Paper Group NANR 214
A Notion of Semantic Coherence for Underspecified Semantic Representation. Building a Corpus for Personality-dependent Natural Language Understanding and Generation. Predicting Psychological Health from Childhood Essays with Convolutional Neural Networks for the CLPsych 2018 Shared Task (Team UKNLP). The New Propbank: Aligning Propbank with AMR thr …
A Notion of Semantic Coherence for Underspecified Semantic Representation
Title | A Notion of Semantic Coherence for Underspecified Semantic Representation |
Authors | Mehdi Manshadi, Daniel Gildea, James F. Allen |
Abstract | The general problem of finding satisfying solutions to constraint-based underspecified representations of quantifier scope is NP-complete. Existing frameworks, including Dominance Graphs, Minimal Recursion Semantics, and Hole Semantics, have struggled to balance expressivity and tractability in order to cover real natural language sentences with efficient algorithms. We address this trade-off with a general principle of coherence, which requires that every variable introduced in the domain of discourse must contribute to the overall semantics of the sentence. We show that every underspecified representation meeting this criterion can be efficiently processed, and that our set of representations subsumes all previously identified tractable sets. |
Tasks | |
Published | 2018-03-01 |
URL | https://www.aclweb.org/anthology/J18-1003/ |
https://www.aclweb.org/anthology/J18-1003 | |
PWC | https://paperswithcode.com/paper/a-notion-of-semantic-coherence-for |
Repo | |
Framework | |
Building a Corpus for Personality-dependent Natural Language Understanding and Generation
Title | Building a Corpus for Personality-dependent Natural Language Understanding and Generation |
Authors | Ricelli Ramos, Georges Neto, Barbara Silva, Danielle Monteiro, Iv Paraboni, r{'e}, Rafael Dias |
Abstract | |
Tasks | Text Generation |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1183/ |
https://www.aclweb.org/anthology/L18-1183 | |
PWC | https://paperswithcode.com/paper/building-a-corpus-for-personality-dependent |
Repo | |
Framework | |
Predicting Psychological Health from Childhood Essays with Convolutional Neural Networks for the CLPsych 2018 Shared Task (Team UKNLP)
Title | Predicting Psychological Health from Childhood Essays with Convolutional Neural Networks for the CLPsych 2018 Shared Task (Team UKNLP) |
Authors | Anthony Rios, Tung Tran, Ramakanth Kavuluru |
Abstract | This paper describes the systems we developed for tasks A and B of the 2018 CLPsych shared task. The first task (task A) focuses on predicting behavioral health scores at age 11 using childhood essays. The second task (task B) asks participants to predict future psychological distress at ages 23, 33, 42, and 50 using the age 11 essays. We propose two convolutional neural network based methods that map each task to a regression problem. Among seven teams we ranked third on task A with disattenuated Pearson correlation (DPC) score of 0.5587. Likewise, we ranked third on task B with an average DPC score of 0.3062. |
Tasks | |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/W18-0611/ |
https://www.aclweb.org/anthology/W18-0611 | |
PWC | https://paperswithcode.com/paper/predicting-psychological-health-from-1 |
Repo | |
Framework | |
The New Propbank: Aligning Propbank with AMR through POS Unification
Title | The New Propbank: Aligning Propbank with AMR through POS Unification |
Authors | Tim O{'}Gorman, Sameer Pradhan, Martha Palmer, Julia Bonn, Katie Conger, James Gung |
Abstract | |
Tasks | Semantic Role Labeling |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1231/ |
https://www.aclweb.org/anthology/L18-1231 | |
PWC | https://paperswithcode.com/paper/the-new-propbank-aligning-propbank-with-amr |
Repo | |
Framework | |
Automatic Poetry Generation with Mutual Reinforcement Learning
Title | Automatic Poetry Generation with Mutual Reinforcement Learning |
Authors | Xiaoyuan Yi, Maosong Sun, Ruoyu Li, Wenhao Li |
Abstract | Poetry is one of the most beautiful forms of human language art. As a crucial step towards computer creativity, automatic poetry generation has drawn researchers{'} attention for decades. In recent years, some neural models have made remarkable progress in this task. However, they are all based on maximum likelihood estimation, which only learns common patterns of the corpus and results in loss-evaluation mismatch. Human experts evaluate poetry in terms of some specific criteria, instead of word-level likelihood. To handle this problem, we directly model the criteria and use them as explicit rewards to guide gradient update by reinforcement learning, so as to motivate the model to pursue higher scores. Besides, inspired by writing theories, we propose a novel mutual reinforcement learning schema. We simultaneously train two learners (generators) which learn not only from the teacher (rewarder) but also from each other to further improve performance. We experiment on Chinese poetry. Based on a strong basic model, our method achieves better results and outperforms the current state-of-the-art method. |
