Paper Group NANR 150
Learning Determinantal Point Processes with Moments and Cycles. InToEventS: An Interactive Toolkit for Discovering and Building Event Schemas. Analytical Guarantees on Numerical Precision of Deep Neural Networks. Enhancing Machine Translation of Academic Course Catalogues with Terminological Resources. Nonnegative Matrix Factorization for Time Seri …
Learning Determinantal Point Processes with Moments and Cycles
| Title | Learning Determinantal Point Processes with Moments and Cycles |
| Authors | John Urschel, Victor-Emmanuel Brunel, Ankur Moitra, Philippe Rigollet |
| Abstract | Determinantal Point Processes (DPPs) are a family of probabilistic models that have a repulsive behavior, and lend themselves naturally to many tasks in machine learning where returning a diverse set of objects is important. While there are fast algorithms for sampling, marginalization and conditioning, much less is known about learning the parameters of a DPP. Our contribution is twofold: (i) we establish the optimal sample complexity achievable in this problem and show that it is governed by a natural parameter, which we call the cycle sparsity; (ii) we propose a provably fast combinatorial algorithm that implements the method of moments efficiently and achieves optimal sample complexity. Finally, we give experimental results that confirm our theoretical findings. |
| Tasks | Point Processes |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=721 |
| http://proceedings.mlr.press/v70/urschel17a/urschel17a.pdf | |
| PWC | https://paperswithcode.com/paper/learning-determinantal-point-processes-with |
| Repo | |
| Framework | |
InToEventS: An Interactive Toolkit for Discovering and Building Event Schemas
| Title | InToEventS: An Interactive Toolkit for Discovering and Building Event Schemas |
| Authors | Germ{'a}n Ferrero, Audi Primadhanty, Ariadna Quattoni |
| Abstract | Event Schema Induction is the task of learning a representation of events (e.g., bombing) and the roles involved in them (e.g, victim and perpetrator). This paper presents InToEventS, an interactive tool for learning these schemas. InToEventS allows users to explore a corpus and discover which kind of events are present. We show how users can create useful event schemas using two interactive clustering steps. |
| Tasks | Slot Filling |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-3026/ |
| https://www.aclweb.org/anthology/E17-3026 | |
| PWC | https://paperswithcode.com/paper/intoevents-an-interactive-toolkit-for |
| Repo | |
| Framework | |
Analytical Guarantees on Numerical Precision of Deep Neural Networks
| Title | Analytical Guarantees on Numerical Precision of Deep Neural Networks |
| Authors | Charbel Sakr, Yongjune Kim, Naresh Shanbhag |
| Abstract | The acclaimed successes of neural networks often overshadow their tremendous complexity. We focus on numerical precision – a key parameter defining the complexity of neural networks. First, we present theoretical bounds on the accuracy in presence of limited precision. Interestingly, these bounds can be computed via the back-propagation algorithm. Hence, by combining our theoretical analysis and the back-propagation algorithm, we are able to readily determine the minimum precision needed to preserve accuracy without having to resort to time-consuming fixed-point simulations. We provide numerical evidence showing how our approach allows us to maintain high accuracy but with lower complexity than state-of-the-art binary networks. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=743 |
| http://proceedings.mlr.press/v70/sakr17a/sakr17a.pdf | |
| PWC | https://paperswithcode.com/paper/analytical-guarantees-on-numerical-precision |
| Repo | |
| Framework | |
Enhancing Machine Translation of Academic Course Catalogues with Terminological Resources
| Title | Enhancing Machine Translation of Academic Course Catalogues with Terminological Resources |
| Authors | R Scansani, y, Silvia Bernardini, Adriano Ferraresi, Federico Gaspari, Marcello Soffritti |
| Abstract | This paper describes an approach to translating course unit descriptions from Italian and German into English, using a phrase-based machine translation (MT) system. The genre is very prominent among those requiring translation by universities in European countries in which English is a non-native language. For each language combination, an in-domain bilingual corpus including course unit and degree program descriptions is used to train an MT engine, whose output is then compared to a baseline engine trained on the Europarl corpus. In a subsequent experiment, a bilingual terminology database is added to the training sets in both engines and its impact on the output quality is evaluated based on BLEU and post-editing score. Results suggest that the use of domain-specific corpora boosts the engines quality for both language combinations, especially for German-English, whereas adding terminological resources does not seem to bring notable benefits. |
