Paper Group NANR 265
Translating a Language You Don’t Know In the Chinese Room. Commonsense Justification for Action Explanation. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts. Domain Adaptation for Disease Phrase Matching with Adversarial Networks. AANN: Absolute Artificial Neural Network. Utilizing Graph M …
Translating a Language You Don’t Know In the Chinese Room
| Title | Translating a Language You Don’t Know In the Chinese Room |
| Authors | Ulf Hermjakob, Jonathan May, Michael Pust, Kevin Knight |
| Abstract | In a corruption of John Searle{'}s famous AI thought experiment, the Chinese Room (Searle, 1980), we twist its original intent by enabling humans to translate text, e.g. from Uyghur to English, even if they don{'}t have any prior knowledge of the source language. Our enabling tool, which we call the Chinese Room, is equipped with the same resources made available to a machine translation engine. We find that our superior language model and world knowledge allows us to create perfectly fluent and nearly adequate translations, with human expertise required only for the target language. The Chinese Room tool can be used to rapidly create small corpora of parallel data when bilingual translators are not readily available, in particular for low-resource languages. |
| Tasks | Domain Adaptation, Language Modelling, Machine Translation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-4011/ |
| https://www.aclweb.org/anthology/P18-4011 | |
| PWC | https://paperswithcode.com/paper/translating-a-language-you-donat-know-in-the |
| Repo | |
| Framework | |
Commonsense Justification for Action Explanation
| Title | Commonsense Justification for Action Explanation |
| Authors | Shaohua Yang, Qiaozi Gao, Sari Sadiya, Joyce Chai |
| Abstract | To enable collaboration and communication between humans and agents, this paper investigates learning to acquire commonsense evidence for action justification. In particular, we have developed an approach based on the generative Conditional Variational Autoencoder(CVAE) that models object relations/attributes of the world as latent variables and jointly learns a performer that predicts actions and an explainer that gathers commonsense evidence to justify the action. Our empirical results have shown that, compared to a typical attention-based model, CVAE achieves significantly higher performance in both action prediction and justification. A human subject study further shows that the commonsense evidence gathered by CVAE can be communicated to humans to achieve a significantly higher common ground between humans and agents. |
| Tasks | Decision Making |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1283/ |
| https://www.aclweb.org/anthology/D18-1283 | |
| PWC | https://paperswithcode.com/paper/commonsense-justification-for-action |
| Repo | |
| Framework | |
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts
| Title | Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-5000/ |
| https://www.aclweb.org/anthology/P18-5000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-acl-2018-tutorial-abstracts |
| Repo | |
| Framework | |
Domain Adaptation for Disease Phrase Matching with Adversarial Networks
| Title | Domain Adaptation for Disease Phrase Matching with Adversarial Networks |
| Authors | Miaofeng Liu, Jialong Han, Haisong Zhang, Yan Song |
| Abstract | With the development of medical information management, numerous medical data are being classified, indexed, and searched in various systems. Disease phrase matching, i.e., deciding whether two given disease phrases interpret each other, is a basic but crucial preprocessing step for the above tasks. Being capable of relieving the scarceness of annotations, domain adaptation is generally considered useful in medical systems. However, efforts on applying it to phrase matching remain limited. This paper presents a domain-adaptive matching network for disease phrases. Our network achieves domain adaptation by adversarial training, i.e., preferring features indicating whether the two phrases match, rather than which domain they come from. Experiments suggest that our model has the best performance among the very few non-adaptive or adaptive methods that can benefit from out-of-domain annotations. |
| Tasks | Domain Adaptation, Entity Linking, Natural Language Inference |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2315/ |
| https://www.aclweb.org/anthology/W18-2315 | |
| PWC | https://paperswithcode.com/paper/domain-adaptation-for-disease-phrase-matching |
| Repo | |
| Framework | |
AANN: Absolute Artificial Neural Network
| Title | AANN: Absolute Artificial Neural Network |
| Authors | Animesh Karnewar |
| Abstract | This research paper describes a simplistic architecture named as AANN: Absolute Artificial Neural Network, which can be used to create highly interpretable representations of the input data. These representations are generated by penalizing the learning of the network in such a way that those learned representations correspond to the respective labels present in the labelled dataset used for supervised training; thereby, simultaneously giving the network the ability to classify the input data. The network can be used in the reverse direction to generate data that closely resembles the input by feeding in representation vectors as required. This research paper also explores the use of mathematical abs (absolute valued) functions as activation functions which constitutes the core part of this neural network architecture. Finally the results obtained on the MNIST dataset by using this technique are presented and discussed in brief. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=rkhxwltab |
| https://openreview.net/pdf?id=rkhxwltab | |
| PWC | https://paperswithcode.com/paper/aann-absolute-artificial-neural-network |
| Repo | |
| Framework | |
Utilizing Graph Measure to Deduce Omitted Entities in Paragraphs