Tasks | |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/D18-1353/ |
https://www.aclweb.org/anthology/D18-1353 | |
PWC | https://paperswithcode.com/paper/automatic-poetry-generation-with-mutual |
Repo | |
Framework | |
Maximum-Entropy Fine Grained Classification
Title | Maximum-Entropy Fine Grained Classification |
Authors | Abhimanyu Dubey, Otkrist Gupta, Ramesh Raskar, Nikhil Naik |
Abstract | Fine-Grained Visual Classification (FGVC) is an important computer vision problem that involves small diversity within the different classes, and often requires expert annotators to collect data. Utilizing this notion of small visual diversity, we revisit Maximum-Entropy learning in the context of fine-grained classification, and provide a training routine that maximizes the entropy of the output probability distribution for training convolutional neural networks on FGVC tasks. We provide a theoretical as well as empirical justification of our approach, and achieve state-of-the-art performance across a variety of classification tasks in FGVC, that can potentially be extended to any fine-tuning task. Our method is robust to different hyperparameter values, amount of training data and amount of training label noise and can hence be a valuable tool in many similar problems. |
Tasks | Fine-Grained Image Classification |
Published | 2018-12-01 |
URL | http://papers.nips.cc/paper/7344-maximum-entropy-fine-grained-classification |
http://papers.nips.cc/paper/7344-maximum-entropy-fine-grained-classification.pdf | |
PWC | https://paperswithcode.com/paper/maximum-entropy-fine-grained-classification |
Repo | |
Framework | |
Cut-Pursuit Algorithm for Regularizing Nonsmooth Functionals with Graph Total Variation
Title | Cut-Pursuit Algorithm for Regularizing Nonsmooth Functionals with Graph Total Variation |
Authors | Hugo Raguet, Loic Landrieu |
Abstract | We present an extension of the cut-pursuit algorithm, introduced by Landrieu and Obozinski (2017), to the graph total-variation regularization of functions with a separable nondifferentiable part. We propose a modified algorithmic scheme as well as adapted proofs of convergence. We also present a heuristic approach for handling the cases in which the values associated to each vertex of the graph are multidimensional. The performance of our algorithm, which we demonstrate on difficult, ill-conditioned large-scale inverse and learning problems, is such that it may in practice extend the scope of application of the total-variation regularization. |
Tasks | |
Published | 2018-07-01 |
URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2392 |
http://proceedings.mlr.press/v80/raguet18a/raguet18a.pdf | |
PWC | https://paperswithcode.com/paper/cut-pursuit-algorithm-for-regularizing |
Repo | |
Framework | |
Bootstrapping a Neural Conversational Agent with Dialogue Self-Play, Crowdsourcing and On-Line Reinforcement Learning
Title | Bootstrapping a Neural Conversational Agent with Dialogue Self-Play, Crowdsourcing and On-Line Reinforcement Learning |
Authors | Pararth Shah, Dilek Hakkani-T{"u}r, Bing Liu, Gokhan T{"u}r |
Abstract | End-to-end neural models show great promise towards building conversational agents that are trained from data and on-line experience using supervised and reinforcement learning. However, these models require a large corpus of dialogues to learn effectively. For goal-oriented dialogues, such datasets are expensive to collect and annotate, since each task involves a separate schema and database of entities. Further, the Wizard-of-Oz approach commonly used for dialogue collection does not provide sufficient coverage of salient dialogue flows, which is critical for guaranteeing an acceptable task completion rate in consumer-facing conversational agents. In this paper, we study a recently proposed approach for building an agent for arbitrary tasks by combining dialogue self-play and crowd-sourcing to generate fully-annotated dialogues with diverse and natural utterances. We discuss the advantages of this approach for industry applications of conversational agents, wherein an agent can be rapidly bootstrapped to deploy in front of users and further optimized via interactive learning from actual users of the system. |
Tasks | |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/N18-3006/ |
https://www.aclweb.org/anthology/N18-3006 | |
PWC | https://paperswithcode.com/paper/bootstrapping-a-neural-conversational-agent |
