Paper Group NANR 44
Exploiting Implicit Trust and Geo-social Network for Recommendation. Logician and Orator: Learning from the Duality between Language and Knowledge in Open Domain. Decipherment for Adversarial Offensive Language Detection. Estimators for Multivariate Information Measures in General Probability Spaces. Decipherment of Substitution Ciphers with Neural …
Exploiting Implicit Trust and Geo-social Network for Recommendation
Title | Exploiting Implicit Trust and Geo-social Network for Recommendation |
Authors | Feiyang Li School of Computer Science and Technology/Suzhou Institute for Advanced Study, University of Science and Technology of China, P.R.china mmmwhy@mail.ustc.edu.cn |
Abstract | Abstract—Recommender system (RS) seeks to predict the rating or preference a user would give to an item, this system often relies on collaborative filtering (CF). CF suffers from the problems of data sparsity, cold start and location insensitive. Existing RSs do not consider the spatial extent of users, we analyze the users’ location data from four commercial websites, and conclude that people with close social relationships prefer to purchase in places that are also physically close.State-of-the-art recommendation algorithm TrustSVD extends RS with social trust information, we propose Trust-location SVD (TLSVD) by incorporating the location information and implicit trust into TrustSVD. The improved TLSVD helps to quantitatively analyze the spatial closeness and preference similarity between users. Experimental results indicate that the accuracy of our method is better than other multiple counterparts’, especially when active users have location information or few ratings. |
Tasks | Recommendation Systems |
Published | 2018-12-06 |
URL | https://ieeexplore.ieee.org/Xplore/home.jsp |
https://ieeexplore.ieee.org/Xplore/home.jsp | |
PWC | https://paperswithcode.com/paper/exploiting-implicit-trust-and-geo-social |
Repo | |
Framework | |
Logician and Orator: Learning from the Duality between Language and Knowledge in Open Domain
Title | Logician and Orator: Learning from the Duality between Language and Knowledge in Open Domain |
Authors | Mingming Sun, Xu Li, Ping Li |
Abstract | We propose the task of Open-Domain Information Narration (OIN) as the reverse task of Open Information Extraction (OIE), to implement the dual structure between language and knowledge in the open domain. Then, we develop an agent, called Orator, to accomplish the OIN task, and assemble the Orator and the recently proposed OIE agent {—} Logician into a dual system to utilize the duality structure with a reinforcement learning paradigm. Experimental results reveal the dual structure between OIE and OIN tasks helps to build better both OIE agents and OIN agents. |
Tasks | Open Information Extraction, Relation Classification |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/D18-1236/ |
https://www.aclweb.org/anthology/D18-1236 | |
PWC | https://paperswithcode.com/paper/logician-and-orator-learning-from-the-duality |
Repo | |
Framework | |
Decipherment for Adversarial Offensive Language Detection
Title | Decipherment for Adversarial Offensive Language Detection |
Authors | Zhelun Wu, Nishant Kambhatla, Anoop Sarkar |
Abstract | Automated filters are commonly used by online services to stop users from sending age-inappropriate, bullying messages, or asking others to expose personal information. Previous work has focused on rules or classifiers to detect and filter offensive messages, but these are vulnerable to cleverly disguised plaintext and unseen expressions especially in an adversarial setting where the users can repeatedly try to bypass the filter. In this paper, we model the disguised messages as if they are produced by encrypting the original message using an invented cipher. We apply automatic decipherment techniques to decode the disguised malicious text, which can be then filtered using rules or classifiers. We provide experimental results on three different datasets and show that decipherment is an effective tool for this task. |
Tasks | Spelling Correction |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/W18-5119/ |
https://www.aclweb.org/anthology/W18-5119 | |
PWC | https://paperswithcode.com/paper/decipherment-for-adversarial-offensive |
Repo | |
Framework | |
Estimators for Multivariate Information Measures in General Probability Spaces
Title | Estimators for Multivariate Information Measures in General Probability Spaces |
Authors | Arman Rahimzamani, Himanshu Asnani, Pramod Viswanath, Sreeram Kannan |
