Paper Group NANR 57
\ell_1-regression with Heavy-tailed Distributions. ASAP++: Enriching the ASAP Automated Essay Grading Dataset with Essay Attribute Scores. The Organization of Lexicons: a Cross-Linguistic Analysis of Monosyllabic Words. The NYU System for the CoNLL–SIGMORPHON 2018 Shared Task on Universal Morphological Reinflection. On the Abstractiveness of Neura …
\ell_1-regression with Heavy-tailed Distributions
| Title | \ell_1-regression with Heavy-tailed Distributions |
| Authors | Lijun Zhang, Zhi-Hua Zhou |
| Abstract | In this paper, we consider the problem of linear regression with heavy-tailed distributions. Different from previous studies that use the squared loss to measure the performance, we choose the absolute loss, which is capable of estimating the conditional median. To address the challenge that both the input and output could be heavy-tailed, we propose a truncated minimization problem, and demonstrate that it enjoys an $O(\sqrt{d/n})$ excess risk, where $d$ is the dimensionality and $n$ is the number of samples. Compared with traditional work on $\ell_1$-regression, the main advantage of our result is that we achieve a high-probability risk bound without exponential moment conditions on the input and output. Furthermore, if the input is bounded, we show that the classical empirical risk minimization is competent for $\ell_1$-regression even when the output is heavy-tailed. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7385-ell_1-regression-with-heavy-tailed-distributions |
| http://papers.nips.cc/paper/7385-ell_1-regression-with-heavy-tailed-distributions.pdf | |
| PWC | https://paperswithcode.com/paper/ell_1-regression-with-heavy-tailed-1 |
| Repo | |
| Framework | |
ASAP++: Enriching the ASAP Automated Essay Grading Dataset with Essay Attribute Scores
| Title | ASAP++: Enriching the ASAP Automated Essay Grading Dataset with Essay Attribute Scores |
| Authors | S Mathias, eep, Pushpak Bhattacharyya |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1187/ |
| https://www.aclweb.org/anthology/L18-1187 | |
| PWC | https://paperswithcode.com/paper/asap-enriching-the-asap-automated-essay |
| Repo | |
| Framework | |
The Organization of Lexicons: a Cross-Linguistic Analysis of Monosyllabic Words
| Title | The Organization of Lexicons: a Cross-Linguistic Analysis of Monosyllabic Words |
| Authors | Shiying Yang, Chelsea Sanker, Uriel Cohen Priva |
| Abstract | |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://www.aclweb.org/anthology/W18-0317/ |
| https://www.aclweb.org/anthology/W18-0317 | |
| PWC | https://paperswithcode.com/paper/the-organization-of-lexicons-a-cross |
| Repo | |
| Framework | |
The NYU System for the CoNLL–SIGMORPHON 2018 Shared Task on Universal Morphological Reinflection
| Title | The NYU System for the CoNLL–SIGMORPHON 2018 Shared Task on Universal Morphological Reinflection |
| Authors | Katharina Kann, Stanislas Lauly, Kyunghyun Cho |
| Abstract | |
| Tasks | Morphological Inflection |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/K18-3006/ |
| https://www.aclweb.org/anthology/K18-3006 | |
| PWC | https://paperswithcode.com/paper/the-nyu-system-for-the-conllasigmorphon-2018 |
| Repo | |
| Framework | |
On the Abstractiveness of Neural Document Summarization
| Title | On the Abstractiveness of Neural Document Summarization |
| Authors | Fangfang Zhang, Jin-ge Yao, Rui Yan |
| Abstract | Many modern neural document summarization systems based on encoder-decoder networks are designed to produce abstractive summaries. We attempted to verify the degree of abstractiveness of modern neural abstractive summarization systems by calculating overlaps in terms of various types of units. Upon the observation that many abstractive systems tend to be near-extractive in practice, we also implemented a pure copy system, which achieved comparable results as abstractive summarizers while being far more computationally efficient. These findings suggest the possibility for future efforts towards more efficient systems that could better utilize the vocabulary in the original document. |
| Tasks | Abstractive Text Summarization, Document Summarization |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1089/ |
| https://www.aclweb.org/anthology/D18-1089 | |
| PWC | https://paperswithcode.com/paper/on-the-abstractiveness-of-neural-document |
| Repo | |
| Framework | |
Proceedings of the First Workshop on Fact Extraction and VERification (FEVER)
| Title | Proceedings of the First Workshop on Fact Extraction and VERification (FEVER) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-5500/ |
| https://www.aclweb.org/anthology/W18-5500 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-first-workshop-on-fact |
| Repo | |
| Framework | |
Labeled Anchors and a Scalable, Transparent, and Interactive Classifier
| Title | Labeled Anchors and a Scalable, Transparent, and Interactive Classifier |
| Authors | Jeffrey Lund, Stephen Cowley, Wilson Fearn, Emily Hales, Kevin Seppi |
| Abstract | We propose Labeled Anchors, an interactive and supervised topic model based on the anchor words algorithm (Arora et al., 2013). Labeled Anchors is similar to Supervised Anchors (Nguyen et al., 2014) in that it extends the vector-space representation of words to include document labels. However, our formulation also admits a classifier which requires no training beyond inferring topics, which means our approach is also fast enough to be interactive. We run a small user study that demonstrates that untrained users can interactively update topics in order to improve classification accuracy. |