Repo | |
Framework | |
On the Generalization Effects of DenseNet Model Structures
Title | On the Generalization Effects of DenseNet Model Structures |
Authors | Yin Liu, Vincent Chen |
Abstract | Modern neural network architectures take advantage of increasingly deeper layers, and various advances in their structure to achieve better performance. While traditional explicit regularization techniques like dropout, weight decay, and data augmentation are still being used in these new models, little about the regularization and generalization effects of these new structures have been studied. Besides being deeper than their predecessors, could newer architectures like ResNet and DenseNet also benefit from their structures’ implicit regularization properties? In this work, we investigate the skip connection’s effect on network’s generalization features. Through experiments, we show that certain neural network architectures contribute to their generalization abilities. Specifically, we study the effect that low-level features have on generalization performance when they are introduced to deeper layers in DenseNet, ResNet as well as networks with ‘skip connections’. We show that these low-level representations do help with generalization in multiple settings when both the quality and quantity of training data is decreased. |
Tasks | Data Augmentation |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=rJbs5gbRW |
https://openreview.net/pdf?id=rJbs5gbRW | |
PWC | https://paperswithcode.com/paper/on-the-generalization-effects-of-densenet |
Repo | |
Framework | |
BinaryFlex: On-the-Fly Kernel Generation in Binary Convolutional Networks
Title | BinaryFlex: On-the-Fly Kernel Generation in Binary Convolutional Networks |
Authors | Vincent W.-S. Tseng, Sourav Bhattachary, Javier Fernández Marqués, Milad Alizadeh, Catherine Tong, Nicholas Donald Lane |
Abstract | In this work we present BinaryFlex, a neural network architecture that learns weighting coefficients of predefined orthogonal binary basis instead of the conventional approach of learning directly the convolutional filters. We have demonstrated the feasibility of our approach for complex computer vision datasets such as ImageNet. Our architecture trained on ImageNet is able to achieve top-5 accuracy of 65.7% while being around 2x smaller than binary networks capable of achieving similar accuracy levels. By using deterministic basis, that can be generated on-the-fly very efficiently, our architecture offers a great deal of flexibility in memory footprint when deploying in constrained microcontroller devices. |
Tasks | |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=HyIFzx-0b |
https://openreview.net/pdf?id=HyIFzx-0b | |
PWC | https://paperswithcode.com/paper/binaryflex-on-the-fly-kernel-generation-in |
Repo | |
Framework | |
Multi Modal Distance - An Approach to Stemma Generation With Weighting
Title | Multi Modal Distance - An Approach to Stemma Generation With Weighting |
Authors | Armin Hoenen |
Abstract | |
Tasks | |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1332/ |
https://www.aclweb.org/anthology/L18-1332 | |
PWC | https://paperswithcode.com/paper/multi-modal-distance-an-approach-to-stemma |
Repo | |
Framework | |
Hallucinating brains with artificial brains
Title | Hallucinating brains with artificial brains |
Authors | Peiye Zhuang, Alexander G. Schwing, Oluwasanmi Koyejo |
Abstract | Human brain function as measured by functional magnetic resonance imaging (fMRI), exhibits a rich diversity. In response, understanding the individual variability of brain function and its association with behavior has become one of the major concerns in modern cognitive neuroscience. Our work is motivated by the view that generative models provide a useful tool for understanding this variability. To this end, this manuscript presents two novel generative models trained on real neuroimaging data which synthesize task-dependent functional brain images. Brain images are high dimensional tensors which exhibit structured spatial correlations. Thus, both models are 3D conditional Generative Adversarial networks (GANs) which apply Convolutional Neural Networks (CNNs) to learn an abstraction of brain image representations. Our results show that the generated brain images are diverse, yet task dependent. In addition to qualitative evaluation, we utilize the generated synthetic brain volumes as additional training data to improve downstream fMRI classifiers (also known as decoding, or brain reading). Our approach achieves significant improvements for a variety of datasets, classifi- cation tasks and evaluation scores. Our classification results provide a quantitative evaluation of the quality of the generated images, and also serve as an additional contribution of this manuscript. |
