Paper Group NANR 23
Automatic Thesaurus Construction for Modern Hebrew. Learning Signed Determinantal Point Processes through the Principal Minor Assignment Problem. Evaluating Multiple System Summary Lengths: A Case Study. Data2Text Studio: Automated Text Generation from Structured Data. Automatic Wordnet Mapping: from CoreNet to Princeton WordNet. Evaluation of Doma …
Automatic Thesaurus Construction for Modern Hebrew
| Title | Automatic Thesaurus Construction for Modern Hebrew |
| Authors | Chaya Liebeskind, Ido Dagan, Jonathan Schler |
| Abstract | |
| Tasks | Machine Translation, Question Answering, Semantic Textual Similarity, Word Sense Disambiguation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1229/ |
| https://www.aclweb.org/anthology/L18-1229 | |
| PWC | https://paperswithcode.com/paper/automatic-thesaurus-construction-for-modern |
| Repo | |
| Framework | |
Learning Signed Determinantal Point Processes through the Principal Minor Assignment Problem
| Title | Learning Signed Determinantal Point Processes through the Principal Minor Assignment Problem |
| Authors | Victor-Emmanuel Brunel |
| Abstract | Symmetric determinantal point processes (DPP) are a class of probabilistic models that encode the random selection of items that have a repulsive behavior. They have attracted a lot of attention in machine learning, where returning diverse sets of items is sought for. Sampling and learning these symmetric DPP’s is pretty well understood. In this work, we consider a new class of DPP’s, which we call signed DPP’s, where we break the symmetry and allow attractive behaviors. We set the ground for learning signed DPP’s through a method of moments, by solving the so called principal assignment problem for a class of matrices $K$ that satisfy $K_{i,j}=\pm K_{j,i}$, $i\neq j$, in polynomial time. |
| Tasks | Point Processes |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7966-learning-signed-determinantal-point-processes-through-the-principal-minor-assignment-problem |
| http://papers.nips.cc/paper/7966-learning-signed-determinantal-point-processes-through-the-principal-minor-assignment-problem.pdf | |
| PWC | https://paperswithcode.com/paper/learning-signed-determinantal-point-processes |
| Repo | |
| Framework | |
Evaluating Multiple System Summary Lengths: A Case Study
| Title | Evaluating Multiple System Summary Lengths: A Case Study |
| Authors | Ori Shapira, David Gabay, Hadar Ronen, Judit Bar-Ilan, Yael Amsterdamer, Ani Nenkova, Ido Dagan |
| Abstract | Practical summarization systems are expected to produce summaries of varying lengths, per user needs. While a couple of early summarization benchmarks tested systems across multiple summary lengths, this practice was mostly abandoned due to the assumed cost of producing reference summaries of multiple lengths. In this paper, we raise the research question of whether reference summaries of a single length can be used to reliably evaluate system summaries of multiple lengths. For that, we have analyzed a couple of datasets as a case study, using several variants of the ROUGE metric that are standard in summarization evaluation. Our findings indicate that the evaluation protocol in question is indeed competitive. This result paves the way to practically evaluating varying-length summaries with simple, possibly existing, summarization benchmarks. |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1087/ |
| https://www.aclweb.org/anthology/D18-1087 | |
| PWC | https://paperswithcode.com/paper/evaluating-multiple-system-summary-lengths-a |
| Repo | |
| Framework | |
Data2Text Studio: Automated Text Generation from Structured Data
| Title | Data2Text Studio: Automated Text Generation from Structured Data |
| Authors | Longxu Dou, Guanghui Qin, Jinpeng Wang, Jin-Ge Yao, Chin-Yew Lin |
| Abstract | Data2Text Studio is a platform for automated text generation from structured data. It is equipped with a Semi-HMMs model to extract high-quality templates and corresponding trigger conditions from parallel data automatically, which improves the interactivity and interpretability of the generated text. In addition, several easy-to-use tools are provided for developers to edit templates of pre-trained models, and APIs are released for developers to call the pre-trained model to generate texts in third-party applications. We conduct experiments on RotoWire datasets for template extraction and text generation. The results show that our model achieves improvements on both tasks. |
| Tasks | Data-to-Text Generation, Text Generation |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/D18-2003/ |
| https://www.aclweb.org/anthology/D18-2003 | |
