Paper Group NANR 180
Structured Siamese Network for Real-Time Visual Tracking. Ontology-Based Retrieval & Neural Approaches for BioASQ Ideal Answer Generation. Toward Better Loanword Identification in Uyghur Using Cross-lingual Word Embeddings. The Lingering of Gradients: How to Reuse Gradients Over Time. A Computational Architecture for the Morphology of Upper Tanana …
Structured Siamese Network for Real-Time Visual Tracking
| Title | Structured Siamese Network for Real-Time Visual Tracking |
| Authors | Yunhua Zhang, Lijun Wang, Jinqing Qi, Dong Wang, Mengyang Feng, Huchuan Lu |
| Abstract | Local structure of target objects are essential for robust tracking. However, existing methods based on deep neural networks mostly describe the target appearance from the global view, leading to high sensitivity to non-rigid appearance change and partial occlusion. In this paper, we circumvent this issue by proposing a local structure learning method, which simultaneously considers the local patterns of the target and their structural relationships for more accurate target tracking. To this end, a local pattern detection module is designed to automatically identify discriminative regions of the target objects. The detection results are further refined by a message passing module, which enforces the structural context among local patterns to construct local structures. We show that the message passing module can be formulated as the inference process of a conditional random field (CRF) and implemented by differentiable operations, allowing the entire model to be trained in an end-to-end manner. By considering various combinations of the local structures, our tracker is able to form various types of structure patterns. Target tracking is finally achieved by a matching procedure of the structure patterns between target template and candidates. Extensive evaluations on three benchmark data sets demonstrate that the proposed tracking algorithm performs favorably against state-of-the-art methods while running at a highly efficient speed of 45 fps. |
| Tasks | Real-Time Visual Tracking, Visual Tracking |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Yunhua_Zhang_Structured_Siamese_Network_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Yunhua_Zhang_Structured_Siamese_Network_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/structured-siamese-network-for-real-time |
| Repo | |
| Framework | |
Ontology-Based Retrieval & Neural Approaches for BioASQ Ideal Answer Generation
| Title | Ontology-Based Retrieval & Neural Approaches for BioASQ Ideal Answer Generation |
| Authors | Ashwin Naresh Kumar, Harini Kesavamoorthy, Madhura Das, Pramati Kalwad, Ch, Khyathi u, Teruko Mitamura, Eric Nyberg |
| Abstract | The ever-increasing magnitude of biomedical information sources makes it difficult and time-consuming for a human researcher to find the most relevant documents and pinpointed answers for a specific question or topic when using only a traditional search engine. Biomedical Question Answering systems automatically identify the most relevant documents and pinpointed answers, given an information need expressed as a natural language question. Generating a non-redundant, human-readable summary that satisfies the information need of a given biomedical question is the focus of the Ideal Answer Generation task, part of the BioASQ challenge. This paper presents a system for ideal answer generation (using ontology-based retrieval and a neural learning-to-rank approach, combined with extractive and abstractive summarization techniques) which achieved the highest ROUGE score of 0.659 on the BioASQ 5b batch 2 test. |
| Tasks | Abstractive Text Summarization, Learning-To-Rank, Question Answering, Text Generation |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-5310/ |
| https://www.aclweb.org/anthology/W18-5310 | |
| PWC | https://paperswithcode.com/paper/ontology-based-retrieval-neural-approaches |
| Repo | |
| Framework | |
Toward Better Loanword Identification in Uyghur Using Cross-lingual Word Embeddings
| Title | Toward Better Loanword Identification in Uyghur Using Cross-lingual Word Embeddings |
| Authors | Chenggang Mi, Yating Yang, Lei Wang, Xi Zhou, Tonghai Jiang |
