Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Topic": models, code, and papers

Approximate Causal Abstraction

Jun 29, 2019
Sander Beckers, Frederick Eberhardt, Joseph Y. Halpern

Scientific models describe natural phenomena at different levels of abstraction. Abstract descriptions can provide the basis for interventions on the system and explanation of observed phenomena at a level of granularity that is coarser than the most fundamental account of the system. Beckers and Halpern (2019), building on work of Rubenstein et al. (2017), developed an account of abstraction for causal models that is exact. Here we extend this account to the more realistic case where an abstract causal model offers only an approximation of the underlying system. We show how the resulting account handles the discrepancy that can arise between low- and high-level causal models of the same system, and in the process provide an account of how one causal model approximates another, a topic of independent interest. Finally, we extend the account of approximate abstractions to probabilistic causal models, indicating how and where uncertainty can enter into an approximate abstraction.

* Appears in UAI-2019 

  Access Paper or Ask Questions

PolSAR Image Classification based on Polarimetric Scattering Coding and Sparse Support Matrix Machine

Jun 17, 2019
Xu Liu, Licheng Jiao, Dan Zhang, Fang Liu

POLSAR image has an advantage over optical image because it can be acquired independently of cloud cover and solar illumination. PolSAR image classification is a hot and valuable topic for the interpretation of POLSAR image. In this paper, a novel POLSAR image classification method is proposed based on polarimetric scattering coding and sparse support matrix machine. First, we transform the original POLSAR data to get a real value matrix by the polarimetric scattering coding, which is called polarimetric scattering matrix and is a sparse matrix. Second, the sparse support matrix machine is used to classify the sparse polarimetric scattering matrix and get the classification map. The combination of these two steps takes full account of the characteristics of POLSAR. The experimental results show that the proposed method can get better results and is an effective classification method.

* IGARSS2019 
* arXiv admin note: text overlap with arXiv:1807.02975 

  Access Paper or Ask Questions

A Persona-based Multi-turn Conversation Model in an Adversarial Learning Framework

Apr 29, 2019
Oluwatobi O. Olabiyi, Anish Khazane, Erik T. Mueller

In this paper, we extend the persona-based sequence-to-sequence (Seq2Seq) neural network conversation model to multi-turn dialogue by modifying the state-of-the-art hredGAN architecture. To achieve this, we introduce an additional input modality into the encoder and decoder of hredGAN to capture other attributes such as speaker identity, location, sub-topics, and other external attributes that might be available from the corpus of human-to-human interactions. The resulting persona hredGAN ($phredGAN$) shows better performance than both the existing persona-based Seq2Seq and hredGAN models when those external attributes are available in a multi-turn dialogue corpus. This superiority is demonstrated on TV drama series with character consistency (such as Big Bang Theory and Friends) and customer service interaction datasets such as Ubuntu dialogue corpus in terms of perplexity, BLEU, ROUGE, and Distinct n-gram scores.

* 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA). arXiv admin note: substantial text overlap with arXiv:1905.01992 

  Access Paper or Ask Questions

What makes a good conversation? How controllable attributes affect human judgments

Apr 10, 2019
Abigail See, Stephen Roller, Douwe Kiela, Jason Weston

A good conversation requires balance -- between simplicity and detail; staying on topic and changing it; asking questions and answering them. Although dialogue agents are commonly evaluated via human judgments of overall quality, the relationship between quality and these individual factors is less well-studied. In this work, we examine two controllable neural text generation methods, conditional training and weighted decoding, in order to control four important attributes for chitchat dialogue: repetition, specificity, response-relatedness and question-asking. We conduct a large-scale human evaluation to measure the effect of these control parameters on multi-turn interactive conversations on the PersonaChat task. We provide a detailed analysis of their relationship to high-level aspects of conversation, and show that by controlling combinations of these variables our models obtain clear improvements in human quality judgments.

* Accepted to NAACL 2019 

  Access Paper or Ask Questions

3D Pursuit-Evasion for AUVs

Sep 26, 2018
Özer Özkahraman, Petter Ögren

In this paper, we consider the problem of pursuit-evasion using multiple Autonomous Underwater Vehicles (AUVs) in a 3D water volume, with and without simple obstacles. Pursuit-evasion is a well studied topic in robotics, but the results are mostly set in 2D environments, using unlimited line of sight sensing. We propose an algorithm for range limited sensing in 3D environments that captures a finite speed evader based on one single previous observation of its location. The pursuers are first moved to form a maximal cage formation, based on their number and sensor ranges, containing all of the possible evader locations. The cage is then shrunk until every part of that volume is sensed, thereby capturing the evader. The pursuers need only limited sensing range and low bandwidth communication, making the algorithm well suited for an underwater environment.