| PWC | https://paperswithcode.com/paper/data2text-studio-automated-text-generation |
| Repo | |
| Framework | |
Automatic Wordnet Mapping: from CoreNet to Princeton WordNet
| Title | Automatic Wordnet Mapping: from CoreNet to Princeton WordNet |
| Authors | Jiseong Kim, Younggyun Hahm, Sunggoo Kwon, Key-Sun Choi |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1230/ |
| https://www.aclweb.org/anthology/L18-1230 | |
| PWC | https://paperswithcode.com/paper/automatic-wordnet-mapping-from-corenet-to |
| Repo | |
| Framework | |
Evaluation of Domain-specific Word Embeddings using Knowledge Resources
| Title | Evaluation of Domain-specific Word Embeddings using Knowledge Resources |
| Authors | Farhad Nooralahzadeh, Lilja {\O}vrelid, Jan Tore L{\o}nning |
| Abstract | |
| Tasks | Chunking, Named Entity Recognition, Sentence Classification, Sentiment Analysis, Word Embeddings |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1228/ |
| https://www.aclweb.org/anthology/L18-1228 | |
| PWC | https://paperswithcode.com/paper/evaluation-of-domain-specific-word-embeddings |
| Repo | |
| Framework | |
Iterative Deep Compression : Compressing Deep Networks for Classification and Semantic Segmentation
| Title | Iterative Deep Compression : Compressing Deep Networks for Classification and Semantic Segmentation |
| Authors | Sugandha Doda, Vitor Fortes Rey, Dr. Nadereh Hatami, Prof. Dr. Paul Lukowicz |
| Abstract | Machine learning and in particular deep learning approaches have outperformed many traditional techniques in accomplishing complex tasks such as image classfication, natural language processing or speech recognition. Most of the state-of-the art deep networks have complex architecture and use a vast number of parameters to reach this superior performance. Though these networks use a large number of learnable parameters, those parameters present significant redundancy. Therefore, it is possible to compress the network without much affecting its accuracy by eliminating those redundant and unimportant parameters. In this work, we propose a three stage compression pipeline, which consists of pruning, weight sharing and quantization to compress deep neural networks. Our novel pruning technique combines magnitude based ones with dense sparse dense ideas and iteratively finds for each layer its achievable sparsity instead of selecting a single threshold for the whole network. Unlike previous works, where compression is only applied on networks performing classification, we evaluate and perform compression on networks for classification as well as semantic segmentation, which is greatly useful for understanding scenes in autonomous driving. We tested our method on LeNet-5 and FCNs, performing classification and semantic segmentation, respectively. With LeNet-5 on MNIST, pruning reduces the number of parameters by 15.3 times and storage requirement from 1.7 MB to 0.006 MB with accuracy loss of 0.03%. With FCN8 on Cityscapes, we decrease the number of parameters by 8 times and reduce the storage requirement from 537.47 MB to 18.23 MB with class-wise intersection-over-union (IoU) loss of 4.93% on the validation data. |
| Tasks | Autonomous Driving, Quantization, Semantic Segmentation, Speech Recognition |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=SJZsR7kCZ |
| https://openreview.net/pdf?id=SJZsR7kCZ | |
| PWC | https://paperswithcode.com/paper/iterative-deep-compression-compressing-deep |
| Repo | |
| Framework | |
Wrapped Gaussian Process Regression on Riemannian Manifolds
| Title | Wrapped Gaussian Process Regression on Riemannian Manifolds |
| Authors | Anton Mallasto, Aasa Feragen |
| Abstract | Gaussian process (GP) regression is a powerful tool in non-parametric regression providing uncertainty estimates. However, it is limited to data in vector spaces. In fields such as shape analysis and diffusion tensor imaging, the data often lies on a manifold, making GP regression non- viable, as the resulting predictive distribution does not live in the correct geometric space. We tackle the problem by defining wrapped Gaussian processes (WGPs) on Rieman- nian manifolds, using the probabilistic setting to general- ize GP regression to the context of manifold-valued targets. The method is validated empirically on diffusion weighted imaging (DWI) data, directional data on the sphere and in the Kendall shape space, endorsing WGP regression as an efficient and flexible tool for manifold-valued regression. |
| Tasks | Gaussian Processes |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Mallasto_Wrapped_Gaussian_Process_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Mallasto_Wrapped_Gaussian_Process_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/wrapped-gaussian-process-regression-on |