| Abstract | To enrich vocabulary of low resource settings, we proposed a novel method which identify loanwords in monolingual corpora. More specifically, we first use cross-lingual word embeddings as the core feature to generate semantically related candidates based on comparable corpora and a small bilingual lexicon; then, a log-linear model which combines several shallow features such as pronunciation similarity and hybrid language model features to predict the final results. In this paper, we use Uyghur as the receipt language and try to detect loanwords in four donor languages: Arabic, Chinese, Persian and Russian. We conduct two groups of experiments to evaluate the effectiveness of our proposed approach: loanword identification and OOV translation in four language pairs and eight translation directions (Uyghur-Arabic, Arabic-Uyghur, Uyghur-Chinese, Chinese-Uyghur, Uyghur-Persian, Persian-Uyghur, Uyghur-Russian, and Russian-Uyghur). Experimental results on loanword identification show that our method outperforms other baseline models significantly. Neural machine translation models integrating results of loanword identification experiments achieve the best results on OOV translation(with 0.5-0.9 BLEU improvements) |
| Tasks | Language Modelling, Machine Translation, Word Embeddings |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1256/ |
| https://www.aclweb.org/anthology/C18-1256 | |
| PWC | https://paperswithcode.com/paper/toward-better-loanword-identification-in |
| Repo | |
| Framework | |
The Lingering of Gradients: How to Reuse Gradients Over Time
| Title | The Lingering of Gradients: How to Reuse Gradients Over Time |
| Authors | Zeyuan Allen-Zhu, David Simchi-Levi, Xinshang Wang |
| Abstract | Classically, the time complexity of a first-order method is estimated by its number of gradient computations. In this paper, we study a more refined complexity by taking into account the ``lingering’’ of gradients: once a gradient is computed at $x_k$, the additional time to compute gradients at $x_{k+1},x_{k+2},\dots$ may be reduced. We show how this improves the running time of gradient descent and SVRG. For instance, if the “additional time’’ scales linearly with respect to the traveled distance, then the “convergence rate’’ of gradient descent can be improved from $1/T$ to $\exp(-T^{1/3})$. On the empirical side, we solve a hypothetical revenue management problem on the Yahoo! Front Page Today Module application with 4.6m users to $10^{-6}$ error (or $10^{-12}$ dual error) using 6 passes of the dataset. | |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7400-the-lingering-of-gradients-how-to-reuse-gradients-over-time |
| http://papers.nips.cc/paper/7400-the-lingering-of-gradients-how-to-reuse-gradients-over-time.pdf | |
| PWC | https://paperswithcode.com/paper/the-lingering-of-gradients-how-to-reuse-1 |
| Repo | |
| Framework | |
A Computational Architecture for the Morphology of Upper Tanana
| Title | A Computational Architecture for the Morphology of Upper Tanana |
| Authors | Olga Lovick, Christopher Cox, Miikka Silfverberg, Antti Arppe, Mans Hulden |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1294/ |
| https://www.aclweb.org/anthology/L18-1294 | |
| PWC | https://paperswithcode.com/paper/a-computational-architecture-for-the |
| Repo | |
| Framework | |
Bayesian Control of Large MDPs with Unknown Dynamics in Data-Poor Environments
| Title | Bayesian Control of Large MDPs with Unknown Dynamics in Data-Poor Environments |
| Authors | Mahdi Imani, Seyede Fatemeh Ghoreishi, Ulisses M. Braga-Neto |
| Abstract | We propose a Bayesian decision making framework for control of Markov Decision Processes (MDPs) with unknown dynamics and large, possibly continuous, state, action, and parameter spaces in data-poor environments. Most of the existing adaptive controllers for MDPs with unknown dynamics are based on the reinforcement learning framework and rely on large data sets acquired by sustained direct interaction with the system or via a simulator. This is not feasible in many applications, due to ethical, economic, and physical constraints. The proposed framework addresses the data poverty issue by decomposing the problem into an offline planning stage that does not rely on sustained direct interaction with the system or simulator and an online execution stage. In the offline process, parallel Gaussian process temporal difference (GPTD) learning techniques are employed for near-optimal Bayesian approximation of the expected discounted reward over a sample drawn from the prior distribution of unknown parameters. In the online stage, the action with the maximum expected return with respect to the posterior distribution of the parameters is selected. This is achieved by an approximation of the posterior distribution using a Markov Chain Monte Carlo (MCMC) algorithm, followed by constructing multiple Gaussian processes over the parameter space for efficient prediction of the means of the expected return at the MCMC sample. The effectiveness of the proposed framework is demonstrated using a simple dynamical system model with continuous state and action spaces, as well as a more complex model for a metastatic melanoma gene regulatory network observed through noisy synthetic gene expression data. |