Abstract | Information theoretic quantities play an important role in various settings in machine learning, including causality testing, structure inference in graphical models, time-series problems, feature selection as well as in providing privacy guarantees. A key quantity of interest is the mutual information and generalizations thereof, including conditional mutual information, multivariate mutual information, total correlation and directed information. While the aforementioned information quantities are well defined in arbitrary probability spaces, existing estimators employ a $\Sigma H$ method, which can only work in purely discrete space or purely continuous case since entropy (or differential entropy) is well defined only in that regime. In this paper, we define a general graph divergence measure ($\mathbb{GDM}$), generalizing the aforementioned information measures and we construct a novel estimator via a coupling trick that directly estimates these multivariate information measures using the Radon-Nikodym derivative. These estimators are proven to be consistent in a general setting which includes several cases where the existing estimators fail, thus providing the only known estimators for the following settings: (1) the data has some discrete and some continuous valued components (2) some (or all) of the components themselves are discrete-continuous \textit{mixtures} (3) the data is real-valued but does not have a joint density on the entire space, rather is supported on a low-dimensional manifold. We show that our proposed estimators significantly outperform known estimators on synthetic and real datasets. |
Tasks | Feature Selection, Time Series |
Published | 2018-12-01 |
URL | http://papers.nips.cc/paper/8084-estimators-for-multivariate-information-measures-in-general-probability-spaces |
http://papers.nips.cc/paper/8084-estimators-for-multivariate-information-measures-in-general-probability-spaces.pdf | |
PWC | https://paperswithcode.com/paper/estimators-for-multivariate-information |
Repo | |
Framework | |
Decipherment of Substitution Ciphers with Neural Language Models
Title | Decipherment of Substitution Ciphers with Neural Language Models |
Authors | Nishant Kambhatla, Anahita Mansouri Bigvand, Anoop Sarkar |
Abstract | |
Tasks | Language Modelling |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/papers/D18-1102/d18-1102 |
https://www.aclweb.org/anthology/D18-1102 | |
PWC | https://paperswithcode.com/paper/decipherment-of-substitution-ciphers-with |
Repo | |
Framework | |
Neural Relation Classification with Text Descriptions
Title | Neural Relation Classification with Text Descriptions |
Authors | Feiliang Ren, Di Zhou, Zhihui Liu, Yongcheng Li, Rongsheng Zhao, Yongkang Liu, Xiaobo Liang |
Abstract | Relation classification is an important task in natural language processing fields. State-of-the-art methods usually concentrate on building deep neural networks based classification models on the training data in which the relations of the labeled entity pairs are given. However, these methods usually suffer from the data sparsity issue greatly. On the other hand, we notice that it is very easily to obtain some concise text descriptions for almost all of the entities in a relation classification task. The text descriptions can provide helpful supplementary information for relation classification. But they are ignored by most of existing methods. In this paper, we propose DesRC, a new neural relation classification method which integrates entities{'} text descriptions into deep neural networks models. We design a two-level attention mechanism to select the most useful information from the {}intra-sentence{''} aspect and the { }cross-sentence{''} aspect. Besides, the adversarial training method is also used to further improve the classification per-formance. Finally, we evaluate the proposed method on the SemEval 2010 dataset. Extensive experiments show that our method achieves much better experimental results than other state-of-the-art relation classification methods. |
Tasks | Relation Classification |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/C18-1100/ |
https://www.aclweb.org/anthology/C18-1100 | |
PWC | https://paperswithcode.com/paper/neural-relation-classification-with-text |
Repo | |
Framework | |
Representing Entropy : A short proof of the equivalence between soft Q-learning and policy gradients
Title | Representing Entropy : A short proof of the equivalence between soft Q-learning and policy gradients |
Authors | Pierre H. Richemond, Brendan Maginnis |
Abstract | Two main families of reinforcement learning algorithms, Q-learning and policy gradients, have recently been proven to be equivalent when using a softmax relaxation on one part, and an entropic regularization on the other. We relate this result to the well-known convex duality of Shannon entropy and the softmax function. Such a result is also known as the Donsker-Varadhan formula. This provides a short proof of the equivalence. We then interpret this duality further, and use ideas of convex analysis to prove a new policy inequality relative to soft Q-learning. |
Tasks | Q-Learning |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=HyY0Ff-AZ |
https://openreview.net/pdf?id=HyY0Ff-AZ | |
PWC | https://paperswithcode.com/paper/representing-entropy-a-short-proof-of-the |
Repo | |
Framework | |
Anaphora Resolution for Twitter Conversations: An Exploratory Study
