Paper Group ANR 501
Generative Counterfactual Introspection for Explainable Deep Learning. Hedging the Drift: Learning to Optimize under Non-Stationarity. TWEETQA: A Social Media Focused Question Answering Dataset. Optimization of Project Scheduling Activities in Dynamic CPM and PERT Networks Using Genetic Algorithms. An Ensemble Method for Producing Word Representati …
Generative Counterfactual Introspection for Explainable Deep Learning
| Title | Generative Counterfactual Introspection for Explainable Deep Learning |
| Authors | Shusen Liu, Bhavya Kailkhura, Donald Loveland, Yong Han |
| Abstract | In this work, we propose an introspection technique for deep neural networks that relies on a generative model to instigate salient editing of the input image for model interpretation. Such modification provides the fundamental interventional operation that allows us to obtain answers to counterfactual inquiries, i.e., what meaningful change can be made to the input image in order to alter the prediction. We demonstrate how to reveal interesting properties of the given classifiers by utilizing the proposed introspection approach on both the MNIST and the CelebA dataset. |
| Tasks | |
| Published | 2019-07-06 |
| URL | https://arxiv.org/abs/1907.03077v1 |
| https://arxiv.org/pdf/1907.03077v1.pdf | |
| PWC | https://paperswithcode.com/paper/generative-counterfactual-introspection-for |
| Repo | |
| Framework | |
Hedging the Drift: Learning to Optimize under Non-Stationarity
| Title | Hedging the Drift: Learning to Optimize under Non-Stationarity |
| Authors | Wang Chi Cheung, David Simchi-Levi, Ruihao Zhu |
| Abstract | We introduce data-driven decision-making algorithms that achieve state-of-the-art \emph{dynamic regret} bounds for non-stationary bandit settings. These settings capture applications such as advertisement allocation, dynamic pricing, and traffic network routing in changing environments. We show how the difficulty posed by the (unknown \emph{a priori} and possibly adversarial) non-stationarity can be overcome by an unconventional marriage between stochastic and adversarial bandit learning algorithms. Our main contribution is a general algorithmic recipe for a wide variety of non-stationary bandit problems. Specifically, we design and analyze the sliding window-upper confidence bound algorithm that achieves the optimal dynamic regret bound for each of the settings when we know the respective underlying \emph{variation budget}, which quantifies the total amount of temporal variation of the latent environments. Boosted by the novel bandit-over-bandit framework that adapts to the latent changes, we can further enjoy the (nearly) optimal dynamic regret bounds in a (surprisingly) parameter-free manner. In addition to the classical exploration-exploitation trade-off, our algorithms leverage the power of the ``forgetting principle” in the learning processes, which is vital in changing environments. Our extensive numerical experiments on both synthetic and real world online auto-loan datasets show that our proposed algorithms achieve superior empirical performance compared to existing algorithms. | |
| Tasks | Decision Making |
| Published | 2019-03-04 |
| URL | https://arxiv.org/abs/1903.01461v2 |
| https://arxiv.org/pdf/1903.01461v2.pdf | |
| PWC | https://paperswithcode.com/paper/hedging-the-drift-learning-to-optimize-under |
| Repo | |
| Framework | |
TWEETQA: A Social Media Focused Question Answering Dataset
| Title | TWEETQA: A Social Media Focused Question Answering Dataset |
| Authors | Wenhan Xiong, Jiawei Wu, Hong Wang, Vivek Kulkarni, Mo Yu, Shiyu Chang, Xiaoxiao Guo, William Yang Wang |
| Abstract | With social media becoming increasingly pop-ular on which lots of news and real-time eventsare reported, developing automated questionanswering systems is critical to the effective-ness of many applications that rely on real-time knowledge. While previous datasets haveconcentrated on question answering (QA) forformal text like news and Wikipedia, wepresent the first large-scale dataset for QA oversocial media data. To ensure that the tweetswe collected are useful, we only gather tweetsused by journalists to write news articles. Wethen ask human annotators to write questionsand answers upon these tweets. Unlike otherQA datasets like SQuAD in which the answersare extractive, we allow the answers to be ab-stractive. We show that two recently proposedneural models that perform well on formaltexts are limited in their performance when ap-plied to our dataset. In addition, even the fine-tuned BERT model is still lagging behind hu-man performance with a large margin. Our re-sults thus point to the need of improved QAsystems targeting social media text. |
| Tasks | Question Answering |
| Published | 2019-07-14 |
