July 28, 2019

2861 words 14 mins read

Paper Group ANR 212

One-Shot Neural Cross-Lingual Transfer for Paradigm Completion. Learning Latent Representations for Speech Generation and Transformation. Towards Proof Synthesis Guided by Neural Machine Translation for Intuitionistic Propositional Logic. A convolutional autoencoder approach for mining features in cellular electron cryo-tomograms and weakly supervi …

One-Shot Neural Cross-Lingual Transfer for Paradigm Completion


Title	One-Shot Neural Cross-Lingual Transfer for Paradigm Completion
Authors	Katharina Kann, Ryan Cotterell, Hinrich Schütze
Abstract	We present a novel cross-lingual transfer method for paradigm completion, the task of mapping a lemma to its inflected forms, using a neural encoder-decoder model, the state of the art for the monolingual task. We use labeled data from a high-resource language to increase performance on a low-resource language. In experiments on 21 language pairs from four different language families, we obtain up to 58% higher accuracy than without transfer and show that even zero-shot and one-shot learning are possible. We further find that the degree of language relatedness strongly influences the ability to transfer morphological knowledge.
Tasks	Cross-Lingual Transfer, One-Shot Learning
Published	2017-03-31
URL	http://arxiv.org/abs/1704.00052v1
PDF	http://arxiv.org/pdf/1704.00052v1.pdf
PWC	https://paperswithcode.com/paper/one-shot-neural-cross-lingual-transfer-for
Repo
Framework

Learning Latent Representations for Speech Generation and Transformation


Title	Learning Latent Representations for Speech Generation and Transformation
Authors	Wei-Ning Hsu, Yu Zhang, James Glass
Abstract	An ability to model a generative process and learn a latent representation for speech in an unsupervised fashion will be crucial to process vast quantities of unlabelled speech data. Recently, deep probabilistic generative models such as Variational Autoencoders (VAEs) have achieved tremendous success in modeling natural images. In this paper, we apply a convolutional VAE to model the generative process of natural speech. We derive latent space arithmetic operations to disentangle learned latent representations. We demonstrate the capability of our model to modify the phonetic content or the speaker identity for speech segments using the derived operations, without the need for parallel supervisory data.
Tasks
Published	2017-04-13
URL	http://arxiv.org/abs/1704.04222v2
PDF	http://arxiv.org/pdf/1704.04222v2.pdf
PWC	https://paperswithcode.com/paper/learning-latent-representations-for-speech
Repo
Framework

Towards Proof Synthesis Guided by Neural Machine Translation for Intuitionistic Propositional Logic


Title	Towards Proof Synthesis Guided by Neural Machine Translation for Intuitionistic Propositional Logic
Authors	Taro Sekiyama, Akifumi Imanishi, Kohei Suenaga
Abstract	Inspired by the recent evolution of deep neural networks (DNNs) in machine learning, we explore their application to PL-related topics. This paper is the first step towards this goal; we propose a proof-synthesis method for the negation-free propositional logic in which we use a DNN to obtain a guide of proof search. The idea is to view the proof-synthesis problem as a translation from a proposition to its proof. We train seq2seq, which is a popular network in neural machine translation, so that it generates a proof encoded as a $\lambda$-term of a given proposition. We implement the whole framework and empirically observe that a generated proof term is close to a correct proof in terms of the tree edit distance of AST. This observation justifies using the output from a trained seq2seq model as a guide for proof search.
Tasks	Machine Translation
Published	2017-06-20
URL	http://arxiv.org/abs/1706.06462v1
PDF	http://arxiv.org/pdf/1706.06462v1.pdf
PWC	https://paperswithcode.com/paper/towards-proof-synthesis-guided-by-neural
Repo
Framework

A convolutional autoencoder approach for mining features in cellular electron cryo-tomograms and weakly supervised coarse segmentation


Title	A convolutional autoencoder approach for mining features in cellular electron cryo-tomograms and weakly supervised coarse segmentation
Authors	Xiangrui Zeng, Miguel Ricardo Leung, Tzviya Zeev-Ben-Mordehai, Min Xu
Abstract	Cellular electron cryo-tomography enables the 3D visualization of cellular organization in the near-native state and at submolecular resolution. However, the contents of cellular tomograms are often complex, making it difficult to automatically isolate different in situ cellular components. In this paper, we propose a convolutional autoencoder-based unsupervised approach to provide a coarse grouping of 3D small subvolumes extracted from tomograms. We demonstrate that the autoencoder can be used for efficient and coarse characterization of features of macromolecular complexes and surfaces, such as membranes. In addition, the autoencoder can be used to detect non-cellular features related to sample preparation and data collection, such as carbon edges from the grid and tomogram boundaries. The autoencoder is also able to detect patterns that may indicate spatial interactions between cellular components. Furthermore, we demonstrate that our autoencoder can be used for weakly supervised semantic segmentation of cellular components, requiring a very small amount of manual annotation.
Tasks	Semantic Segmentation, Weakly-Supervised Semantic Segmentation
Published	2017-06-15
URL	http://arxiv.org/abs/1706.04970v2
PDF	http://arxiv.org/pdf/1706.04970v2.pdf
PWC	https://paperswithcode.com/paper/a-convolutional-autoencoder-approach-for
Repo
Framework