Title | Anaphora Resolution for Twitter Conversations: An Exploratory Study |
Authors | Berfin Akta{\c{s}}, Tatjana Scheffler, Manfred Stede |
Abstract | We present a corpus study of pronominal anaphora on Twitter conversations. After outlining the specific features of this genre, with respect to reference resolution, we explain the construction of our corpus and the annotation steps. From this we derive a list of phenomena that need to be considered when performing anaphora resolution on this type of data. Finally, we test the performance of an off-the-shelf resolution system, and provide some qualitative error analysis. |
Tasks | |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/W18-0701/ |
https://www.aclweb.org/anthology/W18-0701 | |
PWC | https://paperswithcode.com/paper/anaphora-resolution-for-twitter-conversations |
Repo | |
Framework | |
CaLcs: Continuously Approximating Longest Common Subsequence for Sequence Level Optimization
Title | CaLcs: Continuously Approximating Longest Common Subsequence for Sequence Level Optimization |
Authors | Semih Yavuz, Chung-Cheng Chiu, Patrick Nguyen, Yonghui Wu |
Abstract | Maximum-likelihood estimation (MLE) is one of the most widely used approaches for training structured prediction models for text-generation based natural language processing applications. However, besides exposure bias, models trained with MLE suffer from wrong objective problem where they are trained to maximize the word-level correct next step prediction, but are evaluated with respect to sequence-level discrete metrics such as ROUGE and BLEU. Several variants of policy-gradient methods address some of these problems by optimizing for final discrete evaluation metrics and showing improvements over MLE training for downstream tasks like text summarization and machine translation. However, policy-gradient methods suffers from high sample variance, making the training process very difficult and unstable. In this paper, we present an alternative direction towards mitigating this problem by introducing a new objective (CaLcs) based on a differentiable surrogate of longest common subsequence (LCS) measure that captures sequence-level structure similarity. Experimental results on abstractive summarization and machine translation validate the effectiveness of the proposed approach. |
Tasks | Abstractive Text Summarization, Image Captioning, Machine Translation, Policy Gradient Methods, Structured Prediction, Text Generation, Text Summarization |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/D18-1406/ |
https://www.aclweb.org/anthology/D18-1406 | |
PWC | https://paperswithcode.com/paper/calcs-continuously-approximating-longest |
Repo | |
Framework | |
Alibaba’s Neural Machine Translation Systems for WMT18
Title | Alibaba’s Neural Machine Translation Systems for WMT18 |
Authors | Yongchao Deng, Shanbo Cheng, Jun Lu, Kai Song, Jingang Wang, Shenglan Wu, Liang Yao, Guchun Zhang, Haibo Zhang, Pei Zhang, Changfeng Zhu, Boxing Chen |
Abstract | This paper describes the submission systems of Alibaba for WMT18 shared news translation task. We participated in 5 translation directions including English ↔ Russian, English ↔ Turkish in both directions and English → Chinese. Our systems are based on Google{'}s Transformer model architecture, into which we integrated the most recent features from the academic research. We also employed most techniques that have been proven effective during the past WMT years, such as BPE, back translation, data selection, model ensembling and reranking, at industrial scale. For some morphologically-rich languages, we also incorporated linguistic knowledge into our neural network. For the translation tasks in which we have participated, our resulting systems achieved the best case sensitive BLEU score in all 5 directions. Notably, our English → Russian system outperformed the second reranked system by 5 BLEU score. |
Tasks | Machine Translation |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/W18-6408/ |
https://www.aclweb.org/anthology/W18-6408 | |
PWC | https://paperswithcode.com/paper/alibabas-neural-machine-translation-systems |
Repo | |
Framework | |
Adversarial Geometry-Aware Human Motion Prediction
Title | Adversarial Geometry-Aware Human Motion Prediction |
Authors | Liang-Yan Gui, Yu-Xiong Wang, Xiaodan Liang, Jose M. F. Moura |