| URL | https://arxiv.org/abs/1907.06292v1 |
| https://arxiv.org/pdf/1907.06292v1.pdf | |
| PWC | https://paperswithcode.com/paper/tweetqa-a-social-media-focused-question |
| Repo | |
| Framework | |
Optimization of Project Scheduling Activities in Dynamic CPM and PERT Networks Using Genetic Algorithms
| Title | Optimization of Project Scheduling Activities in Dynamic CPM and PERT Networks Using Genetic Algorithms |
| Authors | Muhammed Hanefi Calp, Muhammet Ali Akcayol |
| Abstract | Projects consist of interconnected dimensions such as objective, time, resource and environment. Use of these dimensions in a controlled way and their effective scheduling brings the project success. Project scheduling process includes defining project activities, and estimation of time and resources to be used for the activities. At this point, the project resource-scheduling problems have begun to attract more attention after Program Evaluation and Review Technique (PERT) and Critical Path Method (CPM) are developed one after the other. However, complexity and difficulty of CPM and PERT processes led to the use of these techniques through artificial intelligence methods such as Genetic Algorithm (GA). In this study, an algorithm was proposed and developed, which determines critical path, critical activities and project completion duration by using GA, instead of CPM and PERT techniques used for network analysis within the scope of project management. The purpose of using GA was that these algorithms are an effective method for solution of complex optimization problems. Therefore, correct decisions can be made for implemented project activities by using obtained results. Thus, optimum results were obtained in a shorter time than the CPM and PERT techniques by using the model based on the dynamic algorithm. It is expected that this study will contribute to the performance field (time, speed, low error etc.) of other studies. |
| Tasks | |
| Published | 2019-02-02 |
| URL | http://arxiv.org/abs/1902.00659v1 |
| http://arxiv.org/pdf/1902.00659v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimization-of-project-scheduling-activities |
| Repo | |
| Framework | |
An Ensemble Method for Producing Word Representations for the Greek Language
| Title | An Ensemble Method for Producing Word Representations for the Greek Language |
| Authors | Michalis Lioudakis, Stamatis Outsios, Michalis Vazirgiannis |
| Abstract | In this paper we present a new ensemble method, Continuous Bag-of-Skip-grams (CBOS), that produces high-quality word representations for the Greek language. The CBOS method combines the pioneering approaches for learning word representations: Continuous Bag-of-Words (CBOW) and Continuous Skip-gram. These methods are compared through a word analogy task on three different sources of data: the English Wikipedia corpus, the Greek Wikipedia corpus, and the Greek Web Content corpus. By comparing these methods across different datasets, it is evident that the CBOS method achieves state-of-the-art performance. |
| Tasks | |
| Published | 2019-12-10 |
| URL | https://arxiv.org/abs/1912.04965v1 |
| https://arxiv.org/pdf/1912.04965v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-ensemble-method-for-producing-word |
| Repo | |
| Framework | |
Towards Safe Machine Learning for CPS: Infer Uncertainty from Training Data
| Title | Towards Safe Machine Learning for CPS: Infer Uncertainty from Training Data |
| Authors | Xiaozhe Gu, Arvind Easwaran |
| Abstract | Machine learning (ML) techniques are increasingly applied to decision-making and control problems in Cyber-Physical Systems among which many are safety-critical, e.g., chemical plants, robotics, autonomous vehicles. Despite the significant benefits brought by ML techniques, they also raise additional safety issues because 1) most expressive and powerful ML models are not transparent and behave as a black box and 2) the training data which plays a crucial role in ML safety is usually incomplete. An important technique to achieve safety for ML models is “Safe Fail”, i.e., a model selects a reject option and applies the backup solution, a traditional controller or a human operator for example, when it has low confidence in a prediction. Data-driven models produced by ML algorithms learn from training data, and hence they are only as good as the examples they have learnt. As pointed in [17], ML models work well in the “training space” (i.e., feature space with sufficient training data), but they could not extrapolate beyond the training space. As observed in many previous studies, a feature space that lacks training data generally has a much higher error rate than the one that contains sufficient training samples [31]. Therefore, it is essential to identify the training space and avoid extrapolating beyond the training space. In this paper, we propose an efficient Feature Space Partitioning Tree (FSPT) to address this problem. Using experiments, we also show that, a strong relationship exists between model performance and FSPT score. |
