognition of spatiotemporal patterns. |
| Tasks | |
| Published | 2016-11-12 |
| URL | http://arxiv.org/abs/1611.04023v1 |
| http://arxiv.org/pdf/1611.04023v1.pdf | |
| PWC | https://paperswithcode.com/paper/sparsey-event-recognition-via-deep |
| Repo | |
| Framework | |
Assisted Energy Management in Smart Microgrids
| Title | Assisted Energy Management in Smart Microgrids |
| Authors | Andrea Monacchi, Wilfried Elmenreich |
| Abstract | Demand response provides utilities with a mechanism to share with end users the stochasticity resulting from the use of renewable sources. Pricing is accordingly used to reflect energy availability, to allocate such a limited resource to those loads that value it most. However, the strictly competitive mechanism can result in service interruption in presence of competing demand. To solve this issue we investigate on the use of forward contracts, i.e., service level agreements priced to reflect the expectation of future supply and demand curves. Given the limited resources of microgrids, service interruption is an opposite objective to the one of service availability. We firstly design policy-based brokers and identify then a learning broker based on artificial neural networks. We show the latter being progressively minimizing the reimbursement costs and maximizing the overall profit. |
| Tasks | |
| Published | 2016-06-06 |
| URL | http://arxiv.org/abs/1606.01949v1 |
| http://arxiv.org/pdf/1606.01949v1.pdf | |
| PWC | https://paperswithcode.com/paper/assisted-energy-management-in-smart |
| Repo | |
| Framework | |
Machine learning methods for accurate delineation of tumors in PET images
| Title | Machine learning methods for accurate delineation of tumors in PET images |
| Authors | Jakub Czakon, Filip Drapejkowski, Grzegorz Zurek, Piotr Giedziun, Jacek Zebrowski, Witold Dyrka |
| Abstract | In oncology, Positron Emission Tomography imaging is widely used in diagnostics of cancer metastases, in monitoring of progress in course of the cancer treatment, and in planning radiotherapeutic interventions. Accurate and reproducible delineation of the tumor in the Positron Emission Tomography scans remains a difficult task, despite being crucial for delivering appropriate radiation dose, minimizing adverse side-effects of the therapy, and reliable evaluation of treatment. In this piece of research we attempt to solve the problem of automated delineation of the tumor using 3d implementations of the spatial distance weighted fuzzy c-means, the deep convolutional neural network and a dictionary model. The methods, in diverse ways, combine intensity and spatial information. |
| Tasks | |
| Published | 2016-10-29 |
| URL | http://arxiv.org/abs/1610.09493v1 |
| http://arxiv.org/pdf/1610.09493v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-methods-for-accurate |
| Repo | |
| Framework | |
Significance Driven Hybrid 8T-6T SRAM for Energy-Efficient Synaptic Storage in Artificial Neural Networks
| Title | Significance Driven Hybrid 8T-6T SRAM for Energy-Efficient Synaptic Storage in Artificial Neural Networks |
| Authors | Gopalakrishnan Srinivasan, Parami Wijesinghe, Syed Shakib Sarwar, Akhilesh Jaiswal, Kaushik Roy |
| Abstract | Multilayered artificial neural networks (ANN) have found widespread utility in classification and recognition applications. The scale and complexity of such networks together with the inadequacies of general purpose computing platforms have led to a significant interest in the development of efficient hardware implementations. In this work, we focus on designing energy efficient on-chip storage for the synaptic weights. In order to minimize the power consumption of typical digital CMOS implementations of such large-scale networks, the digital neurons could be operated reliably at scaled voltages by reducing the clock frequency. On the contrary, the on-chip synaptic storage designed using a conventional 6T SRAM is susceptible to bitcell failures at reduced voltages. However, the intrinsic error resiliency of NNs to small synaptic weight perturbations enables us to scale the operating voltage of the 6TSRAM. Our analysis on a widely used digit recognition dataset indicates that the voltage can be scaled by 200mV from the nominal operating voltage (950mV) for practically no loss (less than 0.5%) in accuracy (22nm predictive technology). Scaling beyond that causes substantial performance degradation owing to increased probability of failures in the MSBs of the synaptic weights. We, therefore propose a significance driven hybrid 8T-6T SRAM, wherein the sensitive MSBs are stored in 8T bitcells that are robust at scaled voltages due to decoupled read and write paths. In an effort to further minimize the area penalty, we present a synaptic-sensitivity driven hybrid memory architecture consisting of multiple 8T-6T SRAM banks. Our circuit to system-level simulation framework shows that the proposed synaptic-sensitivity driven architecture provides a 30.91% reduction in the memory access power with a 10.41% area overhead, for less than 1% loss in the classification accuracy. |
| Tasks | |
| Published | 2016-02-27 |
| URL | http://arxiv.org/abs/1602.08556v1 |
| http://arxiv.org/pdf/1602.08556v1.pdf | |
| PWC | https://paperswithcode.com/paper/significance-driven-hybrid-8t-6t-sram-for |
| Repo | |
| Framework | |
A Latent-class Model for Estimating Product-choice Probabilities from Clickstream Data
| Title | A Latent-class Model for Estimating Product-choice Probabilities from Clickstream Data |
| Authors | Naoki Nishimura, Noriyoshi Sukegawa, Yuichi Takano, Jiro Iwanaga |