* 6+1 pages 

  Access Paper or Ask Questions

Regularisation of Neural Networks by Enforcing Lipschitz Continuity

Sep 14, 2018
Henry Gouk, Eibe Frank, Bernhard Pfahringer, Michael Cree

We investigate the effect of explicitly enforcing the Lipschitz continuity of neural networks with respect to their inputs. To this end, we provide a simple technique for computing an upper bound to the Lipschitz constant of a feed forward neural network composed of commonly used layer types and demonstrate inaccuracies in previous work on this topic. Our technique is then used to formulate training a neural network with a bounded Lipschitz constant as a constrained optimisation problem that can be solved using projected stochastic gradient methods. Our evaluation study shows that, in isolation, our method performs comparatively to state-of-the-art regularisation techniques. Moreover, when combined with existing approaches to regularising neural networks the performance gains are cumulative. We also provide evidence that the hyperparameters are intuitive to tune and demonstrate how the choice of norm for computing the Lipschitz constant impacts the resulting model.


  Access Paper or Ask Questions

Summarizing First-Person Videos from Third Persons' Points of Views

Jul 26, 2018
Hsuan-I Ho, Wei-Chen Chiu, Yu-Chiang Frank Wang

Video highlight or summarization is among interesting topics in computer vision, which benefits a variety of applications like viewing, searching, or storage. However, most existing studies rely on training data of third-person videos, which cannot easily generalize to highlight the first-person ones. With the goal of deriving an effective model to summarize first-person videos, we propose a novel deep neural network architecture for describing and discriminating vital spatiotemporal information across videos with different points of view. Our proposed model is realized in a semi-supervised setting, in which fully annotated third-person videos, unlabeled first-person videos, and a small number of annotated first-person ones are presented during training. In our experiments, qualitative and quantitative evaluations on both benchmarks and our collected first-person video datasets are presented.

* 16+10 pages, ECCV 2018 

  Access Paper or Ask Questions

Fake news as we feel it: perception and conceptualization of the term "fake news" in the media

Jul 18, 2018
Evandro Cunha, Gabriel Magno, Josemar Caetano, Douglas Teixeira, Virgilio Almeida

In this article, we quantitatively analyze how the term "fake news" is being shaped in news media in recent years. We study the perception and the conceptualization of this term in the traditional media using eight years of data collected from news outlets based in 20 countries. Our results not only corroborate previous indications of a high increase in the usage of the expression "fake news", but also show contextual changes around this expression after the United States presidential election of 2016. Among other results, we found changes in the related vocabulary, in the mentioned entities, in the surrounding topics and in the contextual polarity around the term "fake news", suggesting that this expression underwent a change in perception and conceptualization after 2016. These outcomes expand the understandings on the usage of the term "fake news", helping to comprehend and more accurately characterize this relevant social phenomenon linked to misinformation and manipulation.

* Accepted as a full paper at the 10th International Conference on Social Informatics (SocInfo 2018). Please cite the SocInfo version 

  Access Paper or Ask Questions

Transfer Learning for Context-Aware Question Matching in Information-seeking Conversations in E-commerce

Jun 14, 2018
Minghui Qiu, Liu Yang, Feng Ji, Weipeng Zhao, Wei Zhou, Jun Huang, Haiqing Chen, W. Bruce Croft, Wei Lin

Building multi-turn information-seeking conversation systems is an important and challenging research topic. Although several advanced neural text matching models have been proposed for this task, they are generally not efficient for industrial applications. Furthermore, they rely on a large amount of labeled data, which may not be available in real-world applications. To alleviate these problems, we study transfer learning for multi-turn information seeking conversations in this paper. We first propose an efficient and effective multi-turn conversation model based on convolutional neural networks. After that, we extend our model to adapt the knowledge learned from a resource-rich domain to enhance the performance. Finally, we deployed our model in an industrial chatbot called AliMe Assist (https://consumerservice.taobao.com/online-help) and observed a significant improvement over the existing online model.

* ACL 2018 
* 6 

  Access Paper or Ask Questions

Efficient Graph-based Word Sense Induction by Distributional Inclusion Vector Embeddings

May 29, 2018
Haw-Shiuan Chang, Amol Agrawal, Ananya Ganesh, Anirudha Desai, Vinayak Mathur, Alfred Hough, Andrew McCallum

Word sense induction (WSI), which addresses polysemy by unsupervised discovery of multiple word senses, resolves ambiguities for downstream NLP tasks and also makes word representations more interpretable. This paper proposes an accurate and efficient graph-based method for WSI that builds a global non-negative vector embedding basis (which are interpretable like topics) and clusters the basis indexes in the ego network of each polysemous word. By adopting distributional inclusion vector embeddings as our basis formation model, we avoid the expensive step of nearest neighbor search that plagues other graph-based methods without sacrificing the quality of sense clusters. Experiments on three datasets show that our proposed method produces similar or better sense clusters and embeddings compared with previous state-of-the-art methods while being significantly more efficient.

* TextGraphs 2018: the Workshop on Graph-based Methods for Natural Language Processing 

  Access Paper or Ask Questions

<<
276
277
278
279
280
281
282
283
284
285
286
287
288
>>