Paper Group NANR 20
Neural Tensor Networks with Diagonal Slice Matrices. Quantifying Qualitative Data for Understanding Controversial Issues. Machine Learning by Two-Dimensional Hierarchical Tensor Networks: A Quantum Information Theoretic Perspective on Deep Architectures. Intertextual Correspondence for Integrating Corpora. Human Needs Categorization of Affective Ev …
Neural Tensor Networks with Diagonal Slice Matrices
| Title | Neural Tensor Networks with Diagonal Slice Matrices |
| Authors | Takahiro Ishihara, Katsuhiko Hayashi, Hitoshi Manabe, Masashi Shimbo, Masaaki Nagata |
| Abstract | Although neural tensor networks (NTNs) have been successful in many NLP tasks, they require a large number of parameters to be estimated, which often leads to overfitting and a long training time. We address these issues by applying eigendecomposition to each slice matrix of a tensor to reduce its number of paramters. First, we evaluate our proposed NTN models on knowledge graph completion. Second, we extend the models to recursive NTNs (RNTNs) and evaluate them on logical reasoning tasks. These experiments show that our proposed models learn better and faster than the original (R)NTNs. |
| Tasks | Knowledge Graph Completion, Sentiment Analysis, Tensor Networks |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1047/ |
| https://www.aclweb.org/anthology/N18-1047 | |
| PWC | https://paperswithcode.com/paper/neural-tensor-networks-with-diagonal-slice |
| Repo | |
| Framework | |
Quantifying Qualitative Data for Understanding Controversial Issues
| Title | Quantifying Qualitative Data for Understanding Controversial Issues |
| Authors | Michael Wojatzki, Saif Mohammad, Torsten Zesch, Svetlana Kiritchenko |
| Abstract | |
| Tasks | Argument Mining, Decision Making, Sentiment Analysis, Stance Detection |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1224/ |
| https://www.aclweb.org/anthology/L18-1224 | |
| PWC | https://paperswithcode.com/paper/quantifying-qualitative-data-for |
| Repo | |
| Framework | |
Machine Learning by Two-Dimensional Hierarchical Tensor Networks: A Quantum Information Theoretic Perspective on Deep Architectures
| Title | Machine Learning by Two-Dimensional Hierarchical Tensor Networks: A Quantum Information Theoretic Perspective on Deep Architectures |
| Authors | Ding Liu, Shi-Ju Ran, Peter Wittek, Cheng Peng, Raul Blázquez García, Gang Su, Maciej Lewenstein |
| Abstract | The resemblance between the methods used in studying quantum-many body physics and in machine learning has drawn considerable attention. In particular, tensor networks (TNs) and deep learning architectures bear striking similarities to the extent that TNs can be used for machine learning. Previous results used one-dimensional TNs in image recognition, showing limited scalability and a request of high bond dimension. In this work, we train two-dimensional hierarchical TNs to solve image recognition problems, using a training algorithm derived from the multipartite entanglement renormalization ansatz (MERA). This approach overcomes scalability issues and implies novel mathematical connections among quantum many-body physics, quantum information theory, and machine learning. While keeping the TN unitary in the training phase, TN states can be defined, which optimally encodes each class of the images into a quantum many-body state. We study the quantum features of the TN states, including quantum entanglement and fidelity. We suggest these quantities could be novel properties that characterize the image classes, as well as the machine learning tasks. Our work could be further applied to identifying possible quantum properties of certain artificial intelligence methods. |
| Tasks | Tensor Networks |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=ryF-cQ6T- |
| https://openreview.net/pdf?id=ryF-cQ6T- | |
| PWC | https://paperswithcode.com/paper/machine-learning-by-two-dimensional-1 |
| Repo | |
| Framework | |
Intertextual Correspondence for Integrating Corpora
| Title | Intertextual Correspondence for Integrating Corpora |
| Authors | Jacky Visser, Rory Duthie, John Lawrence, Chris Reed |
| Abstract | |
| Tasks | Argument Mining |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1554/ |
| https://www.aclweb.org/anthology/L18-1554 | |
| PWC | https://paperswithcode.com/paper/intertextual-correspondence-for-integrating |
| Repo | |
| Framework | |
Human Needs Categorization of Affective Events Using Labeled and Unlabeled Data
| Title | Human Needs Categorization of Affective Events Using Labeled and Unlabeled Data |
| Authors | Haibo Ding, Ellen Riloff |