Abstract | We explore an approach to forecasting human motion in a few milliseconds given an input 3D skeleton sequence based on a recurrent encoder-decoder framework. Current approaches suffer from the problem of prediction discontinuities and may fail to predict human-like motion in longer time horizons due to error accumulation. We address these critical issues by incorporating local geometric structure constraints and regularizing predictions with plausible temporal smoothness and continuity from a global perspective. Specifically, rather than using the conventional Euclidean loss, we propose a novel frame-wise geodesic loss as a geometrically meaningful, more precise distance measurement. Moreover, inspired by the adversarial training mechanism, we present a new learning procedure to simultaneously validate the sequence-level plausibility of the prediction and its coherence with the input sequence by introducing two global recurrent discriminators. An unconditional, fidelity discriminator and a conditional, continuity discriminator are jointly trained along with the predictor in an adversarial manner. Our resulting adversarial geometry-aware encoder-decoder (AGED) model significantly outperforms state-of-the-art deep learning based approaches on the heavily benchmarked H3.6M dataset in both short-term and long-term predictions. |
Tasks | motion prediction |
Published | 2018-09-01 |
URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Liangyan_Gui_Adversarial_Geometry-Aware_Human_ECCV_2018_paper.html |
http://openaccess.thecvf.com/content_ECCV_2018/papers/Liangyan_Gui_Adversarial_Geometry-Aware_Human_ECCV_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/adversarial-geometry-aware-human-motion |
Repo | |
Framework | |
CLEAR – Simple Corpus for Medical French
Title | CLEAR – Simple Corpus for Medical French |
Authors | Natalia Grabar, R{'e}mi Cardon |
Abstract | |
Tasks | Information Retrieval, Machine Translation, Text Simplification |
Published | 2018-11-01 |
URL | https://www.aclweb.org/anthology/W18-7002/ |
https://www.aclweb.org/anthology/W18-7002 | |
PWC | https://paperswithcode.com/paper/clear-simple-corpus-for-medical-french |
Repo | |
Framework | |
Metaphor Suggestions based on a Semantic Metaphor Repository
Title | Metaphor Suggestions based on a Semantic Metaphor Repository |
Authors | Gerard de Melo |
Abstract | |
Tasks | Semantic Textual Similarity, Topic Models |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1695/ |
https://www.aclweb.org/anthology/L18-1695 | |
PWC | https://paperswithcode.com/paper/metaphor-suggestions-based-on-a-semantic |
Repo | |
Framework | |
Decentralize and Randomize: Faster Algorithm for Wasserstein Barycenters
Title | Decentralize and Randomize: Faster Algorithm for Wasserstein Barycenters |
Authors | Pavel Dvurechenskii, Darina Dvinskikh, Alexander Gasnikov, Cesar Uribe, Angelia Nedich |
Abstract | We study the decentralized distributed computation of discrete approximations for the regularized Wasserstein barycenter of a finite set of continuous probability measures distributedly stored over a network. We assume there is a network of agents/machines/computers, and each agent holds a private continuous probability measure and seeks to compute the barycenter of all the measures in the network by getting samples from its local measure and exchanging information with its neighbors. Motivated by this problem, we develop, and analyze, a novel accelerated primal-dual stochastic gradient method for general stochastic convex optimization problems with linear equality constraints. Then, we apply this method to the decen- tralized distributed optimization setting to obtain a new algorithm for the distributed semi-discrete regularized Wasserstein barycenter problem. Moreover, we show explicit non-asymptotic complexity for the proposed algorithm. Finally, we show the effectiveness of our method on the distributed computation of the regularized Wasserstein barycenter of univariate Gaussian and von Mises distributions, as well as some applications to image aggregation. |
Tasks | Distributed Optimization |
Published | 2018-12-01 |
URL | http://papers.nips.cc/paper/8274-decentralize-and-randomize-faster-algorithm-for-wasserstein-barycenters |
http://papers.nips.cc/paper/8274-decentralize-and-randomize-faster-algorithm-for-wasserstein-barycenters.pdf | |
PWC | https://paperswithcode.com/paper/decentralize-and-randomize-faster-algorithm |
Repo | |
Framework | |
Real-time Scholarly Retweeting Prediction System
Title | Real-time Scholarly Retweeting Prediction System |
Authors | Zhunchen Luo, Xiao Liu |
Abstract | Twitter has become one of the most import channels to spread latest scholarly information because of its fast information spread speed. How to predict whether a scholarly tweet will be retweeted is a key task in understanding the message propagation within large user communities. Hence, we present the real-time scholarly retweeting prediction system that retrieves scholarly tweets which will be retweeted. First, we filter scholarly tweets from tracking a tweet stream. Then, we extract Tweet Scholar Blocks indicating metadata of papers. At last, we combine scholarly features with the Tweet Scholar Blocks to predict whether a scholarly tweet will be retweeted. Our system outperforms chosen baseline systems. Additionally, our system has the potential to predict scientific impact in real-time. |
Tasks | |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/C18-2006/ |
https://www.aclweb.org/anthology/C18-2006 | |
PWC | https://paperswithcode.com/paper/real-time-scholarly-retweeting-prediction |
Repo | |
Framework | |