Paper Group ANR 648
Towards Quantification of Explainability in Explainable Artificial Intelligence Methods. Clustering Time-Series by a Novel Slope-Based Similarity Measure Considering Particle Swarm Optimization. Frowning Frodo, Wincing Leia, and a Seriously Great Friendship: Learning to Classify Emotional Relationships of Fictional Characters. Learning Task-Oriente …
Towards Quantification of Explainability in Explainable Artificial Intelligence Methods
| Title | Towards Quantification of Explainability in Explainable Artificial Intelligence Methods |
| Authors | Sheikh Rabiul Islam, William Eberle, Sheikh K. Ghafoor |
| Abstract | Artificial Intelligence (AI) has become an integral part of domains such as security, finance, healthcare, medicine, and criminal justice. Explaining the decisions of AI systems in human terms is a key challenge–due to the high complexity of the model, as well as the potential implications on human interests, rights, and lives . While Explainable AI is an emerging field of research, there is no consensus on the definition, quantification, and formalization of explainability. In fact, the quantification of explainability is an open challenge. In our previous work, we incorporated domain knowledge for better explainability, however, we were unable to quantify the extent of explainability. In this work, we (1) briefly analyze the definitions of explainability from the perspective of different disciplines (e.g., psychology, social science), properties of explanation, explanation methods, and human-friendly explanations; and (2) propose and formulate an approach to quantify the extent of explainability. Our experimental result suggests a reasonable and model-agnostic way to quantify explainability |
| Tasks | |
| Published | 2019-11-22 |
| URL | https://arxiv.org/abs/1911.10104v1 |
| https://arxiv.org/pdf/1911.10104v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-quantification-of-explainability-in |
| Repo | |
| Framework | |
Clustering Time-Series by a Novel Slope-Based Similarity Measure Considering Particle Swarm Optimization
| Title | Clustering Time-Series by a Novel Slope-Based Similarity Measure Considering Particle Swarm Optimization |
| Authors | Hossein Kamalzadeh, Abbas Ahmadi, Saeed Mansour |
| Abstract | Recently there has been an increase in the studies on time-series data mining specifically time-series clustering due to the vast existence of time-series in various domains. The large volume of data in the form of time-series makes it necessary to employ various techniques such as clustering to understand the data and to extract information and hidden patterns. In the field of clustering specifically, time-series clustering, the most important aspects are the similarity measure used and the algorithm employed to conduct the clustering. In this paper, a new similarity measure for time-series clustering is developed based on a combination of a simple representation of time-series, slope of each segment of time-series, Euclidean distance and the so-called dynamic time warping. It is proved in this paper that the proposed distance measure is metric and thus indexing can be applied. For the task of clustering, the Particle Swarm Optimization algorithm is employed. The proposed similarity measure is compared to three existing measures in terms of various criteria used for the evaluation of clustering algorithms. The results indicate that the proposed similarity measure outperforms the rest in almost every dataset used in this paper. |
| Tasks | Time Series, Time Series Clustering |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.02405v1 |
| https://arxiv.org/pdf/1912.02405v1.pdf | |
| PWC | https://paperswithcode.com/paper/clustering-time-series-by-a-novel-slope-based |
| Repo | |
| Framework | |
Frowning Frodo, Wincing Leia, and a Seriously Great Friendship: Learning to Classify Emotional Relationships of Fictional Characters
| Title | Frowning Frodo, Wincing Leia, and a Seriously Great Friendship: Learning to Classify Emotional Relationships of Fictional Characters |
| Authors | Evgeny Kim, Roman Klinger |
| Abstract | The development of a fictional plot is centered around characters who closely interact with each other forming dynamic social networks. In literature analysis, such networks have mostly been analyzed without particular relation types or focusing on roles which the characters take with respect to each other. We argue that an important aspect for the analysis of stories and their development is the emotion between characters. In this paper, we combine these aspects into a unified framework to classify emotional relationships of fictional characters. We formalize it as a new task and describe the annotation of a corpus, based on fan-fiction short stories. The extraction pipeline which we propose consists of character identification (which we treat as given by an oracle here) and the relation classification. For the latter, we provide results using several approaches previously proposed for relation identification with neural methods. The best result of 0.45 F1 is achieved with a GRU with character position indicators on the task of predicting undirected emotion relations in the associated social network graph. |