| Abstract | This paper analyzes customer product-choice behavior based on the recency and frequency of each customer’s page views on e-commerce sites. Recently, we devised an optimization model for estimating product-choice probabilities that satisfy monotonicity, convexity, and concavity constraints with respect to recency and frequency. This shape-restricted model delivered high predictive performance even when there were few training samples. However, typical e-commerce sites deal in many different varieties of products, so the predictive performance of the model can be further improved by integration of such product heterogeneity. For this purpose, we develop a novel latent-class shape-restricted model for estimating product-choice probabilities for each latent class of products. We also give a tailored expectation-maximization algorithm for parameter estimation. Computational results demonstrate that higher predictive performance is achieved with our latent-class model than with the previous shape-restricted model and common latent-class logistic regression. |
| Tasks | |
| Published | 2016-12-20 |
| URL | http://arxiv.org/abs/1612.06589v1 |
| http://arxiv.org/pdf/1612.06589v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-latent-class-model-for-estimating-product |
| Repo | |
| Framework | |
Blind score normalization method for PLDA based speaker recognition
| Title | Blind score normalization method for PLDA based speaker recognition |
| Authors | Danila Doroshin, Nikolay Lubimov, Marina Nastasenko, Mikhail Kotov |
| Abstract | Probabilistic Linear Discriminant Analysis (PLDA) has become state-of-the-art method for modeling $i$-vector space in speaker recognition task. However the performance degradation is observed if enrollment data size differs from one speaker to another. This paper presents a solution to such problem by introducing new PLDA scoring normalization technique. Normalization parameters are derived in a blind way, so that, unlike traditional \textit{ZT-norm}, no extra development data is required. Moreover, proposed method has shown to be optimal in terms of detection cost function. The experiments conducted on NIST SRE 2014 database demonstrate an improved accuracy in a mixed enrollment number condition. |
| Tasks | Speaker Recognition |
| Published | 2016-02-22 |
| URL | http://arxiv.org/abs/1602.06967v1 |
| http://arxiv.org/pdf/1602.06967v1.pdf | |
| PWC | https://paperswithcode.com/paper/blind-score-normalization-method-for-plda |
| Repo | |
| Framework | |
Role of Simplicity in Creative Behaviour: The Case of the Poietic Generator
| Title | Role of Simplicity in Creative Behaviour: The Case of the Poietic Generator |
| Authors | Antoine Saillenfest, Jean-Louis Dessalles, Olivier Auber |
| Abstract | We propose to apply Simplicity Theory (ST) to model interest in creative situations. ST has been designed to describe and predict interest in communication. Here we use ST to derive a decision rule that we apply to a simplified version of a creative game, the Poietic Generator. The decision rule produces what can be regarded as an elementary form of creativity. This study is meant as a proof of principle. It suggests that some creative actions may be motivated by the search for unexpected simplicity. |
| Tasks | |
| Published | 2016-12-22 |
| URL | http://arxiv.org/abs/1612.08657v1 |
| http://arxiv.org/pdf/1612.08657v1.pdf | |
| PWC | https://paperswithcode.com/paper/role-of-simplicity-in-creative-behaviour-the |
| Repo | |
| Framework | |
Computing with hardware neurons: spiking or classical? Perspectives of applied Spiking Neural Networks from the hardware side
| Title | Computing with hardware neurons: spiking or classical? Perspectives of applied Spiking Neural Networks from the hardware side |
| Authors | Sergei Dytckov, Masoud Daneshtalab |
| Abstract | While classical neural networks take a position of a leading method in the machine learning community, spiking neuromorphic systems bring attention and large projects in neuroscience. Spiking neural networks were shown to be able to substitute networks of classical neurons in applied tasks. This work explores recent hardware designs focusing on perspective applications (like convolutional neural networks) for both neuron types from the energy efficiency side to analyse whether there is a possibility for spiking neuromorphic hardware to grow up for a wider use. Our comparison shows that spiking hardware is at least on the same level of energy efficiency or even higher than non-spiking on a level of basic operations. However, on a system level, spiking systems are outmatched and consume much more energy due to inefficient data representation with a long series of spikes. If spike-driven applications, minimizing an amount of spikes, are developed, spiking neural systems may reach the energy efficiency level of classical neural systems. However, in the near future, both type of neuromorphic systems may benefit from emerging memory technologies, minimizing the energy consumption of computation and memory for both neuron types. That would make infrastructure and data transfer energy dominant on the system level. We expect that spiking neurons have some benefits, which would allow achieving better energy results. Still the problem of an amount of spikes will still be the major bottleneck for spiking hardware systems. |
| Tasks | |
| Published | 2016-02-05 |
| URL | http://arxiv.org/abs/1602.02009v2 |
| http://arxiv.org/pdf/1602.02009v2.pdf | |
| PWC | https://paperswithcode.com/paper/computing-with-hardware-neurons-spiking-or |
| Repo | |
| Framework | |