| Tasks | Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-7901/ |
| https://doi.org/10.26615/978-954-452-042-7_001 | |
| PWC | https://paperswithcode.com/paper/enhancing-machine-translation-of-academic |
| Repo | |
| Framework | |
Nonnegative Matrix Factorization for Time Series Recovery From a Few Temporal Aggregates
| Title | Nonnegative Matrix Factorization for Time Series Recovery From a Few Temporal Aggregates |
| Authors | Jiali Mei, Yohann De Castro, Yannig Goude, Georges Hébrail |
| Abstract | Motivated by electricity consumption reconstitution, we propose a new matrix recovery method using nonnegative matrix factorization (NMF). The task tackled here is to reconstitute electricity consumption time series at a fine temporal scale from measures that are temporal aggregates of individual consumption. Contrary to existing NMF algorithms, the proposed method uses temporal aggregates as input data, instead of matrix entries. Furthermore, the proposed method is extended to take into account individual autocorrelation to provide better estimation, using a recent convex relaxation of quadratically constrained quadratic programs. Extensive experiments on synthetic and real-world electricity consumption datasets illustrate the effectiveness of the proposed method. |
| Tasks | Time Series |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=522 |
| http://proceedings.mlr.press/v70/mei17a/mei17a.pdf | |
| PWC | https://paperswithcode.com/paper/nonnegative-matrix-factorization-for-time |
| Repo | |
| Framework | |
Connected Subgraph Detection with Mirror Descent on SDPs
| Title | Connected Subgraph Detection with Mirror Descent on SDPs |
| Authors | Cem Aksoylar, Lorenzo Orecchia, Venkatesh Saligrama |
| Abstract | We propose a novel, computationally efficient mirror-descent based optimization framework for subgraph detection in graph-structured data. Our aim is to discover anomalous patterns present in a connected subgraph of a given graph. This problem arises in many applications such as detection of network intrusions, community detection, detection of anomalous events in surveillance videos or disease outbreaks. Since optimization over connected subgraphs is a combinatorial and computationally difficult problem, we propose a convex relaxation that offers a principled approach to incorporating connectivity and conductance constraints on candidate subgraphs. We develop a novel efficient algorithm to solve the relaxed problem, establish convergence guarantees and demonstrate its feasibility and performance with experiments on real and very large simulated networks. |
| Tasks | Community Detection |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=873 |
| http://proceedings.mlr.press/v70/aksoylar17a/aksoylar17a.pdf | |
| PWC | https://paperswithcode.com/paper/connected-subgraph-detection-with-mirror |
| Repo | |
| Framework | |
Same same, but different: Compositionality of paraphrase granularity levels
| Title | Same same, but different: Compositionality of paraphrase granularity levels |
| Authors | Darina Benikova, Torsten Zesch |
| Abstract | Paraphrases exist on different granularity levels, the most frequently used one being the sentential level. However, we argue that working on the sentential level is not optimal for both machines and humans, and that it would be easier and more efficient to work on sub-sentential levels. To prove this, we quantify and analyze the difference between paraphrases on both sentence and sub-sentence level in order to show the significance of the problem. First results on a preliminary dataset seem to confirm our hypotheses. |
| Tasks | Machine Translation, Question Answering, Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1014/ |
| https://doi.org/10.26615/978-954-452-049-6_014 | |
| PWC | https://paperswithcode.com/paper/same-same-but-different-compositionality-of |
| Repo | |
| Framework | |
RUFINO at SemEval-2017 Task 2: Cross-lingual lexical similarity by extending PMI and word embeddings systems with a Swadesh’s-like list
| Title | RUFINO at SemEval-2017 Task 2: Cross-lingual lexical similarity by extending PMI and word embeddings systems with a Swadesh’s-like list |