| Tasks | Document Classification, Text Classification, Topic Models |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1095/ |
| https://www.aclweb.org/anthology/D18-1095 | |
| PWC | https://paperswithcode.com/paper/labeled-anchors-and-a-scalable-transparent |
| Repo | |
| Framework | |
Word Embeddings for Code-Mixed Language Processing
| Title | Word Embeddings for Code-Mixed Language Processing |
| Authors | Adithya Pratapa, Monojit Choudhury, Sunayana Sitaram |
| Abstract | We compare three existing bilingual word embedding approaches, and a novel approach of training skip-grams on synthetic code-mixed text generated through linguistic models of code-mixing, on two tasks - sentiment analysis and POS tagging for code-mixed text. Our results show that while CVM and CCA based embeddings perform as well as the proposed embedding technique on semantic and syntactic tasks respectively, the proposed approach provides the best performance for both tasks overall. Thus, this study demonstrates that existing bilingual embedding techniques are not ideal for code-mixed text processing and there is a need for learning multilingual word embedding from the code-mixed text. |
| Tasks | Machine Translation, Sentiment Analysis, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1344/ |
| https://www.aclweb.org/anthology/D18-1344 | |
| PWC | https://paperswithcode.com/paper/word-embeddings-for-code-mixed-language |
| Repo | |
| Framework | |
Stochastic Primal-Dual Method for Empirical Risk Minimization with O(1) Per-Iteration Complexity
| Title | Stochastic Primal-Dual Method for Empirical Risk Minimization with O(1) Per-Iteration Complexity |
| Authors | Conghui Tan, Tong Zhang, Shiqian Ma, Ji Liu |
| Abstract | Regularized empirical risk minimization problem with linear predictor appears frequently in machine learning. In this paper, we propose a new stochastic primal-dual method to solve this class of problems. Different from existing methods, our proposed methods only require O(1) operations in each iteration. We also develop a variance-reduction variant of the algorithm that converges linearly. Numerical experiments suggest that our methods are faster than existing ones such as proximal SGD, SVRG and SAGA on high-dimensional problems. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8057-stochastic-primal-dual-method-for-empirical-risk-minimization-with-o1-per-iteration-complexity |
| http://papers.nips.cc/paper/8057-stochastic-primal-dual-method-for-empirical-risk-minimization-with-o1-per-iteration-complexity.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-primal-dual-method-for-empirical |
| Repo | |
| Framework | |
A Lightweight Modeling Middleware for Corpus Processing
| Title | A Lightweight Modeling Middleware for Corpus Processing |
| Authors | Markus G{"a}rtner, Jonas Kuhn |
| Abstract | |
| Tasks | Coreference Resolution |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1176/ |
| https://www.aclweb.org/anthology/L18-1176 | |
| PWC | https://paperswithcode.com/paper/a-lightweight-modeling-middleware-for-corpus |
| Repo | |
| Framework | |
Designing a Collaborative Process to Create Bilingual Dictionaries of Indonesian Ethnic Languages
| Title | Designing a Collaborative Process to Create Bilingual Dictionaries of Indonesian Ethnic Languages |
| Authors | Arbi Haza Nasution, Yohei Murakami, Toru Ishida |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1536/ |
| https://www.aclweb.org/anthology/L18-1536 | |
| PWC | https://paperswithcode.com/paper/designing-a-collaborative-process-to-create |
| Repo | |
| Framework | |
A Zero-Shot Framework for Sketch based Image Retrieval
| Title | A Zero-Shot Framework for Sketch based Image Retrieval |
| Authors | Sasi Kiran Yelamarthi, Shiva Krishna Reddy, Ashish Mishra, Anurag Mittal |
| Abstract | Sketch-based image retrieval (SBIR) is the task of retrieving images from a natural image database that correspond to a given hand-drawn sketch. Ideally, an SBIR model should learn to associate components in the sketch (say, feet, tail, etc.) with the corresponding components in the image. However, current evaluation methods simply focus only on coarse-grained evaluation where the focus is on retrieving images which belong to the same class as the sketch but not necessarily having the same components as in the sketch. As a result, existing methods simply learn to associate sketches with classes seen during training and hence fail to generalize to unseen classes. In this paper, we propose a new bench mark for zero-shot SBIR where the model is evaluated on novel classes that are not seen during training. We show through extensive experiments that existing models for SBIR which are trained in a discriminative setting learn only class specific mappings and fail to generalize to the proposed zero-shot setting. To circumvent this, we propose a generative approach for the SBIR task by proposing deep conditional generative models which take the sketch as an input and fill the missing information stochastically. Experiments on this new benchmark created from the “Sketchy” dataset, which is a large-scale database of sketch-photo pairs demonstrate that the performance of these generative models is significantly better than several state-of-the-art approaches in the proposed zero-shot framework of the coarse-grained SBIR task. |
