Paper Group ANR 1361
Lattice-Based Transformer Encoder for Neural Machine Translation. Multi-Granularity Reasoning for Social Relation Recognition from Images. Neural Networks for Lorenz Map Prediction: A Trip Through Time. Measuring Social Bias in Knowledge Graph Embeddings. A Dataset Schema for Cooperative Learning from Demonstration in Multi-robots Systems. Deep-dus …
Lattice-Based Transformer Encoder for Neural Machine Translation
| Title | Lattice-Based Transformer Encoder for Neural Machine Translation |
| Authors | Fengshun Xiao, Jiangtong Li, Hai Zhao, Rui Wang, Kehai Chen |
| Abstract | Neural machine translation (NMT) takes deterministic sequences for source representations. However, either word-level or subword-level segmentations have multiple choices to split a source sequence with different word segmentors or different subword vocabulary sizes. We hypothesize that the diversity in segmentations may affect the NMT performance. To integrate different segmentations with the state-of-the-art NMT model, Transformer, we propose lattice-based encoders to explore effective word or subword representation in an automatic way during training. We propose two methods: 1) lattice positional encoding and 2) lattice-aware self-attention. These two methods can be used together and show complementary to each other to further improve translation performance. Experiment results show superiorities of lattice-based encoders in word-level and subword-level representations over conventional Transformer encoder. |
| Tasks | Machine Translation |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.01282v1 |
| https://arxiv.org/pdf/1906.01282v1.pdf | |
| PWC | https://paperswithcode.com/paper/lattice-based-transformer-encoder-for-neural |
| Repo | |
| Framework | |
Multi-Granularity Reasoning for Social Relation Recognition from Images
| Title | Multi-Granularity Reasoning for Social Relation Recognition from Images |
| Authors | Meng Zhang, Xinchen Liu, Wu Liu, Anfu Zhou, Huadong Ma, Tao Mei |
| Abstract | Discovering social relations in images can make machines better interpret the behavior of human beings. However, automatically recognizing social relations in images is a challenging task due to the significant gap between the domains of visual content and social relation. Existing studies separately process various features such as faces expressions, body appearance, and contextual objects, thus they cannot comprehensively capture the multi-granularity semantics, such as scenes, regional cues of persons, and interactions among persons and objects. To bridge the domain gap, we propose a Multi-Granularity Reasoning framework for social relation recognition from images. The global knowledge and mid-level details are learned from the whole scene and the regions of persons and objects, respectively. Most importantly, we explore the fine-granularity pose keypoints of persons to discover the interactions among persons and objects. Specifically, the pose-guided Person-Object Graph and Person-Pose Graph are proposed to model the actions from persons to object and the interactions between paired persons, respectively. Based on the graphs, social relation reasoning is performed by graph convolutional networks. Finally, the global features and reasoned knowledge are integrated as a comprehensive representation for social relation recognition. Extensive experiments on two public datasets show the effectiveness of the proposed framework. |
| Tasks | |
| Published | 2019-01-10 |
| URL | http://arxiv.org/abs/1901.03067v1 |
| http://arxiv.org/pdf/1901.03067v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-granularity-reasoning-for-social |
| Repo | |
| Framework | |
Neural Networks for Lorenz Map Prediction: A Trip Through Time
| Title | Neural Networks for Lorenz Map Prediction: A Trip Through Time |
| Authors | Denisa Roberts |
| Abstract | In this article the Lorenz dynamical system is revived and revisited and the current state of the art results for one step ahead forecasting for the Lorenz trajectories are published. The article is a reflection upon the evolution of neural networks with regards to the prediction performance on this canonical task. |
| Tasks | |
| Published | 2019-03-18 |
| URL | https://arxiv.org/abs/1903.07768v4 |
| https://arxiv.org/pdf/1903.07768v4.pdf | |
| PWC | https://paperswithcode.com/paper/lorenz-trajectories-prediction-travel-through |
| Repo | |
| Framework | |
Measuring Social Bias in Knowledge Graph Embeddings