| Tasks | Decision Making, Gaussian Processes |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8037-bayesian-control-of-large-mdps-with-unknown-dynamics-in-data-poor-environments |
| http://papers.nips.cc/paper/8037-bayesian-control-of-large-mdps-with-unknown-dynamics-in-data-poor-environments.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-control-of-large-mdps-with-unknown |
| Repo | |
| Framework | |
Early Text Classification Using Multi-Resolution Concept Representations
| Title | Early Text Classification Using Multi-Resolution Concept Representations |
| Authors | Adrian Pastor L{'o}pez-Monroy, Fabio A. Gonz{'a}lez, Manuel Montes, Hugo Jair Escalante, Thamar Solorio |
| Abstract | The intensive use of e-communications in everyday life has given rise to new threats and risks. When the vulnerable asset is the user, detecting these potential attacks before they cause serious damages is extremely important. This paper proposes a novel document representation to improve the early detection of risks in social media sources. The goal is to effectively identify the potential risk using as few text as possible and with as much anticipation as possible. Accordingly, we devise a Multi-Resolution Representation (MulR), which allows us to generate multiple {``}views{''} of the analyzed text. These views capture different semantic meanings for words and documents at different levels of detail, which is very useful in early scenarios to model the variable amounts of evidence. Intuitively, the representation captures better the content of short documents (very early stages) in low resolutions, whereas large documents (medium/large stages) are better modeled with higher resolutions. We evaluate the proposed ideas in two different tasks where anticipation is critical: sexual predator detection and depression detection. The experimental evaluation for these early tasks revealed that the proposed approach outperforms previous methodologies by a considerable margin. | |
| Tasks | Text Classification |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1110/ |
| https://www.aclweb.org/anthology/N18-1110 | |
| PWC | https://paperswithcode.com/paper/early-text-classification-using-multi |
| Repo | |
| Framework | |
Challenges in Speech Recognition and Translation of High-Value Low-Density Polysynthetic Languages
| Title | Challenges in Speech Recognition and Translation of High-Value Low-Density Polysynthetic Languages |
| Authors | Judith Klavans, John Morgan, Stephen LaRocca, Jeffrey Micher, Clare Voss |
| Abstract | |
| Tasks | Machine Translation, Speech Recognition |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-1921/ |
| https://www.aclweb.org/anthology/W18-1921 | |
| PWC | https://paperswithcode.com/paper/challenges-in-speech-recognition-and |
| Repo | |
| Framework | |
Creating a WhatsApp Dataset to Study Pre-teen Cyberbullying
| Title | Creating a WhatsApp Dataset to Study Pre-teen Cyberbullying |
| Authors | Rachele Sprugnoli, Stefano Menini, Sara Tonelli, Filippo Oncini, Enrico Piras |
| Abstract | Although WhatsApp is used by teenagers as one major channel of cyberbullying, such interactions remain invisible due to the app privacy policies that do not allow ex-post data collection. Indeed, most of the information on these phenomena rely on surveys regarding self-reported data. In order to overcome this limitation, we describe in this paper the activities that led to the creation of a WhatsApp dataset to study cyberbullying among Italian students aged 12-13. We present not only the collected chats with annotations about user role and type of offense, but also the living lab created in a collaboration between researchers and schools to monitor and analyse cyberbullying. Finally, we discuss some open issues, dealing with ethical, operational and epistemic aspects. |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5107/ |
| https://www.aclweb.org/anthology/W18-5107 | |
| PWC | https://paperswithcode.com/paper/creating-a-whatsapp-dataset-to-study-pre-teen |
| Repo | |
| Framework | |
The Interface Between Readability and Automatic Text Simplification
| Title | The Interface Between Readability and Automatic Text Simplification |
| Authors | Thomas Fran{\c{c}}ois |
| Abstract | |
| Tasks | Complex Word Identification, Text Simplification |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-7001/ |
| https://www.aclweb.org/anthology/W18-7001 | |
| PWC | https://paperswithcode.com/paper/the-interface-between-readability-and |