| Repo | |
| Framework | |
Neural Machine Translation with the Transformer and Multi-Source Romance Languages for the Biomedical WMT 2018 task
| Title | Neural Machine Translation with the Transformer and Multi-Source Romance Languages for the Biomedical WMT 2018 task |
| Authors | Brian Tubay, Marta R. Costa-juss{`a} |
| Abstract | The Transformer architecture has become the state-of-the-art in Machine Translation. This model, which relies on attention-based mechanisms, has outperformed previous neural machine translation architectures in several tasks. In this system description paper, we report details of training neural machine translation with multi-source Romance languages with the Transformer model and in the evaluation frame of the biomedical WMT 2018 task. Using multi-source languages from the same family allows improvements of over 6 BLEU points. |
| Tasks | Machine Translation, Speech Recognition |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6449/ |
| https://www.aclweb.org/anthology/W18-6449 | |
| PWC | https://paperswithcode.com/paper/neural-machine-translation-with-the |
| Repo | |
| Framework | |
EmotionX-JTML: Detecting emotions with Attention
| Title | EmotionX-JTML: Detecting emotions with Attention |
| Authors | Johnny Torres |
| Abstract | This paper addresses the problem of automatic recognition of emotions in conversational text datasets for the EmotionX challenge. Emotion is a human characteristic expressed through several modalities (e.g., auditory, visual, tactile). Trying to detect emotions only from the text becomes a difficult task even for humans. This paper evaluates several neural architectures based on Attention Models, which allow extracting relevant parts of the context within a conversation to identify the emotion associated with each utterance. Empirical results in the validation datasets demonstrate the effectiveness of the approach compared to the reference models for some instances, and other cases show better results with simpler models. |
| Tasks | Emotion Classification, Representation Learning |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3510/ |
| https://www.aclweb.org/anthology/W18-3510 | |
| PWC | https://paperswithcode.com/paper/emotionx-jtml-detecting-emotions-with |
| Repo | |
| Framework | |
Descending, lifting or smoothing: Secrets of robust cost optimization
| Title | Descending, lifting or smoothing: Secrets of robust cost optimization |
| Authors | Christopher Zach, Guillaume Bourmaud |
| Abstract | Robust cost optimization is the challenging task of fitting a large number of parameters to data points containing a significant and unknown fraction of outliers. In this work we identify three classes of deterministic second-order algorithms that are able to tackle this type of optimization problem: direct approaches that aim to optimize the robust cost directly with a second order method, lifting-based approaches that add so called lifting variables to embed the given robust cost function into a higher dimensional space, and graduated optimization methods that solve a sequence of smoothed cost functions. We study each of these classes of algorithms and propose improvements either to reduce their computational time or to make them find better local minima. Finally, we experimentally demonstrate the superiority of our improved graduated optimization method over the state of the art algorithms both on synthetic and real data for four different problems. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Christopher_Zach_Descending_lifting_or_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Christopher_Zach_Descending_lifting_or_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/descending-lifting-or-smoothing-secrets-of |
| Repo | |
| Framework | |
Multiplicative Weights Updates with Constant Step-Size in Graphical Constant-Sum Games
| Title | Multiplicative Weights Updates with Constant Step-Size in Graphical Constant-Sum Games |
| Authors | Yun Kuen Cheung |
