Paper Group NANR 260
SPADE: Evaluation Dataset for Monolingual Phrase Alignment. Sound Abstraction and Decomposition of Probabilistic Programs. PAC-Bayes Tree: weighted subtrees with guarantees. MIsA: Multilingual ``IsA’’ Extraction from Corpora. Revealing Common Statistical Behaviors in Heterogeneous Populations. Normalized Blind Deconvolution. What you can cram into …
SPADE: Evaluation Dataset for Monolingual Phrase Alignment
| Title | SPADE: Evaluation Dataset for Monolingual Phrase Alignment |
| Authors | Yuki Arase, Junichi Tsujii |
| Abstract | |
| Tasks | Machine Translation, Paraphrase Identification, Question Answering, Semantic Parsing, Sentence Embeddings |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1220/ |
| https://www.aclweb.org/anthology/L18-1220 | |
| PWC | https://paperswithcode.com/paper/spade-evaluation-dataset-for-monolingual |
| Repo | |
| Framework | |
Sound Abstraction and Decomposition of Probabilistic Programs
| Title | Sound Abstraction and Decomposition of Probabilistic Programs |
| Authors | Steven Holtzen, Guy Broeck, Todd Millstein |
| Abstract | Probabilistic programming languages are a flexible tool for specifying statistical models, but this flexibility comes at the cost of efficient analysis. It is currently difficult to compactly represent the subtle independence properties of a probabilistic program, and exploit independence properties to decompose inference. Classical graphical model abstractions do capture some properties of the underlying distribution, enabling inference algorithms to operate at the level of the graph topology. However, we observe that graph-based abstractions are often too coarse to capture interesting properties of programs. We propose a form of sound abstraction for probabilistic programs wherein the abstractions are themselves simplified programs. We provide a theoretical foundation for these abstractions, as well as an algorithm to generate them. Experimentally, we also illustrate the practical benefits of our framework as a tool to decompose probabilistic program inference. |
| Tasks | Probabilistic Programming |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2418 |
| http://proceedings.mlr.press/v80/holtzen18a/holtzen18a.pdf | |
| PWC | https://paperswithcode.com/paper/sound-abstraction-and-decomposition-of |
| Repo | |
| Framework | |
PAC-Bayes Tree: weighted subtrees with guarantees
| Title | PAC-Bayes Tree: weighted subtrees with guarantees |
| Authors | Tin D. Nguyen, Samory Kpotufe |
| Abstract | We present a weighted-majority classification approach over subtrees of a fixed tree, which provably achieves excess-risk of the same order as the best tree-pruning. Furthermore, the computational efficiency of pruning is maintained at both training and testing time despite having to aggregate over an exponential number of subtrees. We believe this is the first subtree aggregation approach with such guarantees. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8158-pac-bayes-tree-weighted-subtrees-with-guarantees |
| http://papers.nips.cc/paper/8158-pac-bayes-tree-weighted-subtrees-with-guarantees.pdf | |
| PWC | https://paperswithcode.com/paper/pac-bayes-tree-weighted-subtrees-with |
| Repo | |
| Framework | |
MIsA: Multilingual ``IsA’’ Extraction from Corpora
| Title | MIsA: Multilingual ``IsA’’ Extraction from Corpora | |
| Authors | Stefano Faralli, Els Lefever, Simone Paolo Ponzetto |
| Abstract | |
| Tasks | Relation Extraction, Word Sense Disambiguation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1321/ |
| https://www.aclweb.org/anthology/L18-1321 | |
| PWC | https://paperswithcode.com/paper/misa-multilingual-isa-extraction-from-corpora |
| Repo | |
| Framework | |
Revealing Common Statistical Behaviors in Heterogeneous Populations
| Title | Revealing Common Statistical Behaviors in Heterogeneous Populations |
| Authors | Andrey Zhitnikov, Rotem Mulayoff, Tomer Michaeli |
| Abstract | In many areas of neuroscience and biological data analysis, it is desired to reveal common patterns among a group of subjects. Such analyses play important roles e.g., in detecting functional brain networks from fMRI scans and in identifying brain regions which show increased activity in response to certain stimuli. Group level techniques usually assume that all subjects in the group behave according to a single statistical model, or that deviations from the common model have simple parametric forms. Therefore, complex subject-specific deviations from the common model severely impair the performance of such methods. In this paper, we propose nonparametric algorithms for estimating the common covariance matrix and the common density function of several variables in a heterogeneous group of subjects. Our estimates converge to the true model as the number of subjects tends to infinity, under very mild conditions. We illustrate the effectiveness of our methods through extensive simulations as well as on real-data from fMRI scans and from arterial blood pressure and photoplethysmogram measurements. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2019 |
