Paper Group NANR 160
Improving Stochastic Policy Gradients in Continuous Control with Deep Reinforcement Learning using the Beta Distribution. Preferential Bayesian Optmization. Constitui\cc~ao de Um Dicion'ario Eletr^onico Tril'\ingue Fundado em Frames a partir da Extra\cc~ao Autom'atica de Candidatos a Termos do Dom'\inio do Turismo (The Constitution of a Tril …
Improving Stochastic Policy Gradients in Continuous Control with Deep Reinforcement Learning using the Beta Distribution
| Title | Improving Stochastic Policy Gradients in Continuous Control with Deep Reinforcement Learning using the Beta Distribution |
| Authors | Po-Wei Chou, Daniel Maturana, Sebastian Scherer |
| Abstract | Recently, reinforcement learning with deep neural networks has achieved great success in challenging continuous control problems such as 3D locomotion and robotic manipulation. However, in real-world control problems, the actions one can take are bounded by physical constraints, which introduces a bias when the standard Gaussian distribution is used as the stochastic policy. In this work, we propose to use the Beta distribution as an alternative and analyze the bias and variance of the policy gradients of both policies. We show that the Beta policy is bias-free and provides significantly faster convergence and higher scores over the Gaussian policy when both are used with trust region policy optimization (TRPO) and actor critic with experience replay (ACER), the state-of-the-art on- and off-policy stochastic methods respectively, on OpenAI Gym’s and MuJoCo’s continuous control environments. |
| Tasks | Continuous Control |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=733 |
| http://proceedings.mlr.press/v70/chou17a/chou17a.pdf | |
| PWC | https://paperswithcode.com/paper/improving-stochastic-policy-gradients-in |
| Repo | |
| Framework | |
Preferential Bayesian Optmization
| Title | Preferential Bayesian Optmization |
| Authors | Javier González, Zhenwen Dai, Andreas Damianou, Neil D. Lawrence |
| Abstract | Bayesian optimization (BO) has emerged during the last few years as an effective approach to optimize black-box functions where direct queries of the objective are expensive. We consider the case where direct access to the function is not possible, but information about user preferences is. Such scenarios arise in problems where human preferences are modeled, such as A/B tests or recommender systems. We present a new framework for this scenario that we call Preferential Bayesian Optimization (PBO) and that allows to find the optimum of a latent function that can only be queried through pairwise comparisons, so-called duels. PBO extend the applicability of standard BO ideas and generalizes previous discrete dueling approaches by modeling the probability of the the winner of each duel by means of Gaussian process model with a Bernoulli likelihood. The latent preference function is used to define a family of acquisition functions that extend usual policies used in BO. We illustrate the benefits of PBO in a variety of experiments in which we show how the way correlations are modeled is the key ingredient to drastically reduce the number of comparisons to find the optimum of the latent function of interest. |
| Tasks | Recommendation Systems |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=565 |
| http://proceedings.mlr.press/v70/gonzalez17a/gonzalez17a.pdf | |
| PWC | https://paperswithcode.com/paper/preferential-bayesian-optmization |
| Repo | |
| Framework | |
Constitui\cc~ao de Um Dicion'ario Eletr^onico Tril'\ingue Fundado em Frames a partir da Extra\cc~ao Autom'atica de Candidatos a Termos do Dom'\inio do Turismo (The Constitution of a Trilingual Eletronic Dictionary Based on Frames from the Automatic Extraction of Candidate Terms of the Tourism Domain)[In Portuguese]
| Title | Constitui\cc~ao de Um Dicion'ario Eletr^onico Tril'\ingue Fundado em Frames a partir da Extra\cc~ao Autom'atica de Candidatos a Termos do Dom'\inio do Turismo (The Constitution of a Trilingual Eletronic Dictionary Based on Frames from the Automatic Extraction of Candidate Terms of the Tourism Domain)[In Portuguese] |
| Authors | Simone Rodrigues Peron-Corr{^e}a, Tiago Timponi Torrent |
| Abstract | |
| Tasks | |
| Published | 2017-10-01 |
| URL | https://www.aclweb.org/anthology/W17-6622/ |
| https://www.aclweb.org/anthology/W17-6622 | |
| PWC | https://paperswithcode.com/paper/constituiaao-de-um-dicionario-eletra-nico |
| Repo | |
| Framework | |
NUIG at EmoInt-2017: BiLSTM and SVR Ensemble to Detect Emotion Intensity
| Title | NUIG at EmoInt-2017: BiLSTM and SVR Ensemble to Detect Emotion Intensity |
| Authors | Vladimir Andryushechkin, Ian Wood, James O{'} Neill |