| Tasks | Image Retrieval, Sketch-Based Image Retrieval |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Sasikiran_Yelamarthi_A_Zero-Shot_Framework_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Sasikiran_Yelamarthi_A_Zero-Shot_Framework_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/a-zero-shot-framework-for-sketch-based-image-1 |
| Repo | |
| Framework | |
Ground-Truth Adversarial Examples
| Title | Ground-Truth Adversarial Examples |
| Authors | Nicholas Carlini, Guy Katz, Clark Barrett, David L. Dill |
| Abstract | The ability to deploy neural networks in real-world, safety-critical systems is severely limited by the presence of adversarial examples: slightly perturbed inputs that are misclassified by the network. In recent years, several techniques have been proposed for training networks that are robust to such examples; and each time stronger attacks have been devised, demonstrating the shortcomings of existing defenses. This highlights a key difficulty in designing an effective defense: the inability to assess a network’s robustness against future attacks. We propose to address this difficulty through formal verification techniques. We construct ground truths: adversarial examples with a provably-minimal distance from a given input point. We demonstrate how ground truths can serve to assess the effectiveness of attack techniques, by comparing the adversarial examples produced by those attacks to the ground truths; and also of defense techniques, by computing the distance to the ground truths before and after the defense is applied, and measuring the improvement. We use this technique to assess recently suggested attack and defense techniques. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=Hki-ZlbA- |
| https://openreview.net/pdf?id=Hki-ZlbA- | |
| PWC | https://paperswithcode.com/paper/ground-truth-adversarial-examples |
| Repo | |
| Framework | |
Learning and Memorization
| Title | Learning and Memorization |
| Authors | Satrajit Chatterjee |
| Abstract | In the machine learning research community, it is generally believed that there is a tension between memorization and generalization. In this work we examine to what extent this tension exists by exploring if it is possible to generalize by memorizing alone. Although direct memorization with a lookup table obviously does not generalize, we find that introducing depth in the form of a network of support-limited lookup tables leads to generalization that is significantly above chance and closer to those obtained by standard learning algorithms on several tasks derived from MNIST and CIFAR-10. Furthermore, we demonstrate through a series of empirical results that our approach allows for a smooth tradeoff between memorization and generalization and exhibits some of the most salient characteristics of neural networks: depth improves performance; random data can be memorized and yet there is generalization on real data; and memorizing random data is harder in a certain sense than memorizing real data. The extreme simplicity of the algorithm and potential connections with generalization theory point to several interesting directions for future research. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2080 |
| http://proceedings.mlr.press/v80/chatterjee18a/chatterjee18a.pdf | |
| PWC | https://paperswithcode.com/paper/learning-and-memorization |
| Repo | |
| Framework | |
Recognizing Emotions in Video Using Multimodal DNN Feature Fusion
| Title | Recognizing Emotions in Video Using Multimodal DNN Feature Fusion |
| Authors | Jennifer Williams, Steven Kleinegesse, Ramona Comanescu, Oana Radu |
| Abstract | We present our system description of input-level multimodal fusion of audio, video, and text for recognition of emotions and their intensities for the 2018 First Grand Challenge on Computational Modeling of Human Multimodal Language. Our proposed approach is based on input-level feature fusion with sequence learning from Bidirectional Long-Short Term Memory (BLSTM) deep neural networks (DNNs). We show that our fusion approach outperforms unimodal predictors. Our system performs 6-way simultaneous classification and regression, allowing for overlapping emotion labels in a video segment. This leads to an overall binary accuracy of 90{%}, overall 4-class accuracy of 89.2{%} and an overall mean-absolute-error (MAE) of 0.12. Our work shows that an early fusion technique can effectively predict the presence of multi-label emotions as well as their coarse-grained intensities. The presented multimodal approach creates a simple and robust baseline on this new Grand Challenge dataset. Furthermore, we provide a detailed analysis of emotion intensity distributions as output from our DNN, as well as a related discussion concerning the inherent difficulty of this task. |
| Tasks | Emotion Recognition, Machine Translation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3302/ |
| https://www.aclweb.org/anthology/W18-3302 | |
| PWC | https://paperswithcode.com/paper/recognizing-emotions-in-video-using |
| Repo | |
| Framework | |