| http://proceedings.mlr.press/v80/zhitnikov18a/zhitnikov18a.pdf | |
| PWC | https://paperswithcode.com/paper/revealing-common-statistical-behaviors-in |
| Repo | |
| Framework | |
Normalized Blind Deconvolution
| Title | Normalized Blind Deconvolution |
| Authors | Meiguang Jin, Stefan Roth, Paolo Favaro |
| Abstract | We introduce a family of novel approaches to single-image blind deconvolution, ie , the problem of recovering a sharp image and a blur kernel from a single blurry input. This problem is highly ill-posed, because infinite (image, blur) pairs produce the same blurry image. Most research effort has been devoted to the design of priors for natural images and blur kernels, which can drastically prune the set of possible solutions. Unfortunately, these priors are usually not sufficient to favor the sharp solution. In this paper we address this issue by looking at a much less studied aspect: the relative scale ambiguity between the sharp image and the blur. Most prior work eliminates this ambiguity by fixing the $L^1$ norm of the blur kernel. In principle, however, this choice is arbitrary. We show that a careful design of the blur normalization yields a blind deconvolution formulation with remarkable accuracy and robustness to noise. Specifically, we show that using the Frobenius norm to fix the scale ambiguity enables convex image priors, such as the total variation, to achieve state-of-the-art performance on both synthetic and real datasets. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Meiguang_Jin_Normalized_Blind_Deconvolution_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Meiguang_Jin_Normalized_Blind_Deconvolution_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/normalized-blind-deconvolution |
| Repo | |
| Framework | |
What you can cram into a single $&!#* vector: Probing sentence embeddings for linguistic properties
| Title | What you can cram into a single $&!#* vector: Probing sentence embeddings for linguistic properties |
| Authors | Alexis Conneau, German Kruszewski, Guillaume Lample, Lo{"\i}c Barrault, Marco Baroni |
| Abstract | Although much effort has recently been devoted to training high-quality sentence embeddings, we still have a poor understanding of what they are capturing. {``}Downstream{''} tasks, often based on sentence classification, are commonly used to evaluate the quality of sentence representations. The complexity of the tasks makes it however difficult to infer what kind of information is present in the representations. We introduce here 10 probing tasks designed to capture simple linguistic features of sentences, and we use them to study embeddings generated by three different encoders trained in eight distinct ways, uncovering intriguing properties of both encoders and training methods. | |
| Tasks | Machine Translation, Sentence Classification, Sentence Embedding, Sentence Embeddings |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1198/ |
| https://www.aclweb.org/anthology/P18-1198 | |
| PWC | https://paperswithcode.com/paper/what-you-can-cram-into-a-single-vector-1 |
| Repo | |
| Framework | |
Biomedical Document Retrieval for Clinical Decision Support System
| Title | Biomedical Document Retrieval for Clinical Decision Support System |
| Authors | Jainisha Sankhavara |
| Abstract | The availability of huge amount of biomedical literature have opened up new possibilities to apply Information Retrieval and NLP for mining documents from them. In this work, we are focusing on biomedical document retrieval from literature for clinical decision support systems. We compare statistical and NLP based approaches of query reformulation for biomedical document retrieval. Also, we have modeled the biomedical document retrieval as a learning to rank problem. We report initial results for statistical and NLP based query reformulation approaches and learning to rank approach with future direction of research. |
| Tasks | Information Retrieval, Learning-To-Rank, Named Entity Recognition, Question Answering, Text Summarization |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-3012/ |
| https://www.aclweb.org/anthology/P18-3012 | |
| PWC | https://paperswithcode.com/paper/biomedical-document-retrieval-for-clinical |
| Repo | |
| Framework | |
An Iterative, Sketching-based Framework for Ridge Regression
| Title | An Iterative, Sketching-based Framework for Ridge Regression |
| Authors | Agniva Chowdhury, Jiasen Yang, Petros Drineas |
