Paper Group NANR 30
A Corpus Study and Annotation Schema for Named Entity Recognition and Relation Extraction of Business Products. PMKI: an European Commission action for the interoperability, maintainability and sustainability of Language Resources. DeepTC – An Extension of DKPro Text Classification for Fostering Reproducibility of Deep Learning Experiments. Using …
A Corpus Study and Annotation Schema for Named Entity Recognition and Relation Extraction of Business Products
| Title | A Corpus Study and Annotation Schema for Named Entity Recognition and Relation Extraction of Business Products |
| Authors | Saskia Sch{"o}n, Veselina Mironova, Aleks Gabryszak, ra, Leonhard Hennig |
| Abstract | |
| Tasks | Knowledge Graphs, Named Entity Recognition, Question Answering, Relation Extraction |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1704/ |
| https://www.aclweb.org/anthology/L18-1704 | |
| PWC | https://paperswithcode.com/paper/a-corpus-study-and-annotation-schema-for |
| Repo | |
| Framework | |
PMKI: an European Commission action for the interoperability, maintainability and sustainability of Language Resources
| Title | PMKI: an European Commission action for the interoperability, maintainability and sustainability of Language Resources |
| Authors | Peter Schmitz, Enrico Francesconi, Najeh Hajlaoui, Brahim Batouche |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1389/ |
| https://www.aclweb.org/anthology/L18-1389 | |
| PWC | https://paperswithcode.com/paper/pmki-an-european-commission-action-for-the |
| Repo | |
| Framework | |
DeepTC – An Extension of DKPro Text Classification for Fostering Reproducibility of Deep Learning Experiments
| Title | DeepTC – An Extension of DKPro Text Classification for Fostering Reproducibility of Deep Learning Experiments |
| Authors | Tobias Horsmann, Torsten Zesch |
| Abstract | |
| Tasks | Text Classification, Word Embeddings |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1403/ |
| https://www.aclweb.org/anthology/L18-1403 | |
| PWC | https://paperswithcode.com/paper/deeptc-a-an-extension-of-dkpro-text |
| Repo | |
| Framework | |
Using English Baits to Catch Serbian Multi-Word Terminology
| Title | Using English Baits to Catch Serbian Multi-Word Terminology |
| Authors | Cvetana Krstev, {\v{S}}, Branislava rih, Ranka Stankovi{'c}, Miljana Mladenovi{'c} |
| Abstract | |
| Tasks | Machine Translation, Morphological Inflection, Word Alignment |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1395/ |
| https://www.aclweb.org/anthology/L18-1395 | |
| PWC | https://paperswithcode.com/paper/using-english-baits-to-catch-serbian-multi |
| Repo | |
| Framework | |
MetaGAN: An Adversarial Approach to Few-Shot Learning
| Title | MetaGAN: An Adversarial Approach to Few-Shot Learning |
| Authors | Ruixiang Zhang, Tong Che, Zoubin Ghahramani, Yoshua Bengio, Yangqiu Song |
| Abstract | In this paper, we propose a conceptually simple and general framework called MetaGAN for few-shot learning problems. Most state-of-the-art few-shot classification models can be integrated with MetaGAN in a principled and straightforward way. By introducing an adversarial generator conditioned on tasks, we augment vanilla few-shot classification models with the ability to discriminate between real and fake data. We argue that this GAN-based approach can help few-shot classifiers to learn sharper decision boundary, which could generalize better. We show that with our MetaGAN framework, we can extend supervised few-shot learning models to naturally cope with unsupervised data. Different from previous work in semi-supervised few-shot learning, our algorithms can deal with semi-supervision at both sample-level and task-level. We give theoretical justifications of the strength of MetaGAN, and validate the effectiveness of MetaGAN on challenging few-shot image classification benchmarks. |
| Tasks | Few-Shot Image Classification, Few-Shot Learning, Image Classification |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7504-metagan-an-adversarial-approach-to-few-shot-learning |
| http://papers.nips.cc/paper/7504-metagan-an-adversarial-approach-to-few-shot-learning.pdf | |
| PWC | https://paperswithcode.com/paper/metagan-an-adversarial-approach-to-few-shot |
| Repo | |
| Framework | |
Accommodation of Conversational Code-Choice
| Title | Accommodation of Conversational Code-Choice |
| Authors | Anshul Bawa, Monojit Choudhury, Kalika Bali |
| Abstract | Bilingual speakers often freely mix languages. However, in such bilingual conversations, are the language choices of the speakers coordinated? How much does one speaker{'}s choice of language affect other speakers? In this paper, we formulate code-choice as a linguistic style, and show that speakers are indeed sensitive to and accommodating of each other{'}s code-choice. We find that the saliency or markedness of a language in context directly affects the degree of accommodation observed. More importantly, we discover that accommodation of code-choices persists over several conversational turns. We also propose an alternative interpretation of conversational accommodation as a retrieval problem, and show that the differences in accommodation characteristics of code-choices are based on their markedness in context. |
| Tasks | Information Retrieval |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3210/ |
| https://www.aclweb.org/anthology/W18-3210 | |
| PWC | https://paperswithcode.com/paper/accommodation-of-conversational-code-choice |
| Repo | |
| Framework | |
Interactive Image Segmentation With Latent Diversity
| Title | Interactive Image Segmentation With Latent Diversity |
| Authors | Zhuwen Li, Qifeng Chen, Vladlen Koltun |