| Tasks | Autonomous Vehicles, Decision Making |
| Published | 2019-09-11 |
| URL | https://arxiv.org/abs/1909.04886v1 |
| https://arxiv.org/pdf/1909.04886v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-safe-machine-learning-for-cps-infer |
| Repo | |
| Framework | |
Interpretable Question Answering on Knowledge Bases and Text
| Title | Interpretable Question Answering on Knowledge Bases and Text |
| Authors | Alona Sydorova, Nina Poerner, Benjamin Roth |
| Abstract | Interpretability of machine learning (ML) models becomes more relevant with their increasing adoption. In this work, we address the interpretability of ML based question answering (QA) models on a combination of knowledge bases (KB) and text documents. We adapt post hoc explanation methods such as LIME and input perturbation (IP) and compare them with the self-explanatory attention mechanism of the model. For this purpose, we propose an automatic evaluation paradigm for explanation methods in the context of QA. We also conduct a study with human annotators to evaluate whether explanations help them identify better QA models. Our results suggest that IP provides better explanations than LIME or attention, according to both automatic and human evaluation. We obtain the same ranking of methods in both experiments, which supports the validity of our automatic evaluation paradigm. |
| Tasks | Question Answering |
| Published | 2019-06-26 |
| URL | https://arxiv.org/abs/1906.10924v1 |
| https://arxiv.org/pdf/1906.10924v1.pdf | |
| PWC | https://paperswithcode.com/paper/interpretable-question-answering-on-knowledge |
| Repo | |
| Framework | |
Iterative Policy-Space Expansion in Reinforcement Learning
| Title | Iterative Policy-Space Expansion in Reinforcement Learning |
| Authors | Jan Malte Lichtenberg, Özgür Şimşek |
| Abstract | Humans and animals solve a difficult problem much more easily when they are presented with a sequence of problems that starts simple and slowly increases in difficulty. We explore this idea in the context of reinforcement learning. Rather than providing the agent with an externally provided curriculum of progressively more difficult tasks, the agent solves a single task utilizing a decreasingly constrained policy space. The algorithm we propose first learns to categorize features into positive and negative before gradually learning a more refined policy. Experimental results in Tetris demonstrate superior learning rate of our approach when compared to existing algorithms. |
| Tasks | |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.02532v1 |
| https://arxiv.org/pdf/1912.02532v1.pdf | |
| PWC | https://paperswithcode.com/paper/iterative-policy-space-expansion-in |
| Repo | |
| Framework | |
Deep Learning-Based Quantification of Pulmonary Hemosiderophages in Cytology Slides
| Title | Deep Learning-Based Quantification of Pulmonary Hemosiderophages in Cytology Slides |
| Authors | Christian Marzahl, Marc Aubreville, Christof A. Bertram, Jason Stayt, Anne-Katherine Jasensky, Florian Bartenschlager, Marco Fragoso-Garcia, Ann K. Barton, Svenja Elsemann, Samir Jabari, Jens Krauth, Prathmesh Madhu, Jörn Voigt, Jenny Hill, Robert Klopfleisch, Andreas Maier |
| Abstract | Purpose: Exercise-induced pulmonary hemorrhage (EIPH) is a common syndrome in sport horses with negative impact on performance. Cytology of bronchoalveolar lavage fluid by use of a scoring system is considered the most sensitive diagnostic method. Macrophages are classified depending on the degree of cytoplasmic hemosiderin content. The current gold standard is manual grading, which is however monotonous and time-consuming. Methods: We evaluated state-of-the-art deep learning-based methods for single cell macrophage classification and compared them against the performance of nine cytology experts and evaluated inter- and intra-observer variability. Additionally, we evaluated object detection methods on a novel data set of 17 completely annotated cytology whole slide images (WSI) containing 78,047 hemosiderophages. Resultsf: Our deep learning-based approach reached a concordance of 0.85, partially exceeding human expert concordance (0.68 to 0.86, $\mu$=0.73, $\sigma$ =0.04). Intra-observer variability was high (0.68 to 0.88) and inter-observer concordance was moderate (Fleiss kappa = 0.67). Our object detection approach has a mean average precision of 0.66 over the five classes from the whole slide gigapixel image and a computation time of below two minutes. Conclusion: To mitigate the high inter- and intra-rater variability, we propose our automated object detection pipeline, enabling accurate, reproducible and quick EIPH scoring in WSI. |