Tasks | |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=BJaU__eCZ |
https://openreview.net/pdf?id=BJaU__eCZ | |
PWC | https://paperswithcode.com/paper/hallucinating-brains-with-artificial-brains |
Repo | |
Framework | |
UNSUPERVISED SENTENCE EMBEDDING USING DOCUMENT STRUCTURE-BASED CONTEXT
Title | UNSUPERVISED SENTENCE EMBEDDING USING DOCUMENT STRUCTURE-BASED CONTEXT |
Authors | Taesung Lee, Youngja Park |
Abstract | We present a new unsupervised method for learning general-purpose sentence embeddings. Unlike existing methods which rely on local contexts, such as words inside the sentence or immediately neighboring sentences, our method selects, for each target sentence, influential sentences in the entire document based on a document structure. We identify a dependency structure of sentences using metadata or text styles. Furthermore, we propose a novel out-of-vocabulary word handling technique to model many domain-specific terms, which were mostly discarded by existing sentence embedding methods. We validate our model on several tasks showing 30% precision improvement in coreference resolution in a technical domain, and 7.5% accuracy increase in paraphrase detection compared to baselines. |
Tasks | Coreference Resolution, Sentence Embedding, Sentence Embeddings |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=H1a37GWCZ |
https://openreview.net/pdf?id=H1a37GWCZ | |
PWC | https://paperswithcode.com/paper/unsupervised-sentence-embedding-using |
Repo | |
Framework | |
Cross-Domain Review Helpfulness Prediction Based on Convolutional Neural Networks with Auxiliary Domain Discriminators
Title | Cross-Domain Review Helpfulness Prediction Based on Convolutional Neural Networks with Auxiliary Domain Discriminators |
Authors | Cen Chen, Yinfei Yang, Jun Zhou, Xiaolong Li, Forrest Sheng Bao |
Abstract | With the growing amount of reviews in e-commerce websites, it is critical to assess the helpfulness of reviews and recommend them accordingly to consumers. Recent studies on review helpfulness require plenty of labeled samples for each domain/category of interests. However, such an approach based on close-world assumption is not always practical, especially for domains with limited reviews or the {``}out-of-vocabulary{''} problem. Therefore, we propose a convolutional neural network (CNN) based model which leverages both word-level and character-based representations. To transfer knowledge between domains, we further extend our model to jointly model different domains with auxiliary domain discriminators. On the Amazon product review dataset, our approach significantly outperforms the state of the art in terms of both accuracy and cross-domain robustness. | |
Tasks | Machine Translation, Text Classification, Transfer Learning |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/N18-2095/ |
https://www.aclweb.org/anthology/N18-2095 | |
PWC | https://paperswithcode.com/paper/cross-domain-review-helpfulness-prediction |
Repo | |
Framework | |
RF-Based Fall Monitoring Using Convolutional Neural Networks
Title | RF-Based Fall Monitoring Using Convolutional Neural Networks |
Authors | Yonglong Tian, Guang-He Lee, Hao He, Chen-Yu Hsu, Dina Katabi |
Abstract | Falls are the top reason for fatal and non-fatal injuries among seniors. Existing solutions are based on wearable fall-alert sensors, but medical research has shown that they are ineffective, mostly because seniors do not wear them. These revelations have led to new passive sensors that infer falls by analyzing Radio Frequency (RF) signals in homes. Seniors can go about their lives as usual without the need to wear any device. While passive monitoring has made major advances, current approaches still cannot deal with the complexities of real-world scenarios. They typically train and test their classifiers on the same people in the same environments, and cannot generalize to new people or new environments. Further, they cannot separate motions from different people and can easily miss a fall in the presence of other motions. To overcome these limitations, we introduce Aryokee, an RF-based fall detection system that uses convolutional neural networks governed by a state machine. Aryokee works with new people and environments unseen in the training set. It also separates different sources of motion to increase robustness. Results from testing Aryokee with over 140 people performing 40 types of activities in 57 different environments show a recall of 94% and a precision of 92% in detecting falls. |
Tasks | RF-based Pose Estimation |
Published | 2018-09-01 |
URL | https://doi.org/10.1145/3264947 |
http://people.csail.mit.edu/yonglong/yonglong/rffall.pdf | |
PWC | https://paperswithcode.com/paper/rf-based-fall-monitoring-using-convolutional |
Repo | |
Framework | |