| Abstract | Interactive image segmentation is characterized by multimodality. When the user clicks on a door, do they intend to select the door or the whole house? We present an end-to-end learning approach to interactive image segmentation that tackles this ambiguity. Our architecture couples two convolutional networks. The first is trained to synthesize a diverse set of plausible segmentations that conform to the user’s input. The second is trained to select among these. By selecting a single solution, our approach retains compatibility with existing interactive segmentation interfaces. By synthesizing multiple diverse solutions before selecting one, the architecture is given the representational power to explore the multimodal solution space. We show that the proposed approach outperforms existing methods for interactive image segmentation, including prior work that applied convolutional networks to this problem, while being much faster. |
| Tasks | Interactive Segmentation, Semantic Segmentation |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Li_Interactive_Image_Segmentation_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Li_Interactive_Image_Segmentation_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/interactive-image-segmentation-with-latent |
| Repo | |
| Framework | |
Nonparametric learning from Bayesian models with randomized objective functions
| Title | Nonparametric learning from Bayesian models with randomized objective functions |
| Authors | Simon Lyddon, Stephen Walker, Chris C. Holmes |
| Abstract | Bayesian learning is built on an assumption that the model space contains a true reflection of the data generating mechanism. This assumption is problematic, particularly in complex data environments. Here we present a Bayesian nonparametric approach to learning that makes use of statistical models, but does not assume that the model is true. Our approach has provably better properties than using a parametric model and admits a Monte Carlo sampling scheme that can afford massive scalability on modern computer architectures. The model-based aspect of learning is particularly attractive for regularizing nonparametric inference when the sample size is small, and also for correcting approximate approaches such as variational Bayes (VB). We demonstrate the approach on a number of examples including VB classifiers and Bayesian random forests. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7477-nonparametric-learning-from-bayesian-models-with-randomized-objective-functions |
| http://papers.nips.cc/paper/7477-nonparametric-learning-from-bayesian-models-with-randomized-objective-functions.pdf | |
| PWC | https://paperswithcode.com/paper/nonparametric-learning-from-bayesian-models-1 |
| Repo | |
| Framework | |
Indian Language Wordnets and their Linkages with Princeton WordNet
| Title | Indian Language Wordnets and their Linkages with Princeton WordNet |
| Authors | Diptesh Kanojia, Kevin Patel, Pushpak Bhattacharyya |
| Abstract | |
| Tasks | Information Retrieval, Machine Translation, Word Sense Disambiguation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1728/ |
| https://www.aclweb.org/anthology/L18-1728 | |
| PWC | https://paperswithcode.com/paper/indian-language-wordnets-and-their-linkages |
| Repo | |
| Framework | |
Albanian Part-of-Speech Tagging: Gold Standard and Evaluation
| Title | Albanian Part-of-Speech Tagging: Gold Standard and Evaluation |
| Authors | Besim Kabashi, Thomas Proisl |
| Abstract | |
| Tasks | Morphological Analysis, Part-Of-Speech Tagging |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1412/ |
| https://www.aclweb.org/anthology/L18-1412 | |
| PWC | https://paperswithcode.com/paper/albanian-part-of-speech-tagging-gold-standard |
| Repo | |
| Framework | |
Inferring Networks From Random Walk-Based Node Similarities
| Title | Inferring Networks From Random Walk-Based Node Similarities |
| Authors | Jeremy Hoskins, Cameron Musco, Christopher Musco, Babis Tsourakakis |
| Abstract | Digital presence in the world of online social media entails significant privacy risks. In this work we consider a privacy threat to a social network in which an attacker has access to a subset of random walk-based node similarities, such as effective resistances (i.e., commute times) or personalized PageRank scores. Using these similarities, the attacker seeks to infer as much information as possible about the network, including unknown pairwise node similarities and edges. For the effective resistance metric, we show that with just a small subset of measurements, one can learn a large fraction of edges in a social network. We also show that it is possible to learn a graph which accurately matches the underlying network on all other effective resistances. This second observation is interesting from a data mining perspective, since it can be expensive to compute all effective resistances or other random walk-based similarities. As an alternative, our graphs learned from just a subset of effective resistances can be used as surrogates in a range of applications that use effective resistances to probe graph structure, including for graph clustering, node centrality evaluation, and anomaly detection. We obtain our results by formalizing the graph learning objective mathematically, using two optimization problems. One formulation is convex and can be solved provably in polynomial time. The other is not, but we solve it efficiently with projected gradient and coordinate descent. We demonstrate the effectiveness of these methods on a number of social networks obtained from Facebook. We also discuss how our methods can be generalized to other random walk-based similarities, such as personalized PageRank scores. Our code is available at https://github.com/cnmusco/graph-similarity-learning. |
| Tasks | Anomaly Detection, Graph Clustering, Graph Similarity |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7628-inferring-networks-from-random-walk-based-node-similarities |
| http://papers.nips.cc/paper/7628-inferring-networks-from-random-walk-based-node-similarities.pdf | |
| PWC | https://paperswithcode.com/paper/inferring-networks-from-random-walk-based |