| Tasks | Object Detection |
| Published | 2019-08-12 |
| URL | https://arxiv.org/abs/1908.04767v1 |
| https://arxiv.org/pdf/1908.04767v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-based-quantification-of |
| Repo | |
| Framework | |
ParaQG: A System for Generating Questions and Answers from Paragraphs
| Title | ParaQG: A System for Generating Questions and Answers from Paragraphs |
| Authors | Vishwajeet Kumar, Sivaanandh Muneeswaran, Ganesh Ramakrishnan, Yuan-Fang Li |
| Abstract | Generating syntactically and semantically valid and relevant questions from paragraphs is useful with many applications. Manual generation is a labour-intensive task, as it requires the reading, parsing and understanding of long passages of text. A number of question generation models based on sequence-to-sequence techniques have recently been proposed. Most of them generate questions from sentences only, and none of them is publicly available as an easy-to-use service. In this paper, we demonstrate ParaQG, a Web-based system for generating questions from sentences and paragraphs. ParaQG incorporates a number of novel functionalities to make the question generation process user-friendly. It provides an interactive interface for a user to select answers with visual insights on generation of questions. It also employs various faceted views to group similar questions as well as filtering techniques to eliminate unanswerable questions |
| Tasks | Question Generation |
| Published | 2019-09-04 |
| URL | https://arxiv.org/abs/1909.01642v1 |
| https://arxiv.org/pdf/1909.01642v1.pdf | |
| PWC | https://paperswithcode.com/paper/paraqg-a-system-for-generating-questions-and |
| Repo | |
| Framework | |
The Literary Theme Ontology for Media Annotation and Information Retrieval
| Title | The Literary Theme Ontology for Media Annotation and Information Retrieval |
| Authors | Paul Sheridan, Mikael Onsjö, Janna Hastings |
| Abstract | Literary theme identification and interpretation is a focal point of literary studies scholarship. Classical forms of literary scholarship, such as close reading, have flourished with scarcely any need for commonly defined literary themes. However, the rise in popularity of collaborative and algorithmic analyses of literary themes in works of fiction, together with a requirement for computational searching and indexing facilities for large corpora, creates the need for a collection of shared literary themes to ensure common terminology and definitions. To address this need, we here introduce a first draft of the Literary Theme Ontology. Inspired by a traditional framing from literary theory, the ontology comprises literary themes drawn from the authors own analyses, reference books, and online sources. The ontology is available at https://github.com/theme-ontology/lto under a Creative Commons Attribution 4.0 International license (CC BY 4.0). |
| Tasks | Information Retrieval |
| Published | 2019-05-01 |
| URL | https://arxiv.org/abs/1905.00522v2 |
| https://arxiv.org/pdf/1905.00522v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-literary-theme-ontology-for-media |
| Repo | |
| Framework | |
Concept Drift Adaptive Physical Event Detection for Social Media Streams
| Title | Concept Drift Adaptive Physical Event Detection for Social Media Streams |
| Authors | Abhijit Suprem, Aibek Musaev, Calton Pu |
| Abstract | Event detection has long been the domain of physical sensors operating in a static dataset assumption. The prevalence of social media and web access has led to the emergence of social, or human sensors who report on events globally. This warrants development of event detectors that can take advantage of the truly dense and high spatial and temporal resolution data provided by more than 3 billion social users. The phenomenon of concept drift, which causes terms and signals associated with a topic to change over time, renders static machine learning ineffective. Towards this end, we present an application for physical event detection on social sensors that improves traditional physical event detection with concept drift adaptation. Our approach continuously updates its machine learning classifiers automatically, without the need for human intervention. It integrates data from heterogeneous sources and is designed to handle weak-signal events (landslides, wildfires) with around ten posts per event in addition to large-signal events (hurricanes, earthquakes) with hundreds of thousands of posts per event. We demonstrate a landslide detector on our application that detects almost 350% more land-slides compared to static approaches. Our application has high performance: using classifiers trained in 2014, achieving event detection accuracy of 0.988, compared to 0.762 for static approaches. |