| Abstract | We often talk about events that impact us positively or negatively. For example {}I got a job{''} is good news, but {}I lost my job{''} is bad news. When we discuss an event, we not only understand its affective polarity but also the reason why the event is beneficial or detrimental. For example, getting or losing a job has affective polarity primarily because it impacts us financially. Our work aims to categorize affective events based upon human need categories that often explain people{'}s motivations and desires: PHYSIOLOGICAL, HEALTH, LEISURE, SOCIAL, FINANCIAL, COGNITION, and FREEDOM. We create classification models based on event expressions as well as models that use contexts surrounding event mentions. We also design a co-training model that learns from unlabeled data by simultaneously training event expression and event context classifiers in an iterative learning process. Our results show that co-training performs well, producing substantially better results than the individual classifiers. |
| Tasks | Reading Comprehension, Text Summarization |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1174/ |
| https://www.aclweb.org/anthology/N18-1174 | |
| PWC | https://paperswithcode.com/paper/human-needs-categorization-of-affective |
| Repo | |
| Framework | |
TreeAnnotator: Versatile Visual Annotation of Hierarchical Text Relations
| Title | TreeAnnotator: Versatile Visual Annotation of Hierarchical Text Relations |
| Authors | Philipp Helfrich, Elias Rieb, Giuseppe Abrami, Andy L{"u}cking, Alex Mehler, er |
| Abstract | |
| Tasks | Lemmatization, Tokenization |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1308/ |
| https://www.aclweb.org/anthology/L18-1308 | |
| PWC | https://paperswithcode.com/paper/treeannotator-versatile-visual-annotation-of |
| Repo | |
| Framework | |
Learning a Mixture of Two Multinomial Logits
| Title | Learning a Mixture of Two Multinomial Logits |
| Authors | Flavio Chierichetti, Ravi Kumar, Andrew Tomkins |
| Abstract | The classical Multinomial Logit (MNL) is a behavioral model for user choice. In this model, a user is offered a slate of choices (a subset of a finite universe of $n$ items), and selects exactly one item from the slate, each with probability proportional to its (positive) weight. Given a set of observed slates and choices, the likelihood-maximizing item weights are easy to learn at scale, and easy to interpret. However, the model fails to represent common real-world behavior. As a result, researchers in user choice often turn to mixtures of MNLs, which are known to approximate a large class of models of rational user behavior. Unfortunately, the only known algorithms for this problem have been heuristic in nature. In this paper we give the first polynomial-time algorithms for exact learning of uniform mixtures of two MNLs. Interestingly, the parameters of the model can be learned for any $n$ by sampling the behavior of random users only on slates of sizes 2 and 3; in contrast, we show that slates of size 2 are insufficient by themselves. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2238 |
| http://proceedings.mlr.press/v80/chierichetti18a/chierichetti18a.pdf | |
| PWC | https://paperswithcode.com/paper/learning-a-mixture-of-two-multinomial-logits |
| Repo | |
| Framework | |
SentiArabic: A Sentiment Analyzer for Standard Arabic
| Title | SentiArabic: A Sentiment Analyzer for Standard Arabic |
| Authors | Esk, Ramy er |
| Abstract | |
| Tasks | Arabic Sentiment Analysis, Lemmatization, Morphological Analysis, Sentiment Analysis |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1195/ |
| https://www.aclweb.org/anthology/L18-1195 | |
| PWC | https://paperswithcode.com/paper/sentiarabic-a-sentiment-analyzer-for-standard |
| Repo | |
| Framework | |
Monocular Depth Estimation Using Whole Strip Masking and Reliability-Based Refinement
| Title | Monocular Depth Estimation Using Whole Strip Masking and Reliability-Based Refinement |
| Authors | Minhyeok Heo, Jaehan Lee, Kyung-Rae Kim, Han-Ul Kim, Chang-Su Kim |
| Abstract | We propose a monocular depth estimation algorithm, which extracts a depth map from a single image, based on whole strip masking (WSM) and reliability-based refinement. First, we develop a convolutional neural network (CNN) tailored for the depth estimation. Specifically, we design a novel filter, called WSM, to exploit the tendency that a scene has similar depths in horizonal or vertical directions. The proposed CNN combines WSM upsampling blocks with the ResNet encoder. Second, we measure the reliability of an estimated depth, by appending additional layers to the main CNN. Using the reliability information, we perform conditional random field (CRF) optimization to refine the estimated depth map. Extensive experimental results demonstrate that the proposed algorithm provides the state-of-the-art depth estimation performance, outperforming conventional algorithms significantly. |