| Title | Measuring Social Bias in Knowledge Graph Embeddings |
| Authors | Joseph Fisher |
| Abstract | It has recently been shown that word embeddings encode social biases, with a harmful impact on downstream tasks. However, to this point there has been no similar work done in the field of graph embeddings. We present the first study on social bias in knowledge graph embeddings, and propose a new metric suitable for measuring such bias. We conduct experiments on Wikidata and Freebase, and show that, as with word embeddings, harmful social biases related to professions are encoded in the embeddings with respect to gender, religion, ethnicity and nationality. For example, graph embeddings encode the information that men are more likely to be bankers, and women more likely to be homekeepers. As graph embeddings become increasingly utilized, we suggest that it is important the existence of such biases are understood and steps taken to mitigate their impact. |
| Tasks | Knowledge Graph Embeddings, Word Embeddings |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.02761v1 |
| https://arxiv.org/pdf/1912.02761v1.pdf | |
| PWC | https://paperswithcode.com/paper/measuring-social-bias-in-knowledge-graph |
| Repo | |
| Framework | |
A Dataset Schema for Cooperative Learning from Demonstration in Multi-robots Systems
| Title | A Dataset Schema for Cooperative Learning from Demonstration in Multi-robots Systems |
| Authors | Marco A. C. Simões, Robson Marinho da Silva, Tatiane Nogueira |
| Abstract | Multi-Agent Systems (MASs) have been used to solve complex problems that demand intelligent agents working together to reach the desired goals. These Agents should effectively synchronize their individual behaviors so that they can act as a team in a coordinated manner to achieve the common goal of the whole system. One of the main issues in MASs is the agents’ coordination, being common domain experts observing MASs execution disapprove agents’ decisions. Even if the MAS was designed using the best methods and tools for agents’ coordination, this difference of decisions between experts and MAS is confirmed. Therefore, this paper proposes a new dataset schema to support learning the coordinated behavior in MASs from demonstration. The results of the proposed solution are validated in a Multi-Robot System (MRS) organizing a collection of new cooperative plans recommendations from the demonstration by domain experts. |
| Tasks | |
| Published | 2019-12-03 |
| URL | https://arxiv.org/abs/1912.01741v1 |
| https://arxiv.org/pdf/1912.01741v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-dataset-schema-for-cooperative-learning |
| Repo | |
| Framework | |
Deep-dust: Predicting concentrations of fine dust in Seoul using LSTM
| Title | Deep-dust: Predicting concentrations of fine dust in Seoul using LSTM |
| Authors | Sookyung Kim, Jungmin M. Lee, Jiwoo Lee, Jihoon Seo |
| Abstract | Polluting fine dusts in South Korea which are mainly consisted of biomass burning and fugitive dust blown from dust belt is significant problem these days. Predicting concentrations of fine dust particles in Seoul is challenging because they are product of complicate chemical reactions among gaseous pollutants and also influenced by dynamical interactions between pollutants and multiple climate variables. Elaborating state-of-art time series analysis techniques using deep learning, non-linear interactions between multiple variables can be captured and used to predict future dust concentration. In this work, we propose the LSTM based model to predict hourly concentration of fine dust at target location in Seoul based on previous concentration of pollutants, dust concentrations and climate variables in surrounding area. Our results show that proposed model successfully predicts future dust concentrations at 25 target districts(Gu) in Seoul. |
| Tasks | Time Series, Time Series Analysis |
| Published | 2019-01-29 |
| URL | http://arxiv.org/abs/1901.10106v1 |
| http://arxiv.org/pdf/1901.10106v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-dust-predicting-concentrations-of-fine |
| Repo | |
| Framework | |
Accurate Nuclear Segmentation with Center Vector Encoding
| Title | Accurate Nuclear Segmentation with Center Vector Encoding |
| Authors | Jiahui Li, Zhiqiang Hu, Shuang Yang |