| Tasks | Relation Classification |
| Published | 2019-03-29 |
| URL | http://arxiv.org/abs/1903.12453v2 |
| http://arxiv.org/pdf/1903.12453v2.pdf | |
| PWC | https://paperswithcode.com/paper/frowning-frodo-wincing-leia-and-a-seriously |
| Repo | |
| Framework | |
Learning Task-Oriented Grasping from Human Activity Datasets
| Title | Learning Task-Oriented Grasping from Human Activity Datasets |
| Authors | Mia Kokic, Danica Kragic, Jeannette Bohg |
| Abstract | We propose to leverage a real-world, human activity RGB datasets to teach a robot {\em Task-Oriented Grasping} (TOG). On the one hand, RGB-D datasets that contain hands and objects in interaction often lack annotations due to the manual effort in obtaining them. On the other hand, RGB datasets are often annotated with labels that do not provide enough information to infer a 6D robotic grasp pose. However, they contain examples of grasps on a variety of objects for many different tasks. Thereby, they provide a much richer source of supervision than RGB-D datasets. We propose a model that takes as input an RGB image and outputs a hand pose and configuration as well as an object pose and a shape. We follow the insight that jointly estimating hand and object poses increases accuracy compared to estimating these quantities independently of each other. Quantitative experiments show that training an object pose predictor with the hand pose information (and vice versa) is better than training without this information. Given the trained model, we process an RGB dataset to automatically obtain training data for a TOG model. This model takes as input an object point cloud and a task and outputs a suitable region for grasping, given the task. Qualitative experiments show that our model can successfully process a real-world dataset. Experiments with a robot demonstrate that this data allows a robot to learn task-oriented grasping on novel objects. |
| Tasks | |
| Published | 2019-10-25 |
| URL | https://arxiv.org/abs/1910.11669v1 |
| https://arxiv.org/pdf/1910.11669v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-task-oriented-grasping-from-human |
| Repo | |
| Framework | |
Chinese Named Entity Recognition Augmented with Lexicon Memory
| Title | Chinese Named Entity Recognition Augmented with Lexicon Memory |
| Authors | Yi Zhou, Xiaoqing Zheng, Xuanjing Huang |
| Abstract | Inspired by a concept of content-addressable retrieval from cognitive science, we propose a novel fragment-based model augmented with a lexicon-based memory for Chinese NER, in which both the character-level and word-level features are combined to generate better feature representations for possible name candidates. It is observed that locating the boundary information of entity names is useful in order to classify them into pre-defined categories. Position-dependent features, including prefix and suffix are introduced for NER in the form of distributed representation. The lexicon-based memory is used to help generate such position-dependent features and deal with the problem of out-of-vocabulary words. Experimental results showed that the proposed model, called LEMON, achieved state-of-the-art on four datasets. |
| Tasks | Chinese Named Entity Recognition, Named Entity Recognition |
| Published | 2019-12-17 |
| URL | https://arxiv.org/abs/1912.08282v1 |
| https://arxiv.org/pdf/1912.08282v1.pdf | |
| PWC | https://paperswithcode.com/paper/chinese-named-entity-recognition-augmented |
| Repo | |
| Framework | |
What Should I Ask? Using Conversationally Informative Rewards for Goal-Oriented Visual Dialog
| Title | What Should I Ask? Using Conversationally Informative Rewards for Goal-Oriented Visual Dialog |
| Authors | Pushkar Shukla, Carlos Elmadjian, Richika Sharan, Vivek Kulkarni, Matthew Turk, William Yang Wang |
| Abstract | The ability to engage in goal-oriented conversations has allowed humans to gain knowledge, reduce uncertainty, and perform tasks more efficiently. Artificial agents, however, are still far behind humans in having goal-driven conversations. In this work, we focus on the task of goal-oriented visual dialogue, aiming to automatically generate a series of questions about an image with a single objective. This task is challenging since these questions must not only be consistent with a strategy to achieve a goal, but also consider the contextual information in the image. We propose an end-to-end goal-oriented visual dialogue system, that combines reinforcement learning with regularized information gain. Unlike previous approaches that have been proposed for the task, our work is motivated by the Rational Speech Act framework, which models the process of human inquiry to reach a goal. We test the two versions of our model on the GuessWhat?! dataset, obtaining significant results that outperform the current state-of-the-art models in the task of generating questions to find an undisclosed object in an image. |
| Tasks | Visual Dialog |
| Published | 2019-07-28 |
| URL | https://arxiv.org/abs/1907.12021v1 |
| https://arxiv.org/pdf/1907.12021v1.pdf | |
| PWC | https://paperswithcode.com/paper/what-should-i-ask-using-conversationally-1 |