| Title | Utilizing Graph Measure to Deduce Omitted Entities in Paragraphs |
| Authors | Eun-kyung Kim, Kijong Han, Jiho Kim, Key-Sun Choi |
| Abstract | This demo deals with the problem of capturing omitted arguments in relation extraction given a proper knowledge base for entities of interest. This paper introduces the concept of a salient entity and use this information to deduce omitted entities in the paragraph which allows improving the relation extraction quality. The main idea to compute salient entities is to construct a graph on the given information (by identifying the entities but without parsing it), rank it with standard graph measures and embed it in the context of the sentences. |
| Tasks | Question Answering, Relation Extraction, Relationship Extraction (Distant Supervised) |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-2011/ |
| https://www.aclweb.org/anthology/C18-2011 | |
| PWC | https://paperswithcode.com/paper/utilizing-graph-measure-to-deduce-omitted |
| Repo | |
| Framework | |
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers)
| Title | Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-3000/ |
| https://www.aclweb.org/anthology/N18-3000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2018-conference-of-the-2 |
| Repo | |
| Framework | |
IRISA at SMM4H 2018: Neural Network and Bagging for Tweet Classification
| Title | IRISA at SMM4H 2018: Neural Network and Bagging for Tweet Classification |
| Authors | Anne-Lyse Minard, Christian Raymond, Vincent Claveau |
| Abstract | This paper describes the systems developed by IRISA to participate to the four tasks of the SMM4H 2018 challenge. For these tweet classification tasks, we adopt a common approach based on recurrent neural networks (BiLSTM). Our main contributions are the use of certain features, the use of Bagging in order to deal with unbalanced datasets, and on the automatic selection of difficult examples. These techniques allow us to reach 91.4, 46.5, 47.8, 85.0 as F1-scores for Tasks 1 to 4. |
| Tasks | Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5913/ |
| https://www.aclweb.org/anthology/W18-5913 | |
| PWC | https://paperswithcode.com/paper/irisa-at-smm4h-2018-neural-network-and |
| Repo | |
| Framework | |
Dual Principal Component Pursuit: Improved Analysis and Efficient Algorithms
| Title | Dual Principal Component Pursuit: Improved Analysis and Efficient Algorithms |
| Authors | Zhihui Zhu, Yifan Wang, Daniel Robinson, Daniel Naiman, Rene Vidal, Manolis Tsakiris |
| Abstract | Recent methods for learning a linear subspace from data corrupted by outliers are based on convex L1 and nuclear norm optimization and require the dimension of the subspace and the number of outliers to be sufficiently small [27]. In sharp contrast, the recently proposed Dual Principal Component Pursuit (DPCP) method [22] can provably handle subspaces of high dimension by solving a non-convex L1 optimization problem on the sphere. However, its geometric analysis is based on quantities that are difficult to interpret and are not amenable to statistical analysis. In this paper we provide a refined geometric analysis and a new statistical analysis that show that DPCP can tolerate as many outliers as the square of the number of inliers, thus improving upon other provably correct robust PCA methods. We also propose a scalable Projected Sub-Gradient Descent method (DPCP-PSGD) for solving the DPCP problem and show it admits linear convergence even though the underlying optimization problem is non-convex and non-smooth. Experiments on road plane detection from 3D point cloud data demonstrate that DPCP-PSGD can be more efficient than the traditional RANSAC algorithm, which is one of the most popular methods for such computer vision applications. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7486-dual-principal-component-pursuit-improved-analysis-and-efficient-algorithms |
| http://papers.nips.cc/paper/7486-dual-principal-component-pursuit-improved-analysis-and-efficient-algorithms.pdf | |
| PWC | https://paperswithcode.com/paper/dual-principal-component-pursuit-improved |
| Repo | |
| Framework | |
SphereNet: Learning Spherical Representations for Detection and Classification in Omnidirectional Images
| Title | SphereNet: Learning Spherical Representations for Detection and Classification in Omnidirectional Images |
| Authors | Benjamin Coors, Alexandru Paul Condurache, Andreas Geiger |
| Abstract | Omnidirectional cameras offer great benefits over classical cameras wherever a wide field of view is essential, such as in virtual reality applications or in autonomous robots. Unfortunately, standard convolutional neural networks are not well suited for this scenario as the natural projection surface is a sphere which cannot be unwrapped to a plane without introducing significant distortions, particularly in the polar regions. In this work, we present SphereNet, a novel deep learning framework which encodes invariance against such distortions explicitly into convolutional neural networks. Towards this goal, SphereNet adapts the sampling locations of the convolutional filters, effectively reversing distortions, and wraps the filters around the sphere. By building on regular convolutions, SphereNet enables the transfer of existing perspective convolutional neural network models to the omnidirectional case. We demonstrate the effectiveness of our method on the tasks of image classification and object detection, exploiting two newly created semi-synthetic and real-world omnidirectional datasets. |
| Tasks | Image Classification, Object Detection |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Benjamin_Coors_SphereNet_Learning_Spherical_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Benjamin_Coors_SphereNet_Learning_Spherical_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/spherenet-learning-spherical-representations |
| Repo | |
| Framework | |