| Repo | |
| Framework | |
Proceedings of the CoNLL–SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection
| Title | Proceedings of the CoNLL–SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/K18-3000/ |
| https://www.aclweb.org/anthology/K18-3000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-conll-sigmorphon-2018 |
| Repo | |
| Framework | |
DeepExposure: Learning to Expose Photos with Asynchronously Reinforced Adversarial Learning
| Title | DeepExposure: Learning to Expose Photos with Asynchronously Reinforced Adversarial Learning |
| Authors | Runsheng Yu, Wenyu Liu, Yasen Zhang, Zhi Qu, Deli Zhao, Bo Zhang |
| Abstract | The accurate exposure is the key of capturing high-quality photos in computational photography, especially for mobile phones that are limited by sizes of camera modules. Inspired by luminosity masks usually applied by professional photographers, in this paper, we develop a novel algorithm for learning local exposures with deep reinforcement adversarial learning. To be specific, we segment an image into sub-images that can reflect variations of dynamic range exposures according to raw low-level features. Based on these sub-images, a local exposure for each sub-image is automatically learned by virtue of policy network sequentially while the reward of learning is globally designed for striking a balance of overall exposures. The aesthetic evaluation function is approximated by discriminator in generative adversarial networks. The reinforcement learning and the adversarial learning are trained collaboratively by asynchronous deterministic policy gradient and generative loss approximation. To further simply the algorithmic architecture, we also prove the feasibility of leveraging the discriminator as the value function. Further more, we employ each local exposure to retouch the raw input image respectively, thus delivering multiple retouched images under different exposures which are fused with exposure blending. The extensive experiments verify that our algorithms are superior to state-of-the-art methods in terms of quantitative accuracy and visual illustration. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7484-deepexposure-learning-to-expose-photos-with-asynchronously-reinforced-adversarial-learning |
| http://papers.nips.cc/paper/7484-deepexposure-learning-to-expose-photos-with-asynchronously-reinforced-adversarial-learning.pdf | |
| PWC | https://paperswithcode.com/paper/deepexposure-learning-to-expose-photos-with |
| Repo | |
| Framework | |
Computer-assisted Speaker Diarization: How to Evaluate Human Corrections
| Title | Computer-assisted Speaker Diarization: How to Evaluate Human Corrections |
| Authors | Pierre-Alex Broux, re, David Doukhan, Simon Petitrenaud, Sylvain Meignier, Jean Carrive |
| Abstract | |
| Tasks | Active Learning, Face Recognition, Optical Character Recognition, Speaker Diarization, Speaker Identification, Speaker Recognition |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1238/ |
| https://www.aclweb.org/anthology/L18-1238 | |
| PWC | https://paperswithcode.com/paper/computer-assisted-speaker-diarization-how-to |
| Repo | |
| Framework | |
Data center cooling using model-predictive control
| Title | Data center cooling using model-predictive control |
| Authors | Nevena Lazic, Craig Boutilier, Tyler Lu, Eehern Wong, Binz Roy, Mk Ryu, Greg Imwalle |
| Abstract | Despite impressive recent advances in reinforcement learning (RL), its deployment in real-world physical systems is often complicated by unexpected events, limited data, and the potential for expensive failures. In this paper, we describe an application of RL “in the wild” to the task of regulating temperatures and airflow inside a large-scale data center (DC). Adopting a data-driven, model-based approach, we demonstrate that an RL agent with little prior knowledge is able to effectively and safely regulate conditions on a server floor after just a few hours of exploration, while improving operational efficiency relative to existing PID controllers. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7638-data-center-cooling-using-model-predictive-control |
| http://papers.nips.cc/paper/7638-data-center-cooling-using-model-predictive-control.pdf | |
| PWC | https://paperswithcode.com/paper/data-center-cooling-using-model-predictive |
| Repo | |
| Framework | |
XLIFF 2
| Title | XLIFF 2 |
| Authors | David Filip |
| Abstract | |
| Tasks | |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-2003/ |
| https://www.aclweb.org/anthology/W18-2003 | |
| PWC | https://paperswithcode.com/paper/xliff-2 |
| Repo | |
| Framework | |