| Authors | Sergio Jimenez, George Due{~n}as, Lorena Gaitan, Jorge Segura |
| Abstract | The RUFINO team proposed a non-supervised, conceptually-simple and low-cost approach for addressing the Multilingual and Cross-lingual Semantic Word Similarity challenge at SemEval 2017. The proposed systems were cross-lingual extensions of popular monolingual lexical similarity approaches such as PMI and word2vec. The extensions were possible by means of a small parallel list of concepts similar to the Swadesh{'}s list, which we obtained in a semi-automatic way. In spite of its simplicity, our approach showed to be effective obtaining statistically-significant and consistent results in all datasets proposed for the task. Besides, we provide some research directions for improving this novel and affordable approach. |
| Tasks | Semantic Textual Similarity, Word Embeddings, Word Sense Disambiguation |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2037/ |
| https://www.aclweb.org/anthology/S17-2037 | |
| PWC | https://paperswithcode.com/paper/rufino-at-semeval-2017-task-2-cross-lingual |
| Repo | |
| Framework | |
N-Hance at SemEval-2017 Task 7: A Computational Approach using Word Association for Puns
| Title | N-Hance at SemEval-2017 Task 7: A Computational Approach using Word Association for Puns |
| Authors | {"O}zge Sevgili, Nima Ghotbi, Selma Tekir |
| Abstract | This paper presents a system developed for SemEval-2017 Task 7, Detection and Interpretation of English Puns consisting of three subtasks; pun detection, pun location, and pun interpretation, respectively. The system stands on recognizing a distinctive word which has a high association with the pun in the given sentence. The intended humorous meaning of pun is identified through the use of this word. Our official results confirm the potential of this approach. |
| Tasks | Word Sense Disambiguation |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2074/ |
| https://www.aclweb.org/anthology/S17-2074 | |
| PWC | https://paperswithcode.com/paper/n-hance-at-semeval-2017-task-7-a |
| Repo | |
| Framework | |
Visual Vibrometry: Estimating Material Properties from Small Motions in Video
| Title | Visual Vibrometry: Estimating Material Properties from Small Motions in Video |
| Authors | Abe Davis, Katherine L. Bouman, Justin G. Chen, Michael Rubinstein, Oral Buyukozturk, Fredo Durand, William T. Freeman |
| Abstract | The estimation of material properties is important for scene understanding, with many applications in vision, robotics, and structural engineering. This paper connects fundamentals of vibration mechanics with computer vision techniques in order to infer material properties from small, often imperceptible motion in video. Objects tend to vibrate in a set of preferred modes. The shapes and frequencies ofthese modes depend on the structure and material properties of an object. Focusing on the case where geometry is known or fixed, we show how information about an object’s modes of vibration can be extracted from video and used to make inferences about that object’s material properties. We demonstrate our approach by estimating material properties for a variety of rods and fabrics by passively observing their motion in high-speed and regular frame rate video |
| Tasks | Scene Understanding |
| Published | 2017-04-15 |
| URL | https://ieeexplore.ieee.org/document/7728146 |
| http://visualvibrometry.com/publications/Davis_2015_CVPR.pdf | |
| PWC | https://paperswithcode.com/paper/visual-vibrometry-estimating-material-1 |
| Repo | |
| Framework | |
Prox-PDA: The Proximal Primal-Dual Algorithm for Fast Distributed Nonconvex Optimization and Learning Over Networks
| Title | Prox-PDA: The Proximal Primal-Dual Algorithm for Fast Distributed Nonconvex Optimization and Learning Over Networks |
| Authors | Mingyi Hong, Davood Hajinezhad, Ming-Min Zhao |
| Abstract | In this paper we consider nonconvex optimization and learning over a network of distributed nodes. We develop a Proximal Primal-Dual Algorithm (Prox-PDA), which enables the network nodes to distributedly and collectively compute the set of first-order stationary solutions in a global sublinear manner [with a rate of $O(1/r)$, where $r$ is the iteration counter]. To the best of our knowledge, this is the first algorithm that enables distributed nonconvex optimization with global rate guarantees. Our numerical experiments also demonstrate the effectiveness of the proposed algorithm. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=749 |