| Abstract | Since Multiplicative Weights (MW) updates are the discrete analogue of the continuous Replicator Dynamics (RD), some researchers had expected their qualitative behaviours would be similar. We show that this is false in the context of graphical constant-sum games, which include two-person zero-sum games as special cases. In such games which have a fully-mixed Nash Equilibrium (NE), it was known that RD satisfy the permanence and Poincare recurrence properties, but we show that MW updates with any constant step-size eps > 0 converge to the boundary of the state space, and thus do not satisfy the two properties. Using this result, we show that MW updates have a regret lower bound of Omega( 1 / (eps T) ), while it was known that the regret of RD is upper bounded by O( 1 / T ). Interestingly, the regret perspective can be useful for better understanding of the behaviours of MW updates. In a two-person zero-sum game, if it has a unique NE which is fully mixed, then we show, via regret, that for any sufficiently small eps, there exist at least two probability densities and a constant Z > 0, such that for any arbitrarily small z > 0, each of the two densities fluctuates above Z and below z infinitely often. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7612-multiplicative-weights-updates-with-constant-step-size-in-graphical-constant-sum-games |
| http://papers.nips.cc/paper/7612-multiplicative-weights-updates-with-constant-step-size-in-graphical-constant-sum-games.pdf | |
| PWC | https://paperswithcode.com/paper/multiplicative-weights-updates-with-constant |
| Repo | |
| Framework | |
Extending Search System based on Interactive Visualization for Speech Corpora
| Title | Extending Search System based on Interactive Visualization for Speech Corpora |
| Authors | Tomoko Ohsuga, Yuichi Ishimoto, Tomoko Kajiyama, Shunsuke Kozawa, Kiyotaka Uchimoto, Shuichi Itahashi |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1456/ |
| https://www.aclweb.org/anthology/L18-1456 | |
| PWC | https://paperswithcode.com/paper/extending-search-system-based-on-interactive |
| Repo | |
| Framework | |
Aggression Detection in Social Media using Deep Neural Networks
| Title | Aggression Detection in Social Media using Deep Neural Networks |
| Authors | Sreekanth Madisetty, Maunendra Sankar Desarkar |
| Abstract | With the rise of user-generated content in social media coupled with almost non-existent moderation in many such systems, aggressive contents have been observed to rise in such forums. In this paper, we work on the problem of aggression detection in social media. Aggression can sometimes be expressed directly or overtly or it can be hidden or covert in the text. On the other hand, most of the content in social media is non-aggressive in nature. We propose an ensemble based system to classify an input post to into one of three classes, namely, Overtly Aggressive, Covertly Aggressive, and Non-aggressive. Our approach uses three deep learning methods, namely, Convolutional Neural Networks (CNN) with five layers (input, convolution, pooling, hidden, and output), Long Short Term Memory networks (LSTM), and Bi-directional Long Short Term Memory networks (Bi-LSTM). A majority voting based ensemble method is used to combine these classifiers (CNN, LSTM, and Bi-LSTM). We trained our method on Facebook comments dataset and tested on Facebook comments (in-domain) and other social media posts (cross-domain). Our system achieves the F1-score (weighted) of 0.604 for Facebook posts and 0.508 for social media posts. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4415/ |
| https://www.aclweb.org/anthology/W18-4415 | |
| PWC | https://paperswithcode.com/paper/aggression-detection-in-social-media-using-1 |
| Repo | |
| Framework | |
WHAT ARE GANS USEFUL FOR?
| Title | WHAT ARE GANS USEFUL FOR? |
| Authors | Pablo M. Olmos, Briland Hitaj, Paolo Gasti, Giuseppe Ateniese, Fernando Perez-Cruz |
| Abstract | GANs have shown how deep neural networks can be used for generative modeling, aiming at achieving the same impact that they brought for discriminative modeling. The first results were impressive, GANs were shown to be able to generate samples in high dimensional structured spaces, like images and text, that were no copies of the training data. But generative and discriminative learning are quite different. Discriminative learning has a clear end, while generative modeling is an intermediate step to understand the data or generate hypothesis. The quality of implicit density estimation is hard to evaluate, because we cannot tell how well a data is represented by the model. How can we certainly say that a generative process is generating natural images with the same distribution as we do? In this paper, we noticed that even though GANs might not be able to generate samples from the underlying distribution (or we cannot tell at least), they are capturing some structure of the data in that high dimensional space. It is therefore needed to address how we can leverage those estimates produced by GANs in the same way we are able to use other generative modeling algorithms. |
| Tasks | Density Estimation |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=HkwrqtlR- |
| https://openreview.net/pdf?id=HkwrqtlR- | |
| PWC | https://paperswithcode.com/paper/what-are-gans-useful-for |
| Repo | |
| Framework | |