Weakly Supervised Semantic Segmentation Based on Web Image Co-segmentation


Title	Weakly Supervised Semantic Segmentation Based on Web Image Co-segmentation
Authors	Tong Shen, Guosheng Lin, Lingqiao Liu, Chunhua Shen, Ian Reid
Abstract	Training a Fully Convolutional Network (FCN) for semantic segmentation requires a large number of masks with pixel level labelling, which involves a large amount of human labour and time for annotation. In contrast, web images and their image-level labels are much easier and cheaper to obtain. In this work, we propose a novel method for weakly supervised semantic segmentation with only image-level labels. The method utilizes the internet to retrieve a large number of images and uses a large scale co-segmentation framework to generate masks for the retrieved images. We first retrieve images from search engines, e.g. Flickr and Google, using semantic class names as queries, e.g. class names in the dataset PASCAL VOC 2012. We then use high quality masks produced by co-segmentation on the retrieved images as well as the target dataset images with image level labels to train segmentation networks. We obtain an IoU score of 56.9 on test set of PASCAL VOC 2012, which reaches the state-of-the-art performance.
Tasks	Semantic Segmentation, Weakly-Supervised Semantic Segmentation
Published	2017-05-25
URL	http://arxiv.org/abs/1705.09052v3
PDF	http://arxiv.org/pdf/1705.09052v3.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-semantic-segmentation-based
Repo
Framework

Dynamic Stripes: Exploiting the Dynamic Precision Requirements of Activation Values in Neural Networks


Title	Dynamic Stripes: Exploiting the Dynamic Precision Requirements of Activation Values in Neural Networks
Authors	Alberto Delmas, Patrick Judd, Sayeh Sharify, Andreas Moshovos
Abstract	Stripes is a Deep Neural Network (DNN) accelerator that uses bit-serial computation to offer performance that is proportional to the fixed-point precision of the activation values. The fixed-point precisions are determined a priori using profiling and are selected at a per layer granularity. This paper presents Dynamic Stripes, an extension to Stripes that detects precision variance at runtime and at a finer granularity. This extra level of precision reduction increases performance by 41% over Stripes.
Tasks
Published	2017-06-01
URL	http://arxiv.org/abs/1706.00504v1
PDF	http://arxiv.org/pdf/1706.00504v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-stripes-exploiting-the-dynamic
Repo
Framework

Learning and Refining of Privileged Information-based RNNs for Action Recognition from Depth Sequences


Title	Learning and Refining of Privileged Information-based RNNs for Action Recognition from Depth Sequences
Authors	Zhiyuan Shi, Tae-Kyun Kim
Abstract	Existing RNN-based approaches for action recognition from depth sequences require either skeleton joints or hand-crafted depth features as inputs. An end-to-end manner, mapping from raw depth maps to action classes, is non-trivial to design due to the fact that: 1) single channel map lacks texture thus weakens the discriminative power; 2) relatively small set of depth training data. To address these challenges, we propose to learn an RNN driven by privileged information (PI) in three-steps: An encoder is pre-trained to learn a joint embedding of depth appearance and PI (i.e. skeleton joints). The learned embedding layers are then tuned in the learning step, aiming to optimize the network by exploiting PI in a form of multi-task loss. However, exploiting PI as a secondary task provides little help to improve the performance of a primary task (i.e. classification) due to the gap between them. Finally, a bridging matrix is defined to connect two tasks by discovering latent PI in the refining step. Our PI-based classification loss maintains a consistency between latent PI and predicted distribution. The latent PI and network are iteratively estimated and updated in an expectation-maximization procedure. The proposed learning process provides greater discriminative power to model subtle depth difference, while helping avoid overfitting the scarcer training data. Our experiments show significant performance gains over state-of-the-art methods on three public benchmark datasets and our newly collected Blanket dataset.
Tasks	Temporal Action Localization
Published	2017-03-28
URL	http://arxiv.org/abs/1703.09625v4
PDF	http://arxiv.org/pdf/1703.09625v4.pdf
PWC	https://paperswithcode.com/paper/learning-and-refining-of-privileged
Repo
Framework