| Repo | |
| Framework | |
Multi-Task Adversarial Network for Disentangled Feature Learning
| Title | Multi-Task Adversarial Network for Disentangled Feature Learning |
| Authors | Yang Liu, Zhaowen Wang, Hailin Jin, Ian Wassell |
| Abstract | We address the problem of image feature learning for the applications where multiple factors exist in the image generation process and only some factors are of our interest. We present a novel multi-task adversarial network based on an encoder-discriminator-generator architecture. The encoder extracts a disentangled feature representation for the factors of interest. The discriminators classify each of the factors as individual tasks. The encoder and the discriminators are trained cooperatively on factors of interest, but in an adversarial way on factors of distraction. The generator provides further regularization on the learned feature by reconstructing images with shared factors as the input image. We design a new optimization scheme to stabilize the adversarial optimization process when multiple distributions need to be aligned. The experiments on face recognition and font recognition tasks show that our method outperforms the state-of-the-art methods in terms of both recognizing the factors of interest and generalization to images with unseen variations. |
| Tasks | Face Recognition, Image Generation |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Liu_Multi-Task_Adversarial_Network_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Liu_Multi-Task_Adversarial_Network_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/multi-task-adversarial-network-for |
| Repo | |
| Framework | |
Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Faces
| Title | Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Faces |
| Authors | Hao Zhou, Jin Sun, Yaser Yacoob, David W. Jacobs |
| Abstract | Lighting estimation from faces is an important task and has applications in many areas such as image editing, intrinsic image decomposition, and image forgery detection. We propose to train a deep Convolutional Neural Network (CNN) to regress lighting parameters from a single face image. Lacking massive ground truth lighting labels for face images in the wild, we use an existing method to estimate lighting parameters, which are treated as ground truth with noise. To alleviate the effect of such noise, we utilize the idea of Generative Adversarial Networks (GAN) and propose a Label Denoising Adversarial Network (LDAN). LDAN makes use of synthetic data with accurate ground truth to help train a deep CNN for lighting regression on real face images. Experiments show that our network outperforms existing methods in producing consistent lighting parameters of different faces under similar lighting conditions. To further evaluate the proposed method, we also apply it to regress object 2D key points where ground truth labels are available. Our experiments demonstrate its effectiveness on this application. |
| Tasks | Denoising, Intrinsic Image Decomposition |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Zhou_Label_Denoising_Adversarial_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhou_Label_Denoising_Adversarial_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/label-denoising-adversarial-network-ldan-for-1 |
| Repo | |
| Framework | |
Self-Governing Neural Networks for On-Device Short Text Classification
| Title | Self-Governing Neural Networks for On-Device Short Text Classification |
| Authors | Sujith Ravi, Zornitsa Kozareva |
| Abstract | Deep neural networks reach state-of-the-art performance for wide range of natural language processing, computer vision and speech applications. Yet, one of the biggest challenges is running these complex networks on devices such as mobile phones or smart watches with tiny memory footprint and low computational capacity. We propose on-device Self-Governing Neural Networks (SGNNs), which learn compact projection vectors with local sensitive hashing. The key advantage of SGNNs over existing work is that they surmount the need for pre-trained word embeddings and complex networks with huge parameters. We conduct extensive evaluation on dialog act classification and show significant improvement over state-of-the-art results. Our findings show that SGNNs are effective at capturing low-dimensional semantic text representations, while maintaining high accuracy. |
| Tasks | Dialog Act Classification, Dialogue Act Classification, Text Classification, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1105/ |
| https://www.aclweb.org/anthology/D18-1105 | |
| PWC | https://paperswithcode.com/paper/self-governing-neural-networks-for-on-device |
| Repo | |
| Framework | |
Annotation of Tense and Aspect Semantics for Sentential AMR
| Title | Annotation of Tense and Aspect Semantics for Sentential AMR |
| Authors | Lucia Donatelli, Michael Regan, William Croft, Nathan Schneider |
| Abstract | Although English grammar encodes a number of semantic contrasts with tense and aspect marking, these semantics are currently ignored by Abstract Meaning Representation (AMR) annotations. This paper extends sentence-level AMR to include a coarse-grained treatment of tense and aspect semantics. The proposed framework augments the representation of finite predications to include a four-way temporal distinction (event time before, up to, at, or after speech time) and several aspectual distinctions (including static vs. dynamic, habitual vs. episodic, and telic vs. atelic). This will enable AMR to be used for NLP tasks and applications that require sophisticated reasoning about time and event structure. |
| Tasks | Entity Typing |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4912/ |
| https://www.aclweb.org/anthology/W18-4912 | |
| PWC | https://paperswithcode.com/paper/annotation-of-tense-and-aspect-semantics-for |
| Repo | |
| Framework | |