| Abstract | Nuclear segmentation is important and frequently demanded for pathology image analysis, yet is also challenging due to nuclear crowdedness and possible occlusion. In this paper, we present a novel bottom-up method for nuclear segmentation. The concepts of Center Mask and Center Vector are introduced to better depict the relationship between pixels and nuclear instances. The instance differentiation process are thus largely simplified and easier to understand. Experiments demonstrate the effectiveness of Center Vector Encoding, where our method outperforms state-of-the-arts by a clear margin. |
| Tasks | Nuclear Segmentation |
| Published | 2019-07-09 |
| URL | https://arxiv.org/abs/1907.03951v2 |
| https://arxiv.org/pdf/1907.03951v2.pdf | |
| PWC | https://paperswithcode.com/paper/accurate-nuclear-segmentation-with-center |
| Repo | |
| Framework | |
A new approach for query expansion using Wikipedia and WordNet
| Title | A new approach for query expansion using Wikipedia and WordNet |
| Authors | Hiteshwar Kumar Azad, Akshay Deepak |
| Abstract | Query expansion (QE) is a well-known technique used to enhance the effectiveness of information retrieval. QE reformulates the initial query by adding similar terms that help in retrieving more relevant results. Several approaches have been proposed in literature producing quite favorable results, but they are not evenly favorable for all types of queries (individual and phrase queries). One of the main reasons for this is the use of the same kind of data sources and weighting scheme while expanding both the individual and the phrase query terms. As a result, the holistic relationship among the query terms is not well captured or scored. To address this issue, we have presented a new approach for QE using Wikipedia and WordNet as data sources. Specifically, Wikipedia gives rich expansion terms for phrase terms, while WordNet does the same for individual terms. We have also proposed novel weighting schemes for expansion terms: in-link score (for terms extracted from Wikipedia) and a tf-idf based scheme (for terms extracted from WordNet). In the proposed Wikipedia-WordNet-based QE technique (WWQE), we weigh the expansion terms twice: first, they are scored by the weighting scheme individually, and then, the weighting scheme scores the selected expansion terms concerning the entire query using correlation score. The proposed approach gains improvements of 24% on the MAP score and 48% on the GMAP score over unexpanded queries on the FIRE dataset. Experimental results achieve a significant improvement over individual expansion and other related state-of-the-art approaches. We also analyzed the effect on retrieval effectiveness of the proposed technique by varying the number of expansion terms. |
| Tasks | Information Retrieval |
| Published | 2019-01-29 |
| URL | https://arxiv.org/abs/1901.10197v2 |
| https://arxiv.org/pdf/1901.10197v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-new-approach-for-query-expansion-using |
| Repo | |
| Framework | |
Optimal multiclass overfitting by sequence reconstruction from Hamming queries
| Title | Optimal multiclass overfitting by sequence reconstruction from Hamming queries |
| Authors | Jayadev Acharya, Ananda Theertha Suresh |
| Abstract | A primary concern of excessive reuse of test datasets in machine learning is that it can lead to overfitting. Multiclass classification was recently shown to be more resistant to overfitting than binary classification. In an open problem of COLT 2019, Feldman, Frostig, and Hardt ask to characterize the dependence of the amount of overfitting bias with the number of classes $m$, the number of accuracy queries $k$, and the number of examples in the dataset $n$. We resolve this problem and determine the amount of overfitting possible in multi-class classification. We provide computationally efficient algorithms that achieve overfitting bias of $\tilde{\Theta}(\max{\sqrt{{k}/{(mn)}}, k/n})$, matching the known upper bounds. |
| Tasks | |
| Published | 2019-08-08 |
| URL | https://arxiv.org/abs/1908.03156v2 |
| https://arxiv.org/pdf/1908.03156v2.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-multiclass-overfitting-by-sequence |
| Repo | |
| Framework | |
An Online Learning Approach to Model Predictive Control
| Title | An Online Learning Approach to Model Predictive Control |
| Authors | Nolan Wagener, Ching-An Cheng, Jacob Sacks, Byron Boots |