Generative Models for Learning from Crowds


Title	Generative Models for Learning from Crowds
Authors	Chi Hong
Abstract	In this paper, we propose generative probabilistic models for label aggregation. We use Gibbs sampling and a novel variational inference algorithm to perform the posterior inference. Empirical results show that our methods consistently outperform state-of-the-art methods.
Tasks
Published	2017-06-13
URL	http://arxiv.org/abs/1706.03930v3
PDF	http://arxiv.org/pdf/1706.03930v3.pdf
PWC	https://paperswithcode.com/paper/generative-models-for-learning-from-crowds
Repo
Framework

Combining Lexical and Syntactic Features for Detecting Content-dense Texts in News


Title	Combining Lexical and Syntactic Features for Detecting Content-dense Texts in News
Authors	Yinfei Yang, Ani Nenkova
Abstract	Content-dense news report important factual information about an event in direct, succinct manner. Information seeking applications such as information extraction, question answering and summarization normally assume all text they deal with is content-dense. Here we empirically test this assumption on news articles from the business, U.S. international relations, sports and science journalism domains. Our findings clearly indicate that about half of the news texts in our study are in fact not content-dense and motivate the development of a supervised content-density detector. We heuristically label a large training corpus for the task and train a two-layer classifying model based on lexical and unlexicalized syntactic features. On manually annotated data, we compare the performance of domain-specific classifiers, trained on data only from a given news domain and a general classifier in which data from all four domains is pooled together. Our annotation and prediction experiments demonstrate that the concept of content density varies depending on the domain and that naive annotators provide judgement biased toward the stereotypical domain label. Domain-specific classifiers are more accurate for domains in which content-dense texts are typically fewer. Domain independent classifiers reproduce better naive crowdsourced judgements. Classification prediction is high across all conditions, around 80%.
Tasks	Question Answering
Published	2017-04-03
URL	http://arxiv.org/abs/1704.00440v1
PDF	http://arxiv.org/pdf/1704.00440v1.pdf
PWC	https://paperswithcode.com/paper/combining-lexical-and-syntactic-features-for
Repo
Framework

Robust PCA by Manifold Optimization


Title	Robust PCA by Manifold Optimization
Authors	Teng Zhang, Yi Yang
Abstract	Robust PCA is a widely used statistical procedure to recover a underlying low-rank matrix with grossly corrupted observations. This work considers the problem of robust PCA as a nonconvex optimization problem on the manifold of low-rank matrices, and proposes two algorithms (for two versions of retractions) based on manifold optimization. It is shown that, with a proper designed initialization, the proposed algorithms are guaranteed to converge to the underlying low-rank matrix linearly. Compared with a previous work based on the Burer-Monterio decomposition of low-rank matrices, the proposed algorithms reduce the dependence on the conditional number of the underlying low-rank matrix theoretically. Simulations and real data examples confirm the competitive performance of our method.
Tasks
Published	2017-08-01
URL	http://arxiv.org/abs/1708.00257v3
PDF	http://arxiv.org/pdf/1708.00257v3.pdf
PWC	https://paperswithcode.com/paper/robust-pca-by-manifold-optimization
Repo
Framework

A novel model-based heuristic for energy optimal motion planning for automated driving


Title	A novel model-based heuristic for energy optimal motion planning for automated driving
Authors	Zlatan Ajanovic, Michael Stolz, Martin Horn
Abstract	Predictive motion planning is the key to achieve energy-efficient driving, which is one of the main benefits of automated driving. Researchers have been studying the planning of velocity trajectories, a simpler form of motion planning, for over a decade now and many different methods are available. Dynamic programming has shown to be the most common choice due to its numerical background and ability to include nonlinear constraints and models. Although planning of an optimal trajectory is done in a systematic way, dynamic programming does not use any knowledge about the considered problem to guide the exploration and therefore explores all possible trajectories. A* is a search algorithm which enables using knowledge about the problem to guide the exploration to the most promising solutions first. Knowledge has to be represented in a form of a heuristic function, which gives an optimistic estimate of cost for transitioning to the final state, which is not a straightforward task. This paper presents a novel heuristics incorporating air drag and auxiliary power as well as operational costs of the vehicle, besides kinetic and potential energy and rolling resistance known in the literature. Furthermore, optimal cruising velocity, which depends on vehicle aerodynamic properties and auxiliary power, is derived. Results are compared for different variants of heuristic functions and dynamic programming as well.
Tasks	Motion Planning, Optimal Motion Planning
Published	2017-12-11
URL	http://arxiv.org/abs/1712.03719v2
PDF	http://arxiv.org/pdf/1712.03719v2.pdf
PWC	https://paperswithcode.com/paper/a-novel-model-based-heuristic-for-energy
Repo
Framework