| Repo | |
| Framework | |
Graph Convolutional Networks for Road Networks
| Title | Graph Convolutional Networks for Road Networks |
| Authors | Tobias Skovgaard Jepsen, Christian S. Jensen, Thomas Dyhre Nielsen |
| Abstract | Machine learning techniques for road networks hold the potential to facilitate many important transportation applications. Graph Convolutional Networks (GCNs) are neural networks that are capable of leveraging the structure of a road network by utilizing information of, e.g., adjacent road segments. While state-of-the-art GCNs target node classification tasks in social, citation, and biological networks, machine learning tasks in road networks differ substantially from such tasks. In road networks, prediction tasks concern edges representing road segments, and many tasks involve regression. In addition, road networks differ substantially from the networks assumed in the GCN literature in terms of the attribute information available and the network characteristics. Many implicit assumptions of GCNs do therefore not apply. We introduce the notion of Relational Fusion Network (RFN), a novel type of GCN designed specifically for machine learning on road networks. In particular, we propose methods that outperform state-of-the-art GCNs on both a road segment regression task and a road segment classification task by 32-40% and 21-24%, respectively. In addition, we provide experimental evidence of the short-comings of state-of-the-art GCNs in the context of road networks: unlike our method, they cannot effectively leverage the road network structure for road segment classification and fail to outperform a regular multi-layer perceptron. |
| Tasks | Node Classification |
| Published | 2019-08-30 |
| URL | https://arxiv.org/abs/1908.11567v2 |
| https://arxiv.org/pdf/1908.11567v2.pdf | |
| PWC | https://paperswithcode.com/paper/graph-convolutional-networks-for-road |
| Repo | |
| Framework | |
Advanced Customer Activity Prediction based on Deep Hierarchic Encoder-Decoders
| Title | Advanced Customer Activity Prediction based on Deep Hierarchic Encoder-Decoders |
| Authors | Andrei Damian, Laurentiu Piciu, Sergiu Turlea, Nicolae Tapus |
| Abstract | Product recommender systems and customer profiling techniques have always been a priority in online retail. Recent machine learning research advances and also wide availability of massive parallel numerical computing has enabled various approaches and directions of recommender systems advancement. Worth to mention is the fact that in past years multiple traditional “offline” retail business are gearing more and more towards employing inferential and even predictive analytics both to stock-related problems such as predictive replenishment but also to enrich customer interaction experience. One of the most important areas of recommender systems research and development is that of Deep Learning based models which employ representational learning to model consumer behavioral patterns. Current state of the art in Deep Learning based recommender systems uses multiple approaches ranging from already classical methods such as the ones based on learning product representation vector, to recurrent analysis of customer transactional time-series and up to generative models based on adversarial training. Each of these methods has multiple advantages and inherent weaknesses such as inability of understanding the actual user-journey, ability to propose only single product recommendation or top-k product recommendations without prediction of actual next-best-offer. In our work we will present a new and innovative architectural approach of applying state-of-the-art hierarchical multi-module encoder-decoder architecture in order to solve several of current state-of-the-art recommender systems issues. Our approach will also produce by-products such as product need-based segmentation and customer behavioral segmentation - all in an end-to-end trainable approach. Finally, we will present a couple methods that solve known retail & distribution pain-points based on the proposed architecture. |
| Tasks | Activity Prediction, Product Recommendation, Recommendation Systems, Time Series |
| Published | 2019-04-11 |
| URL | https://arxiv.org/abs/1904.07687v4 |
| https://arxiv.org/pdf/1904.07687v4.pdf | |
| PWC | https://paperswithcode.com/paper/advanced-customer-activity-prediction-based |
| Repo | |
| Framework | |
Modular Meta-Learning with Shrinkage
| Title | Modular Meta-Learning with Shrinkage |
| Authors | Yutian Chen, Abram L. Friesen, Feryal Behbahani, Arnaud Doucet, David Budden, Matthew W. Hoffman, Nando de Freitas |
| Abstract | The modular nature of deep networks allows some components to learn general features, while others learn more task-specific features. When a deep model is then fine-tuned on a new task, each component adapts differently. For example, the input layers of an image classification convnet typically adapt very little, while the output layers may change significantly. However, standard meta-learning approaches ignore this variability and either adapt all modules equally or hand-pick a subset to adapt. This can result in overfitting and wasted computation during adaptation. In this work, we develop techniques based on Bayesian shrinkage to meta-learn how task-independent each module is and to regularize it accordingly. We show that various recent meta-learning algorithms, such as MAML and Reptile, are special cases of our formulation in the limit of no regularization. Empirically, our approach discovers a small subset of modules to adapt, and improves performance. Notably, our method finds that the final layer is not always the best layer to adapt, contradicting standard practices in the literature. |