| Abstract | Model predictive control (MPC) is a powerful technique for solving dynamic control tasks. In this paper, we show that there exists a close connection between MPC and online learning, an abstract theoretical framework for analyzing online decision making in the optimization literature. This new perspective provides a foundation for leveraging powerful online learning algorithms to design MPC algorithms. Specifically, we propose a new algorithm based on dynamic mirror descent (DMD), an online learning algorithm that is designed for non-stationary setups. Our algorithm, Dynamic Mirror Descent Model Predictive Control (DMD-MPC), represents a general family of MPC algorithms that includes many existing techniques as special instances. DMD-MPC also provides a fresh perspective on previous heuristics used in MPC and suggests a principled way to design new MPC algorithms. In the experimental section of this paper, we demonstrate the flexibility of DMD-MPC, presenting a set of new MPC algorithms on a simple simulated cartpole and a simulated and real-world aggressive driving task. Videos of the real-world experiments can be found at https://youtu.be/vZST3v0_S9w and https://youtu.be/MhuqiHo2t98. |
| Tasks | Decision Making |
| Published | 2019-02-24 |
| URL | https://arxiv.org/abs/1902.08967v3 |
| https://arxiv.org/pdf/1902.08967v3.pdf | |
| PWC | https://paperswithcode.com/paper/an-online-learning-approach-to-model |
| Repo | |
| Framework | |
Online Trajectory Planning Through Combined Trajectory Optimization and Function Approximation: Application to the Exoskeleton Atalante
| Title | Online Trajectory Planning Through Combined Trajectory Optimization and Function Approximation: Application to the Exoskeleton Atalante |
| Authors | Alexis Duburcq, Yann Chevaleyre, Nicolas Bredeche, Guilhem Boéris |
| Abstract | Autonomous robots require online trajectory planning capability to operate in the real world. Efficient offline trajectory planning methods already exist, but are computationally demanding, preventing their use online. In this paper, we present a novel algorithm called Guided Trajectory Learning that learns a function approximation of solutions computed through trajectory optimization while ensuring accurate and reliable predictions. This function approximation is then used online to generate trajectories. This algorithm is designed to be easy to implement, and practical since it does not require massive computing power. It is readily applicable to any robotics systems and effortless to set up on real hardware since robust control strategies are usually already available. We demonstrate the computational performance of our algorithm on flat-foot walking with the self-balanced exoskeleton Atalante. |
| Tasks | |
| Published | 2019-10-01 |
| URL | https://arxiv.org/abs/1910.00514v3 |
| https://arxiv.org/pdf/1910.00514v3.pdf | |
| PWC | https://paperswithcode.com/paper/online-trajectory-planning-through-combined |
| Repo | |
| Framework | |
Fine-grained Sentiment Analysis with Faithful Attention
| Title | Fine-grained Sentiment Analysis with Faithful Attention |
| Authors | Ruiqi Zhong, Steven Shao, Kathleen McKeown |
| Abstract | While the general task of textual sentiment classification has been widely studied, much less research looks specifically at sentiment between a specified source and target. To tackle this problem, we experimented with a state-of-the-art relation extraction model. Surprisingly, we found that despite reasonable performance, the model’s attention was often systematically misaligned with the words that contribute to sentiment. Thus, we directly trained the model’s attention with human rationales and improved our model performance by a robust 4~8 points on all tasks we defined on our data sets. We also present a rigorous analysis of the model’s attention, both trained and untrained, using novel and intuitive metrics. Our results show that untrained attention does not provide faithful explanations; however, trained attention with concisely annotated human rationales not only increases performance, but also brings faithful explanations. Encouragingly, a small amount of annotated human rationales suffice to correct the attention in our task. |
| Tasks | Relation Extraction, Sentiment Analysis |
| Published | 2019-08-19 |
| URL | https://arxiv.org/abs/1908.06870v1 |
| https://arxiv.org/pdf/1908.06870v1.pdf | |
| PWC | https://paperswithcode.com/paper/fine-grained-sentiment-analysis-with-faithful |
| Repo | |
| Framework | |
Featured Snippets Results in Google Web Search: An Exploratory Study
| Title | Featured Snippets Results in Google Web Search: An Exploratory Study |