| Abstract | This paper describes the entry NUIG in the WASSA 2017 (8th Workshop on Computational Approaches to Subjectivity, Sentiment {&} Social Media Analysis) shared task on emotion recognition. The NUIG system used an SVR (SVM regression) and BLSTM ensemble, utilizing primarily n-grams (for SVR features) and tweet word embeddings (for BLSTM features). Experiments were carried out on several other candidate features, some of which were added to the SVR model. Parameter selection for the SVR model was run as a grid search whilst parameters for the BLSTM model were selected through a non-exhaustive ad-hoc search. |
| Tasks | Emotion Recognition, Speech Recognition, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5223/ |
| https://www.aclweb.org/anthology/W17-5223 | |
| PWC | https://paperswithcode.com/paper/nuig-at-emoint-2017-bilstm-and-svr-ensemble |
| Repo | |
| Framework | |
Uma Proposta Metodol'ogica para a Categoriza\cc~ao Automatizada de Atra\cc~oes Tur'\isticas a partir de Coment'arios de Usu'arios em Plataformas Online (A Methodological Proposition for the Automatic Categorization of Touristic Attractions from User Comments in Online Platforms)[In Portuguese]
| Title | Uma Proposta Metodol'ogica para a Categoriza\cc~ao Automatizada de Atra\cc~oes Tur'\isticas a partir de Coment'arios de Usu'arios em Plataformas Online (A Methodological Proposition for the Automatic Categorization of Touristic Attractions from User Comments in Online Platforms)[In Portuguese] |
| Authors | Vanessa Maria Ramos Lopes Paiva, Tiago Timponi Torrent |
| Abstract | |
| Tasks | |
| Published | 2017-10-01 |
| URL | https://www.aclweb.org/anthology/W17-6627/ |
| https://www.aclweb.org/anthology/W17-6627 | |
| PWC | https://paperswithcode.com/paper/uma-proposta-metodola3gica-para-a |
| Repo | |
| Framework | |
TrentoTeam at SemEval-2017 Task 3: An application of Grice Maxims in Ranking Community Question Answers
| Title | TrentoTeam at SemEval-2017 Task 3: An application of Grice Maxims in Ranking Community Question Answers |
| Authors | Mohammed R. H. Qwaider, Abed Alhakim Freihat, Fausto Giunchiglia |
| Abstract | In this paper we present the Tren-toTeam system which participated to thetask 3 at SemEval-2017 (Nakov et al.,2017).We concentrated our work onapplying Grice Maxims(used in manystate-of-the-art Machine learning applica-tions(Vogel et al., 2013; Kheirabadiand Aghagolzadeh, 2012; Dale and Re-iter, 1995; Franke, 2011)) to ranking an-swers of a question by answers relevancy.Particularly, we created a ranker systembased on relevancy scores, assigned by 3main components: Named entity recogni-tion, similarity score, sentiment analysis.Our system obtained a comparable resultsto Machine learning systems. |
| Tasks | Named Entity Recognition, Sentiment Analysis |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2043/ |
| https://www.aclweb.org/anthology/S17-2043 | |
| PWC | https://paperswithcode.com/paper/trentoteam-at-semeval-2017-task-3-an |
| Repo | |
| Framework | |
Character-based Bidirectional LSTM-CRF with words and characters for Japanese Named Entity Recognition
| Title | Character-based Bidirectional LSTM-CRF with words and characters for Japanese Named Entity Recognition |
| Authors | Shotaro Misawa, Motoki Taniguchi, Yasuhide Miura, Tomoko Ohkuma |
| Abstract | Recently, neural models have shown superior performance over conventional models in NER tasks. These models use CNN to extract sub-word information along with RNN to predict a tag for each word. However, these models have been tested almost entirely on English texts. It remains unclear whether they perform similarly in other languages. We worked on Japanese NER using neural models and discovered two obstacles of the state-of-the-art model. First, CNN is unsuitable for extracting Japanese sub-word information. Secondly, a model predicting a tag for each word cannot extract an entity when a part of a word composes an entity. The contributions of this work are (1) verifying the effectiveness of the state-of-the-art NER model for Japanese, (2) proposing a neural model for predicting a tag for each character using word and character information. Experimentally obtained results demonstrate that our model outperforms the state-of-the-art neural English NER model in Japanese. |
| Tasks | Named Entity Recognition |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4114/ |
| https://www.aclweb.org/anthology/W17-4114 | |
| PWC | https://paperswithcode.com/paper/character-based-bidirectional-lstm-crf-with |
| Repo | |
| Framework | |
Practical Data-Dependent Metric Compression with Provable Guarantees
| Title | Practical Data-Dependent Metric Compression with Provable Guarantees |
| Authors | Piotr Indyk, Ilya Razenshteyn, Tal Wagner |
| Abstract | We introduce a new distance-preserving compact representation of multi-dimensional point-sets. Given n points in a d-dimensional space where each coordinate is represented using B bits (i.e., dB bits per point), it produces a representation of size O( d log(d B/epsilon) +log n) bits per point from which one can approximate the distances up to a factor of 1 + epsilon. Our algorithm almost matches the recent bound of Indyk et al, 2017} while being much simpler. We compare our algorithm to Product Quantization (PQ) (Jegou et al, 2011) a state of the art heuristic metric compression method. We evaluate both algorithms on several data sets: SIFT, MNIST, New York City taxi time series and a synthetic one-dimensional data set embedded in a high-dimensional space. Our algorithm produces representations that are comparable to or better than those produced by PQ, while having provable guarantees on its performance. |