Greater data science at baccalaureate institutions


Title	Greater data science at baccalaureate institutions
Authors	Amelia McNamara, Nicholas J. Horton, Benjamin S. Baumer
Abstract	Donoho’s JCGS (in press) paper is a spirited call to action for statisticians, who he points out are losing ground in the field of data science by refusing to accept that data science is its own domain. (Or, at least, a domain that is becoming distinctly defined.) He calls on writings by John Tukey, Bill Cleveland, and Leo Breiman, among others, to remind us that statisticians have been dealing with data science for years, and encourages acceptance of the direction of the field while also ensuring that statistics is tightly integrated. As faculty at baccalaureate institutions (where the growth of undergraduate statistics programs has been dramatic), we are keen to ensure statistics has a place in data science and data science education. In his paper, Donoho is primarily focused on graduate education. At our undergraduate institutions, we are considering many of the same questions.
Tasks
Published	2017-10-24
URL	http://arxiv.org/abs/1710.08728v1
PDF	http://arxiv.org/pdf/1710.08728v1.pdf
PWC	https://paperswithcode.com/paper/greater-data-science-at-baccalaureate
Repo
Framework

Role of Morphology Injection in Statistical Machine Translation


Title	Role of Morphology Injection in Statistical Machine Translation
Authors	Sreelekha S, Pushpak Bhattacharyya
Abstract	Phrase-based Statistical models are more commonly used as they perform optimally in terms of both, translation quality and complexity of the system. Hindi and in general all Indian languages are morphologically richer than English. Hence, even though Phrase-based systems perform very well for the less divergent language pairs, for English to Indian language translation, we need more linguistic information (such as morphology, parse tree, parts of speech tags, etc.) on the source side. Factored models seem to be useful in this case, as Factored models consider word as a vector of factors. These factors can contain any information about the surface word and use it while translating. Hence, the objective of this work is to handle morphological inflections in Hindi and Marathi using Factored translation models while translating from English. SMT approaches face the problem of data sparsity while translating into a morphologically rich language. It is very unlikely for a parallel corpus to contain all morphological forms of words. We propose a solution to generate these unseen morphological forms and inject them into original training corpora. In this paper, we study factored models and the problem of sparseness in context of translation to morphologically rich languages. We propose a simple and effective solution which is based on enriching the input with various morphological forms of words. We observe that morphology injection improves the quality of translation in terms of both adequacy and fluency. We verify this with the experiments on two morphologically rich languages: Hindi and Marathi, while translating from English.
Tasks	Machine Translation
Published	2017-09-16
URL	http://arxiv.org/abs/1709.05487v1
PDF	http://arxiv.org/pdf/1709.05487v1.pdf
PWC	https://paperswithcode.com/paper/role-of-morphology-injection-in-statistical
Repo
Framework

Idea density for predicting Alzheimer’s disease from transcribed speech


Title	Idea density for predicting Alzheimer’s disease from transcribed speech
Authors	Kairit Sirts, Olivier Piguet, Mark Johnson
Abstract	Idea Density (ID) measures the rate at which ideas or elementary predications are expressed in an utterance or in a text. Lower ID is found to be associated with an increased risk of developing Alzheimer’s disease (AD) (Snowdon et al., 1996; Engelman et al., 2010). ID has been used in two different versions: propositional idea density (PID) counts the expressed ideas and can be applied to any text while semantic idea density (SID) counts pre-defined information content units and is naturally more applicable to normative domains, such as picture description tasks. In this paper, we develop DEPID, a novel dependency-based method for computing PID, and its version DEPID-R that enables to exclude repeating ideas—a feature characteristic to AD speech. We conduct the first comparison of automatically extracted PID and SID in the diagnostic classification task on two different AD datasets covering both closed-topic and free-recall domains. While SID performs better on the normative dataset, adding PID leads to a small but significant improvement (+1.7 F-score). On the free-topic dataset, PID performs better than SID as expected (77.6 vs 72.3 in F-score) but adding the features derived from the word embedding clustering underlying the automatic SID increases the results considerably, leading to an F-score of 84.8.
Tasks
Published	2017-06-14
URL	http://arxiv.org/abs/1706.04473v1
PDF	http://arxiv.org/pdf/1706.04473v1.pdf
PWC	https://paperswithcode.com/paper/idea-density-for-predicting-alzheimers
Repo
Framework

Exact Learning from an Honest Teacher That Answers Membership Queries


Title	Exact Learning from an Honest Teacher That Answers Membership Queries
Authors	Nader H. Bshouty
Abstract	Given a teacher that holds a function $f:X\to R$ from some class of functions $C$. The teacher can receive from the learner an element~$d$ in the domain $X$ (a query) and returns the value of the function in $d$, $f(d)\in R$. The learner goal is to find $f$ with a minimum number of queries, optimal time complexity, and optimal resources. In this survey, we present some of the results known from the literature, different techniques used, some new problems, and open problems.
Tasks
Published	2017-06-13
URL	http://arxiv.org/abs/1706.03935v1
PDF	http://arxiv.org/pdf/1706.03935v1.pdf
PWC	https://paperswithcode.com/paper/exact-learning-from-an-honest-teacher-that
Repo
Framework