Autoregressive Generative Adversarial Networks
| Title | Autoregressive Generative Adversarial Networks |
| Authors | Yasin Yazici, Kim-Hui Yap, Stefan Winkler |
| Abstract | Generative Adversarial Networks (GANs) learn a generative model by playing an adversarial game between a generator and an auxiliary discriminator, which classifies data samples vs. generated ones. However, it does not explicitly model feature co-occurrences in samples. In this paper, we propose a novel Autoregressive Generative Adversarial Network (ARGAN), that models the latent distribution of data using an autoregressive model, rather than relying on binary classification of samples into data/generated categories. In this way, feature co-occurrences in samples can be more efficiently captured. Our model was evaluated on two widely used datasets: CIFAR-10 and STL-10. Its performance is competitive with respect to other GAN models both quantitatively and qualitatively. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=rJWrK9lAb |
| https://openreview.net/pdf?id=rJWrK9lAb | |
| PWC | https://paperswithcode.com/paper/autoregressive-generative-adversarial |
| Repo | |
| Framework | |
Preliminary theoretical troubleshooting in Variational Autoencoder
| Title | Preliminary theoretical troubleshooting in Variational Autoencoder |
| Authors | Shiqi Liu, Qian Zhao, Xiangyong Cao, Deyu Meng, Zilu Ma, Tao Yu |
| Abstract | What would be learned by variational autoencoder(VAE) and what influence the disentanglement of VAE? This paper tries to preliminarily address VAE’s intrinsic dimension, real factor, disentanglement and indicator issues theoretically in the idealistic situation and implementation issue practically through noise modeling perspective in the realistic case. On intrinsic dimension issue, due to information conservation, the idealistic VAE learns and only learns intrinsic factor dimension. Besides, suggested by mutual information separation property, the constraint induced by Gaussian prior to the VAE objective encourages the information sparsity in dimension. On disentanglement issue, subsequently, inspired by information conservation theorem the clarification on disentanglement in this paper is made. On real factor issue, due to factor equivalence, the idealistic VAE possibly learns any factor set in the equivalence class. On indicator issue, the behavior of current disentanglement metric is discussed, and several performance indicators regarding the disentanglement and generating influence are subsequently raised to evaluate the performance of VAE model and to supervise the used factors. On implementation issue, the experiments under noise modeling and constraints empirically testify the theoretical analysis and also show their own characteristic in pursuing disentanglement. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=SkERSm-0- |
| https://openreview.net/pdf?id=SkERSm-0- | |
| PWC | https://paperswithcode.com/paper/preliminary-theoretical-troubleshooting-in |
| Repo | |
| Framework | |
Semantic Equivalence Detection: Are Interrogatives Harder than Declaratives?
| Title | Semantic Equivalence Detection: Are Interrogatives Harder than Declaratives? |
| Authors | Jo{~a}o Rodrigues, Chakaveh Saedi, Ant{'o}nio Branco, Jo{~a}o Silva |
| Abstract | |
| Tasks | Community Question Answering, Information Retrieval, Question Answering, Relation Extraction, Sentiment Analysis |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1513/ |
| https://www.aclweb.org/anthology/L18-1513 | |
| PWC | https://paperswithcode.com/paper/semantic-equivalence-detection-are |
| Repo | |
| Framework | |
Understanding and Simplifying One-Shot Architecture Search
| Title | Understanding and Simplifying One-Shot Architecture Search |
| Authors | Gabriel Bender, Pieter-Jan Kindermans, Barret Zoph, Vijay Vasudevan, Quoc Le |
| Abstract | There is growing interest in automating neural network architecture design. Existing architecture search methods can be computationally expensive, requiring thousands of different architectures to be trained from scratch. Recent work has explored weight sharing across models to amortize the cost of training. Although previous methods reduced the cost of architecture search by orders of magnitude, they remain complex, requiring hypernetworks or reinforcement learning controllers. We aim to understand weight sharing for one-shot architecture search. With careful experimental analysis, we show that it is possible to efficiently identify promising architectures from a complex search space without either hypernetworks or RL. |
| Tasks | Neural Architecture Search |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2077 |
| http://proceedings.mlr.press/v80/bender18a/bender18a.pdf | |
| PWC | https://paperswithcode.com/paper/understanding-and-simplifying-one-shot |
| Repo | |
| Framework | |
Neural Program Search: Solving Data Processing Tasks from Description and Examples
| Title | Neural Program Search: Solving Data Processing Tasks from Description and Examples |
| Authors | Illia Polosukhin, Alexander Skidanov |
| Abstract | We present a Neural Program Search, an algorithm to generate programs from natural language description and a small number of input / output examples. The algorithm combines methods from Deep Learning and Program Synthesis fields by designing rich domain-specific language (DSL) and defining efficient search algorithm guided by a Seq2Tree model on it. To evaluate the quality of the approach we also present a semi-synthetic dataset of descriptions with test examples and corresponding programs. We show that our algorithm significantly outperforms sequence-to-sequence model with attention baseline. |
| Tasks | Program Synthesis |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=B1KJJf-R- |
| https://openreview.net/pdf?id=B1KJJf-R- | |
| PWC | https://paperswithcode.com/paper/neural-program-search-solving-data-processing |
| Repo | |
| Framework | |