| http://proceedings.mlr.press/v70/hong17a/hong17a.pdf | |
| PWC | https://paperswithcode.com/paper/prox-pda-the-proximal-primal-dual-algorithm |
| Repo | |
| Framework | |
UWAV at SemEval-2017 Task 7: Automated feature-based system for locating puns
| Title | UWAV at SemEval-2017 Task 7: Automated feature-based system for locating puns |
| Authors | Ankit Vadehra |
| Abstract | In this paper we describe our system created for SemEval-2017 Task 7: Detection and Interpretation of English Puns. We tackle subtask 1, pun detection, by leveraging features selected from sentences to design a classifier that can disambiguate between the presence or absence of a pun. We address subtask 2, pun location, by utilizing a decision flow structure that uses presence or absence of certain features to decide the next action. The results obtained by our system are encouraging, considering the simplicity of the system. We consider this system as a precursor for deeper exploration on efficient feature selection for pun detection. |
| Tasks | Feature Selection, Language Modelling, Machine Translation, Sentiment Analysis, Word Sense Disambiguation |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2077/ |
| https://www.aclweb.org/anthology/S17-2077 | |
| PWC | https://paperswithcode.com/paper/uwav-at-semeval-2017-task-7-automated-feature |
| Repo | |
| Framework | |
Faster and Non-ergodic O(1/K) Stochastic Alternating Direction Method of Multipliers
| Title | Faster and Non-ergodic O(1/K) Stochastic Alternating Direction Method of Multipliers |
| Authors | Cong Fang, Feng Cheng, Zhouchen Lin |
| Abstract | We study stochastic convex optimization subjected to linear equality constraints. Traditional Stochastic Alternating Direction Method of Multipliers and its Nesterov’s acceleration scheme can only achieve ergodic O(1/\sqrt{K}) convergence rates, where K is the number of iteration. By introducing Variance Reduction (VR) techniques, the convergence rates improve to ergodic O(1/K). In this paper, we propose a new stochastic ADMM which elaborately integrates Nesterov’s extrapolation and VR techniques. With Nesterov’s extrapolation, our algorithm can achieve a non-ergodic O(1/K) convergence rate which is optimal for separable linearly constrained non-smooth convex problems, while the convergence rates of VR based ADMM methods are actually tight O(1/\sqrt{K}) in non-ergodic sense. To the best of our knowledge, this is the first work that achieves a truly accelerated, stochastic convergence rate for constrained convex problems. The experimental results demonstrate that our algorithm is significantly faster than the existing state-of-the-art stochastic ADMM methods. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7034-faster-and-non-ergodic-o1k-stochastic-alternating-direction-method-of-multipliers |
| http://papers.nips.cc/paper/7034-faster-and-non-ergodic-o1k-stochastic-alternating-direction-method-of-multipliers.pdf | |
| PWC | https://paperswithcode.com/paper/faster-and-non-ergodic-o1k-stochastic |
| Repo | |
| Framework | |
Proceedings of the 3rd Workshop on Noisy User-generated Text
| Title | Proceedings of the 3rd Workshop on Noisy User-generated Text |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4400/ |
| https://www.aclweb.org/anthology/W17-4400 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-3rd-workshop-on-noisy-user |
| Repo | |
| Framework | |
Re-revisiting Learning on Hypergraphs: Confidence Interval and Subgradient Method
| Title | Re-revisiting Learning on Hypergraphs: Confidence Interval and Subgradient Method |
| Authors | Chenzi Zhang, Shuguang Hu, Zhihao Gavin Tang, T-H. Hubert Chan |
| Abstract | We revisit semi-supervised learning on hypergraphs. Same as previous approaches, our method uses a convex program whose objective function is not everywhere differentiable. We exploit the non-uniqueness of the optimal solutions, and consider confidence intervals which give the exact ranges that unlabeled vertices take in any optimal solution. Moreover, we give a much simpler approach for solving the convex program based on the subgradient method. Our experiments on real-world datasets confirm that our confidence interval approach on hypergraphs outperforms existing methods, and our sub-gradient method gives faster running times when the number of vertices is much larger than the number of edges. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=517 |
| http://proceedings.mlr.press/v70/zhang17d/zhang17d.pdf | |
| PWC | https://paperswithcode.com/paper/re-revisiting-learning-on-hypergraphs |
| Repo | |
| Framework | |