| Abstract | Ridge regression is a variant of regularized least squares regression that is particularly suitable in settings where the number of predictor variables greatly exceeds the number of observations. We present a simple, iterative, sketching-based algorithm for ridge regression that guarantees high-quality approximations to the optimal solution vector. Our analysis builds upon two simple structural results that boil down to randomized matrix multiplication, a fundamental and well-understood primitive of randomized linear algebra. An important contribution of our work is the analysis of the behavior of subsampled ridge regression problems when the ridge leverage scores are used: we prove that accurate approximations can be achieved by a sample whose size depends on the degrees of freedom of the ridge-regression problem rather than the dimensions of the design matrix. Our experimental evaluations verify our theoretical results on both real and synthetic data. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=1895 |
| http://proceedings.mlr.press/v80/chowdhury18a/chowdhury18a.pdf | |
| PWC | https://paperswithcode.com/paper/an-iterative-sketching-based-framework-for |
| Repo | |
| Framework | |
Video Person Re-Identification With Competitive Snippet-Similarity Aggregation and Co-Attentive Snippet Embedding
| Title | Video Person Re-Identification With Competitive Snippet-Similarity Aggregation and Co-Attentive Snippet Embedding |
| Authors | Dapeng Chen, Hongsheng Li, Tong Xiao, Shuai Yi, Xiaogang Wang |
| Abstract | In this paper, we address video-based person re-identification with competitive snippet-similarity aggregation and co-attentive snippet embedding. Our approach divides long person sequences into multiple short video snippets and aggregates the top-ranked snippet similarities for sequence-similarity estimation. With this strategy, the intra-person visual variation of each sample could be minimized for similarity estimation, while the diverse appearance and temporal information are maintained. The snippet similarities are estimated by a deep neural network with a novel temporal co-attention for snippet embedding. The attention weights are obtained based on a query feature, which is learned from the whole probe snippet by an LSTM network, making the resulting embeddings less affected by noisy frames. The gallery snippet shares the same query feature with the probe snippet. Thus the embedding of gallery snippet can present more relevant features to compare with the probe snippet, yielding more accurate snippet similarity. Extensive ablation studies verify the effectiveness of competitive snippet-similarity aggregation as well as the temporal co-attentive embedding. Our method significantly outperforms the current state-of-the-art approaches on multiple datasets. |
| Tasks | Person Re-Identification, Video-Based Person Re-Identification |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Chen_Video_Person_Re-Identification_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Chen_Video_Person_Re-Identification_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/video-person-re-identification-with |
| Repo | |
| Framework | |
Morphological Word Embeddings for Arabic Neural Machine Translation in Low-Resource Settings
| Title | Morphological Word Embeddings for Arabic Neural Machine Translation in Low-Resource Settings |
| Authors | Pamela Shapiro, Kevin Duh |
| Abstract | Neural machine translation has achieved impressive results in the last few years, but its success has been limited to settings with large amounts of parallel data. One way to improve NMT for lower-resource settings is to initialize a word-based NMT model with pretrained word embeddings. However, rare words still suffer from lower quality word embeddings when trained with standard word-level objectives. We introduce word embeddings that utilize morphological resources, and compare to purely unsupervised alternatives. We work with Arabic, a morphologically rich language with available linguistic resources, and perform Ar-to-En MT experiments on a small corpus of TED subtitles. We find that word embeddings utilizing subword information consistently outperform standard word embeddings on a word similarity task and as initialization of the source word embeddings in a low-resource NMT system. |
| Tasks | Machine Translation, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-1201/ |
| https://www.aclweb.org/anthology/W18-1201 | |
| PWC | https://paperswithcode.com/paper/morphological-word-embeddings-for-arabic |
| Repo | |
| Framework | |
Learning Low-Dimensional Temporal Representations
| Title | Learning Low-Dimensional Temporal Representations |
| Authors | Bing Su, Ying Wu |