| Tasks | |
| Published | 2019-09-17 |
| URL | https://arxiv.org/abs/1911.05494v1 |
| https://arxiv.org/pdf/1911.05494v1.pdf | |
| PWC | https://paperswithcode.com/paper/concept-drift-adaptive-physical-event |
| Repo | |
| Framework | |
Tree-Structured Semantic Encoder with Knowledge Sharing for Domain Adaptation in Natural Language Generation
| Title | Tree-Structured Semantic Encoder with Knowledge Sharing for Domain Adaptation in Natural Language Generation |
| Authors | Bo-Hsiang Tseng, Paweł Budzianowski, Yen-Chen Wu, Milica Gašić |
| Abstract | Domain adaptation in natural language generation (NLG) remains challenging because of the high complexity of input semantics across domains and limited data of a target domain. This is particularly the case for dialogue systems, where we want to be able to seamlessly include new domains into the conversation. Therefore, it is crucial for generation models to share knowledge across domains for the effective adaptation from one domain to another. In this study, we exploit a tree-structured semantic encoder to capture the internal structure of complex semantic representations required for multi-domain dialogues in order to facilitate knowledge sharing across domains. In addition, a layer-wise attention mechanism between the tree encoder and the decoder is adopted to further improve the model’s capability. The automatic evaluation results show that our model outperforms previous methods in terms of the BLEU score and the slot error rate, in particular when the adaptation data is limited. In subjective evaluation, human judges tend to prefer the sentences generated by our model, rating them more highly on informativeness and naturalness than other systems. |
| Tasks | Domain Adaptation, Text Generation |
| Published | 2019-10-02 |
| URL | https://arxiv.org/abs/1910.06719v1 |
| https://arxiv.org/pdf/1910.06719v1.pdf | |
| PWC | https://paperswithcode.com/paper/tree-structured-semantic-encoder-with-1 |
| Repo | |
| Framework | |
DFSMN-SAN with Persistent Memory Model for Automatic Speech Recognition
| Title | DFSMN-SAN with Persistent Memory Model for Automatic Speech Recognition |
| Authors | Zhao You, Dan Su, Jie Chen, Chao Weng, Dong Yu |
| Abstract | Self-attention networks (SAN) have been introduced into automatic speech recognition (ASR) and achieved state-of-the-art performance owing to its superior ability in capturing long term dependency. One of the key ingredients is the self-attention mechanism which can be effectively performed on the whole utterance level. In this paper, we try to investigate whether even more information beyond the whole utterance level can be exploited and beneficial. We propose to apply self-attention layer with augmented memory to ASR. Specifically, we first propose a variant model architecture which combines deep feed-forward sequential memory network (DFSMN) with self-attention layers to form a better baseline model compared with a purely self-attention network. Then, we propose and compare two kinds of additional memory structures added into self-attention layers. Experiments on large-scale LVCSR tasks show that on four individual test sets, the DFSMN-SAN architecture outperforms vanilla SAN encoder by 5% relatively in character error rate (CER). More importantly, the additional memory structure provides further 5% to 11% relative improvement in CER. |
| Tasks | Large Vocabulary Continuous Speech Recognition, Speech Recognition |
| Published | 2019-10-28 |
| URL | https://arxiv.org/abs/1910.13282v1 |
| https://arxiv.org/pdf/1910.13282v1.pdf | |
| PWC | https://paperswithcode.com/paper/dfsmn-san-with-persistent-memory-model-for |
| Repo | |
| Framework | |
Hierarchical Data Reduction and Learning
| Title | Hierarchical Data Reduction and Learning |
| Authors | Prashant Shekhar, Abani Patra |
| Abstract | This paper describes a hierarchical learning strategy for generating sparse representations of multivariate datasets. The hierarchy arises from approximation spaces considered at successively finer scales. A detailed analysis of stability, convergence and behavior of error functionals associated with the approximations are presented, along with a well chosen set of applications. Results show the performance of the approach as a data reduction mechanism for both synthetic (univariate and multivariate) and real datasets (geospatial and numerical model outcomes). The sparse representation generated is shown to efficiently reconstruct data and minimize error in prediction. |
| Tasks | |
| Published | 2019-06-27 |
| URL | https://arxiv.org/abs/1906.11426v2 |
| https://arxiv.org/pdf/1906.11426v2.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchical-data-reduction-and-learning |
| Repo | |
| Framework | |