| Authors | Artur Strzelecki, Paulina Rutecka |
| Abstract | In this paper authors analyzed 163412 keywords and results with featured snippets collected from localized Polish Google search engine. A method-ology for retrieving data from Google search engine was proposed in terms of obtaining necessary data to study featured snippets. It was observed that almost half of featured snippets (48%) is taken from result on first ranking position. Furthermore, some correlations between prepositions and the most often appearing content words in keywords was discovered. Results show that featured snippets are often taken from trustworthy websites like e.g., Wikipedia and are mainly presented in form of a paragraph. Paragraph can be read by Google Assistant or Home Assistant with voice search. We conclude our findings with discussion and research limitations. |
| Tasks | |
| Published | 2019-07-10 |
| URL | https://arxiv.org/abs/1907.04891v3 |
| https://arxiv.org/pdf/1907.04891v3.pdf | |
| PWC | https://paperswithcode.com/paper/featured-snippets-results-in-google-web |
| Repo | |
| Framework | |
Transfer Learning for Performance Modeling of Deep Neural Network Systems
| Title | Transfer Learning for Performance Modeling of Deep Neural Network Systems |
| Authors | Md Shahriar Iqbal, Lars Kotthoff, Pooyan Jamshidi |
| Abstract | Modern deep neural network (DNN) systems are highly configurable with large a number of options that significantly affect their non-functional behavior, for example inference time and energy consumption. Performance models allow to understand and predict the effects of such configuration options on system behavior, but are costly to build because of large configuration spaces. Performance models from one environment cannot be transferred directly to another; usually models are rebuilt from scratch for different environments, for example different hardware. Recently, transfer learning methods have been applied to reuse knowledge from performance models trained in one environment in another. In this paper, we perform an empirical study to understand the effectiveness of different transfer learning strategies for building performance models of DNN systems. Our results show that transferring information on the most influential configuration options and their interactions is an effective way of reducing the cost to build performance models in new environments. |
| Tasks | Transfer Learning |
| Published | 2019-04-04 |
| URL | http://arxiv.org/abs/1904.02838v1 |
| http://arxiv.org/pdf/1904.02838v1.pdf | |
| PWC | https://paperswithcode.com/paper/transfer-learning-for-performance-modeling-of-2 |
| Repo | |
| Framework | |
Auxiliary Interference Speaker Loss for Target-Speaker Speech Recognition
| Title | Auxiliary Interference Speaker Loss for Target-Speaker Speech Recognition |
| Authors | Naoyuki Kanda, Shota Horiguchi, Ryoichi Takashima, Yusuke Fujita, Kenji Nagamatsu, Shinji Watanabe |
| Abstract | In this paper, we propose a novel auxiliary loss function for target-speaker automatic speech recognition (ASR). Our method automatically extracts and transcribes target speaker’s utterances from a monaural mixture of multiple speakers speech given a short sample of the target speaker. The proposed auxiliary loss function attempts to additionally maximize interference speaker ASR accuracy during training. This will regularize the network to achieve a better representation for speaker separation, thus achieving better accuracy on the target-speaker ASR. We evaluated our proposed method using two-speaker-mixed speech in various signal-to-interference-ratio conditions. We first built a strong target-speaker ASR baseline based on the state-of-the-art lattice-free maximum mutual information. This baseline achieved a word error rate (WER) of 18.06% on the test set while a normal ASR trained with clean data produced a completely corrupted result (WER of 84.71%). Then, our proposed loss further reduced the WER by 6.6% relative to this strong baseline, achieving a WER of 16.87%. In addition to the accuracy improvement, we also showed that the auxiliary output branch for the proposed loss can even be used for a secondary ASR for interference speakers’ speech. |
| Tasks | Speaker Separation, Speech Recognition |
| Published | 2019-06-26 |
| URL | https://arxiv.org/abs/1906.10876v1 |
| https://arxiv.org/pdf/1906.10876v1.pdf | |
| PWC | https://paperswithcode.com/paper/auxiliary-interference-speaker-loss-for |
| Repo | |
| Framework | |