| Tasks | Image Classification, Meta-Learning |
| Published | 2019-09-12 |
| URL | https://arxiv.org/abs/1909.05557v2 |
| https://arxiv.org/pdf/1909.05557v2.pdf | |
| PWC | https://paperswithcode.com/paper/modular-meta-learning-with-shrinkage |
| Repo | |
| Framework | |
Applying Active Diagnosis to Space Systems by On-Board Control Procedures
| Title | Applying Active Diagnosis to Space Systems by On-Board Control Procedures |
| Authors | Elodie Chanthery, Louise Travé-Massuyès, Yannick Pencolé, Régis De Ferluc, Brice Dellandrea |
| Abstract | The instrumentation of real systems is often designed for control purposes and control inputs are designed to achieve nominal control objectives. Hence, the available measurements may not be sufficient to isolate faults with certainty and diagnoses are ambiguous. Active diagnosis formulates a planning problem to generate a sequence of actions that, applied to the system, enforce diagnosability and allow to iteratively refine ambiguous diagnoses. This paper analyses the requirements for applying active diagnosis to space systems and proposes ActHyDiag as an effective framework to solve this problem. It presents the results of applying ActHyDiag to a real space case study and of implementing the generated plans in the form of On-Board Control Procedures. The case study is a redundant Spacewire Network where up to 6 instruments, monitored and controlled by the on-board software hosted in the Satellite Management Unit, are transferring science data to a mass memory unit through Spacewire routers. Experiments have been conducted on a real physical benchmark developed by Thales Alenia Space and demonstrate the effectiveness of the plans proposed by ActHyDiag. |
| Tasks | |
| Published | 2019-03-05 |
| URL | http://arxiv.org/abs/1903.01710v1 |
| http://arxiv.org/pdf/1903.01710v1.pdf | |
| PWC | https://paperswithcode.com/paper/applying-active-diagnosis-to-space-systems-by |
| Repo | |
| Framework | |
Robust Named Entity Recognition with Truecasing Pretraining
| Title | Robust Named Entity Recognition with Truecasing Pretraining |
| Authors | Stephen Mayhew, Nitish Gupta, Dan Roth |
| Abstract | Although modern named entity recognition (NER) systems show impressive performance on standard datasets, they perform poorly when presented with noisy data. In particular, capitalization is a strong signal for entities in many languages, and even state of the art models overfit to this feature, with drastically lower performance on uncapitalized text. In this work, we address the problem of robustness of NER systems in data with noisy or uncertain casing, using a pretraining objective that predicts casing in text, or a truecaser, leveraging unlabeled data. The pretrained truecaser is combined with a standard BiLSTM-CRF model for NER by appending output distributions to character embeddings. In experiments over several datasets of varying domain and casing quality, we show that our new model improves performance in uncased text, even adding value to uncased BERT embeddings. Our method achieves a new state of the art on the WNUT17 shared task dataset. |
| Tasks | Named Entity Recognition |
| Published | 2019-12-15 |
| URL | https://arxiv.org/abs/1912.07095v1 |
| https://arxiv.org/pdf/1912.07095v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-named-entity-recognition-with |
| Repo | |
| Framework | |
Integrating Deep Learning with Logic Fusion for Information Extraction
| Title | Integrating Deep Learning with Logic Fusion for Information Extraction |
| Authors | Wenya Wang, Sinno Jialin Pan |
| Abstract | Information extraction (IE) aims to produce structured information from an input text, e.g., Named Entity Recognition and Relation Extraction. Various attempts have been proposed for IE via feature engineering or deep learning. However, most of them fail to associate the complex relationships inherent in the task itself, which has proven to be especially crucial. For example, the relation between 2 entities is highly dependent on their entity types. These dependencies can be regarded as complex constraints that can be efficiently expressed as logical rules. To combine such logic reasoning capabilities with learning capabilities of deep neural networks, we propose to integrate logical knowledge in the form of first-order logic into a deep learning system, which can be trained jointly in an end-to-end manner. The integrated framework is able to enhance neural outputs with knowledge regularization via logic rules, and at the same time update the weights of logic rules to comply with the characteristics of the training data. We demonstrate the effectiveness and generalization of the proposed model on multiple IE tasks. |