| Abstract | Low-dimensional discriminative representations enhance machine learning methods in both performance and complexity, motivating supervised dimensionality reduction (DR) that transforms high-dimensional data to a discriminative subspace. Most DR methods require data to be i.i.d., however, in some domains, data naturally come in sequences, where the observations are temporally correlated. We propose a DR method called LT-LDA to learn low-dimensional temporal representations. We construct the separability among sequence classes by lifting the holistic temporal structures, which are established based on temporal alignments and may change in different subspaces. We jointly learn the subspace and the associated alignments by optimizing an objective which favors easily-separable temporal structures, and show that this objective is connected to the inference of alignments, thus allows an iterative solution. We provide both theoretical insight and empirical evaluation on real-world sequence datasets to show the interest of our method. |
| Tasks | Dimensionality Reduction |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=1910 |
| http://proceedings.mlr.press/v80/su18a/su18a.pdf | |
| PWC | https://paperswithcode.com/paper/learning-low-dimensional-temporal |
| Repo | |
| Framework | |
Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph
| Title | Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph |
| Authors | AmirAli Bagher Zadeh, Paul Pu Liang, Soujanya Poria, Erik Cambria, Louis-Philippe Morency |
| Abstract | Analyzing human multimodal language is an emerging area of research in NLP. Intrinsically this language is multimodal (heterogeneous), sequential and asynchronous; it consists of the language (words), visual (expressions) and acoustic (paralinguistic) modalities all in the form of asynchronous coordinated sequences. From a resource perspective, there is a genuine need for large scale datasets that allow for in-depth studies of this form of language. In this paper we introduce CMU Multimodal Opinion Sentiment and Emotion Intensity (CMU-MOSEI), the largest dataset of sentiment analysis and emotion recognition to date. Using data from CMU-MOSEI and a novel multimodal fusion technique called the Dynamic Fusion Graph (DFG), we conduct experimentation to exploit how modalities interact with each other in human multimodal language. Unlike previously proposed fusion techniques, DFG is highly interpretable and achieves competative performance when compared to the previous state of the art. |
| Tasks | Emotion Recognition, Language Modelling, Multimodal Sentiment Analysis, Multi-Task Learning, Sentiment Analysis |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1208/ |
| https://www.aclweb.org/anthology/P18-1208 | |
| PWC | https://paperswithcode.com/paper/multimodal-language-analysis-in-the-wild-cmu |
| Repo | |
| Framework | |
Lifted Weighted Mini-Bucket
| Title | Lifted Weighted Mini-Bucket |
| Authors | Nicholas Gallo, Alexander T. Ihler |
| Abstract | Many graphical models, such as Markov Logic Networks (MLNs) with evidence, possess highly symmetric substructures but no exact symmetries. Unfortunately, there are few principled methods that exploit these symmetric substructures to perform efficient approximate inference. In this paper, we present a lifted variant of the Weighted Mini-Bucket elimination algorithm which provides a principled way to (i) exploit the highly symmetric substructure of MLN models, and (ii) incorporate high-order inference terms which are necessary for high quality approximate inference. Our method has significant control over the accuracy-time trade-off of the approximation, allowing us to generate any-time approximations. Experimental results demonstrate the utility of this class of approximations, especially in models with strong repulsive potentials. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8234-lifted-weighted-mini-bucket |
| http://papers.nips.cc/paper/8234-lifted-weighted-mini-bucket.pdf | |
| PWC | https://paperswithcode.com/paper/lifted-weighted-mini-bucket |
| Repo | |
| Framework | |
Bounded-Loss Private Prediction Markets
| Title | Bounded-Loss Private Prediction Markets |
| Authors | Rafael Frongillo, Bo Waggoner |
| Abstract | Prior work has investigated variations of prediction markets that preserve participants’ (differential) privacy, which formed the basis of useful mechanisms for purchasing data for machine learning objectives. Such markets required potentially unlimited financial subsidy, however, making them impractical. In this work, we design an adaptively-growing prediction market with a bounded financial subsidy, while achieving privacy, incentives to produce accurate predictions, and precision in the sense that market prices are not heavily impacted by the added privacy-preserving noise. We briefly discuss how our mechanism can extend to the data-purchasing setting, and its relationship to traditional learning algorithms. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8244-bounded-loss-private-prediction-markets |
| http://papers.nips.cc/paper/8244-bounded-loss-private-prediction-markets.pdf | |
| PWC | https://paperswithcode.com/paper/bounded-loss-private-prediction-markets |
| Repo | |
| Framework | |