| Tasks | Quantization, Time Series |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6855-practical-data-dependent-metric-compression-with-provable-guarantees |
| http://papers.nips.cc/paper/6855-practical-data-dependent-metric-compression-with-provable-guarantees.pdf | |
| PWC | https://paperswithcode.com/paper/practical-data-dependent-metric-compression |
| Repo | |
| Framework | |
LIPN-UAM at EmoInt-2017:Combination of Lexicon-based features and Sentence-level Vector Representations for Emotion Intensity Determination
| Title | LIPN-UAM at EmoInt-2017:Combination of Lexicon-based features and Sentence-level Vector Representations for Emotion Intensity Determination |
| Authors | Davide Buscaldi, Belem Priego |
| Abstract | This paper presents the combined LIPN-UAM participation in the WASSA 2017 Shared Task on Emotion Intensity. In particular, the paper provides some highlights on the Tweetaneuse system that was presented to the shared task. We combined lexicon-based features with sentence-level vector representations to implement a random forest regressor. |
| Tasks | Emotion Recognition, Sentiment Analysis, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5236/ |
| https://www.aclweb.org/anthology/W17-5236 | |
| PWC | https://paperswithcode.com/paper/lipn-uam-at-emoint-2017combination-of-lexicon |
| Repo | |
| Framework | |
Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning
| Title | Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning |
| Authors | Yevgen Chebotar, Karol Hausman, Marvin Zhang, Gaurav Sukhatme, Stefan Schaal, Sergey Levine |
| Abstract | Reinforcement learning algorithms for real-world robotic applications must be able to handle complex, unknown dynamical systems while maintaining data-efficient learning. These requirements are handled well by model-free and model-based RL approaches, respectively. In this work, we aim to combine the advantages of these approaches. By focusing on time-varying linear-Gaussian policies, we enable a model-based algorithm based on the linear-quadratic regulator that can be integrated into the model-free framework of path integral policy improvement. We can further combine our method with guided policy search to train arbitrary parameterized policies such as deep neural networks. Our simulation and real-world experiments demonstrate that this method can solve challenging manipulation tasks with comparable or better performance than model-free methods while maintaining the sample efficiency of model-based methods. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=853 |
| http://proceedings.mlr.press/v70/chebotar17a/chebotar17a.pdf | |
| PWC | https://paperswithcode.com/paper/combining-model-based-and-model-free-updates |
| Repo | |
| Framework | |
On the Relevance of Syntactic and Discourse Features for Author Profiling and Identification
| Title | On the Relevance of Syntactic and Discourse Features for Author Profiling and Identification |
| Authors | Juan Soler-Company, Leo Wanner |
| Abstract | The majority of approaches to author profiling and author identification focus mainly on lexical features, i.e., on the content of a text. We argue that syntactic and discourse features play a significantly more prominent role than they were given in the past. We show that they achieve state-of-the-art performance in author and gender identification on a literary corpus while keeping the feature set small: the used feature set is composed of only 188 features and still outperforms the winner of the PAN 2014 shared task on author verification in the literary genre. |
| Tasks | Feature Engineering |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2108/ |
| https://www.aclweb.org/anthology/E17-2108 | |
| PWC | https://paperswithcode.com/paper/on-the-relevance-of-syntactic-and-discourse |
| Repo | |
| Framework | |
Dykstra’s Algorithm, ADMM, and Coordinate Descent: Connections, Insights, and Extensions
| Title | Dykstra’s Algorithm, ADMM, and Coordinate Descent: Connections, Insights, and Extensions |
| Authors | Ryan J. Tibshirani |
| Abstract | We study connections between Dykstra’s algorithm for projecting onto an intersection of convex sets, the augmented Lagrangian method of multipliers or ADMM, and block coordinate descent. We prove that coordinate descent for a regularized regression problem, in which the penalty is a separable sum of support functions, is exactly equivalent to Dykstra’s algorithm applied to the dual problem. ADMM on the dual problem is also seen to be equivalent, in the special case of two sets, with one being a linear subspace. These connections, aside from being interesting in their own right, suggest new ways of analyzing and extending coordinate descent. For example, from existing convergence theory on Dykstra’s algorithm over polyhedra, we discern that coordinate descent for the lasso problem converges at an (asymptotically) linear rate. We also develop two parallel versions of coordinate descent, based on the Dykstra and ADMM connections. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6655-dykstras-algorithm-admm-and-coordinate-descent-connections-insights-and-extensions |