| Tasks | Feature Engineering, Named Entity Recognition, Relation Extraction |
| Published | 2019-12-06 |
| URL | https://arxiv.org/abs/1912.03041v1 |
| https://arxiv.org/pdf/1912.03041v1.pdf | |
| PWC | https://paperswithcode.com/paper/integrating-deep-learning-with-logic-fusion |
| Repo | |
| Framework | |
AI and Accessibility: A Discussion of Ethical Considerations
| Title | AI and Accessibility: A Discussion of Ethical Considerations |
| Authors | Meredith Ringel Morris |
| Abstract | According to the World Health Organization, more than one billion people worldwide have disabilities. The field of disability studies defines disability through a social lens; people are disabled to the extent that society creates accessibility barriers. AI technologies offer the possibility of removing many accessibility barriers; for example, computer vision might help people who are blind better sense the visual world, speech recognition and translation technologies might offer real time captioning for people who are hard of hearing, and new robotic systems might augment the capabilities of people with limited mobility. Considering the needs of users with disabilities can help technologists identify high-impact challenges whose solutions can advance the state of AI for all users; however, ethical challenges such as inclusivity, bias, privacy, error, expectation setting, simulated data, and social acceptability must be considered. |
| Tasks | Speech Recognition |
| Published | 2019-08-21 |
| URL | https://arxiv.org/abs/1908.08939v2 |
| https://arxiv.org/pdf/1908.08939v2.pdf | |
| PWC | https://paperswithcode.com/paper/ai-and-accessibility-a-discussion-of-ethical |
| Repo | |
| Framework | |
Multimodal Generative Models for Compositional Representation Learning
| Title | Multimodal Generative Models for Compositional Representation Learning |
| Authors | Mike Wu, Noah Goodman |
| Abstract | As deep neural networks become more adept at traditional tasks, many of the most exciting new challenges concern multimodality—observations that combine diverse types, such as image and text. In this paper, we introduce a family of multimodal deep generative models derived from variational bounds on the evidence (data marginal likelihood). As part of our derivation we find that many previous multimodal variational autoencoders used objectives that do not correctly bound the joint marginal likelihood across modalities. We further generalize our objective to work with several types of deep generative model (VAE, GAN, and flow-based), and allow use of different model types for different modalities. We benchmark our models across many image, label, and text datasets, and find that our multimodal VAEs excel with and without weak supervision. Additional improvements come from use of GAN image models with VAE language models. Finally, we investigate the effect of language on learned image representations through a variety of downstream tasks, such as compositionally, bounding box prediction, and visual relation prediction. We find evidence that these image representations are more abstract and compositional than equivalent representations learned from only visual data. |
| Tasks | Representation Learning |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/1912.05075v1 |
| https://arxiv.org/pdf/1912.05075v1.pdf | |
| PWC | https://paperswithcode.com/paper/multimodal-generative-models-for |
| Repo | |
| Framework | |
Leveraging Experience in Lazy Search
| Title | Leveraging Experience in Lazy Search |
| Authors | Mohak Bhardwaj, Sanjiban Choudhury, Byron Boots, Siddhartha Srinivasa |
| Abstract | Lazy graph search algorithms are efficient at solving motion planning problems where edge evaluation is the computational bottleneck. These algorithms work by lazily computing the shortest potentially feasible path, evaluating edges along that path, and repeating until a feasible path is found. The order in which edges are selected is critical to minimizing the total number of edge evaluations: a good edge selector chooses edges that are not only likely to be invalid, but also eliminates future paths from consideration. We wish to learn such a selector by leveraging prior experience. We formulate this problem as a Markov Decision Process (MDP) on the state of the search problem. While solving this large MDP is generally intractable, we show that we can compute oracular selectors that can solve the MDP during training. With access to such oracles, we use imitation learning to find effective policies. If new search problems are sufficiently similar to problems solved during training, the learned policy will choose a good edge evaluation ordering and solve the motion planning problem quickly. We evaluate our algorithms on a wide range of 2D and 7D problems and show that the learned selector outperforms baseline commonly used heuristics. |
| Tasks | Imitation Learning, Motion Planning |
| Published | 2019-07-16 |
| URL | https://arxiv.org/abs/1907.07238v1 |
| https://arxiv.org/pdf/1907.07238v1.pdf | |
| PWC | https://paperswithcode.com/paper/leveraging-experience-in-lazy-search |
| Repo | |
| Framework | |