| http://papers.nips.cc/paper/6655-dykstras-algorithm-admm-and-coordinate-descent-connections-insights-and-extensions.pdf | |
| PWC | https://paperswithcode.com/paper/dykstras-algorithm-admm-and-coordinate |
| Repo | |
| Framework | |
Unsupervised Cross-Lingual Scaling of Political Texts
| Title | Unsupervised Cross-Lingual Scaling of Political Texts |
| Authors | Goran Glava{\v{s}}, Federico Nanni, Simone Paolo Ponzetto |
| Abstract | Political text scaling aims to linearly order parties and politicians across political dimensions (e.g., left-to-right ideology) based on textual content (e.g., politician speeches or party manifestos). Existing models scale texts based on relative word usage and cannot be used for cross-lingual analyses. Additionally, there is little quantitative evidence that the output of these models correlates with common political dimensions like left-to-right orientation. Experimental results show that the semantically-informed scaling models better predict the party positions than the existing word-based models in two different political dimensions. Furthermore, the proposed models exhibit no drop in performance in the cross-lingual compared to monolingual setting. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2109/ |
| https://www.aclweb.org/anthology/E17-2109 | |
| PWC | https://paperswithcode.com/paper/unsupervised-cross-lingual-scaling-of |
| Repo | |
| Framework | |
Prediction under Uncertainty in Sparse Spectrum Gaussian Processes with Applications to Filtering and Control
| Title | Prediction under Uncertainty in Sparse Spectrum Gaussian Processes with Applications to Filtering and Control |
| Authors | Yunpeng Pan, Xinyan Yan, Evangelos A. Theodorou, Byron Boots |
| Abstract | Sparse Spectrum Gaussian Processes (SSGPs) are a powerful tool for scaling Gaussian processes (GPs) to large datasets. Existing SSGP algorithms for regression assume deterministic inputs, precluding their use in many real-world robotics and engineering applications where accounting for input uncertainty is crucial. We address this problem by proposing two analytic moment-based approaches with closed-form expressions for SSGP regression with uncertain inputs. Our methods are more general and scalable than their standard GP counterparts, and are naturally applicable to multi-step prediction or uncertainty propagation. We show that efficient algorithms for Bayesian filtering and stochastic model predictive control can use these methods, and we evaluate our algorithms with comparative analyses and both real-world and simulated experiments. |
| Tasks | Gaussian Processes |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=786 |
| http://proceedings.mlr.press/v70/pan17a/pan17a.pdf | |
| PWC | https://paperswithcode.com/paper/prediction-under-uncertainty-in-sparse |
| Repo | |
| Framework | |
Understanding human values and their emotional effect
| Title | Understanding human values and their emotional effect |
| Authors | Alex Balahur, ra |
| Abstract | Emotions can be triggered by various factors. According to the Appraisal Theories (De Rivera, 1977; Frijda, 1986; Ortony et al., 1988; Johnson-Laird and Oatley, 1989) emotions are elicited and differentiated on the basis of the cognitive evaluation of the personal significance of a situation, object or event based on {``}appraisal criteria{''} (intrinsic characteristics of objects and events, significance of events to individual needs and goals, individual{'}s ability to cope with the consequences of the event, compatibility of event with social or personal standards, norms and values). These differences in values can trigger reactions such as anger, disgust (contempt), sadness, etc., because these behaviors are evaluated by the public as being incompatible with their social/personal standards, norms or values. Such arguments are frequently present both in mainstream media, as well as social media, building a society-wide view, attitude and emotional reaction towards refugees/immigrants. In this demo, I will talk about experiments to annotate and detect factual arguments that are linked to human needs/motivations from text and in consequence trigger emotion in the media audience and propose a new task for next year{'}s WASSA. | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5214/ |
| https://www.aclweb.org/anthology/W17-5214 | |
| PWC | https://paperswithcode.com/paper/understanding-human-values-and-their |
| Repo | |
| Framework | |