| Tasks | Depth Estimation, Monocular Depth Estimation |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Minhyeok_Heo_Monocular_Depth_Estimation_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Minhyeok_Heo_Monocular_Depth_Estimation_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/monocular-depth-estimation-using-whole-strip |
| Repo | |
| Framework | |
Sentiment Analysis by Capsules
| Title | Sentiment Analysis by Capsules |
| Authors | Yequan Wang, Aixin Sun, Jialong Han, Ying Liu, Xiaoyan Zhu |
| Abstract | In this paper, we propose RNN-Capsule, a capsule model based on Recurrent Neural Network (RNN) for sentiment analysis. For a given problem, one capsule is built for each sentiment category e.g., ‘positive’ and ‘negative’. Each capsule has an attribute, a state, and three modules: representation module, probability module, and reconstruction module. The attribute of a capsule is the assigned sentiment category. Given an instance encoded in hidden vectors by a typical RNN, the representation module builds capsule representation by the attention mechanism. Based on capsule representation, the probability module computes the capsule’s state probability. A capsule’s state is active if its state probability is the largest among all capsules for the given instance, and inactive otherwise. On two benchmark datasets (i.e., Movie Review and Stanford Sentiment Treebank) and one proprietary dataset (i.e., Hospital Feedback), we show that RNN-Capsule achieves state-of-the-art performance on sentiment classification. More importantly, without using any linguistic knowledge, RNN-Capsule is capable of outputting words with sentiment tendencies reflecting capsules’ attributes. The words well reflect the domain specificity of the dataset. |
| Tasks | Sentiment Analysis |
| Published | 2018-02-01 |
| URL | https://ntunlpsg.github.io/publication/2018_2_ai/ |
| https://www.researchgate.net/publication/323257127_Sentiment_Analysis_by_Capsules/download | |
| PWC | https://paperswithcode.com/paper/sentiment-analysis-by-capsules |
| Repo | |
| Framework | |
Cross-View Training for Semi-Supervised Learning
| Title | Cross-View Training for Semi-Supervised Learning |
| Authors | Kevin Clark, Thang Luong, Quoc V. Le |
| Abstract | We present Cross-View Training (CVT), a simple but effective method for deep semi-supervised learning. On labeled examples, the model is trained with standard cross-entropy loss. On an unlabeled example, the model first performs inference (acting as a “teacher”) to produce soft targets. The model then learns from these soft targets (acting as a ``"student”). We deviate from prior work by adding multiple auxiliary student prediction layers to the model. The input to each student layer is a sub-network of the full model that has a restricted view of the input (e.g., only seeing one region of an image). The students can learn from the teacher (the full model) because the teacher sees more of each example. Concurrently, the students improve the quality of the representations used by the teacher as they learn to make predictions with limited data. When combined with Virtual Adversarial Training, CVT improves upon the current state-of-the-art on semi-supervised CIFAR-10 and semi-supervised SVHN. We also apply CVT to train models on five natural language processing tasks using hundreds of millions of sentences of unlabeled data. On all tasks CVT substantially outperforms supervised learning alone, resulting in models that improve upon or are competitive with the current state-of-the-art. | |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=BJubPWZRW |
| https://openreview.net/pdf?id=BJubPWZRW | |
| PWC | https://paperswithcode.com/paper/cross-view-training-for-semi-supervised |
| Repo | |
| Framework | |
Alternating optimization of decision trees, with application to learning sparse oblique trees
| Title | Alternating optimization of decision trees, with application to learning sparse oblique trees |
| Authors | Miguel A. Carreira-Perpinan, Pooya Tavallali |
| Abstract | Learning a decision tree from data is a difficult optimization problem. The most widespread algorithm in practice, dating to the 1980s, is based on a greedy growth of the tree structure by recursively splitting nodes, and possibly pruning back the final tree. The parameters (decision function) of an internal node are approximately estimated by minimizing an impurity measure. We give an algorithm that, given an input tree (its structure and the parameter values at its nodes), produces a new tree with the same or smaller structure but new parameter values that provably lower or leave unchanged the misclassification error. This can be applied to both axis-aligned and oblique trees and our experiments show it consistently outperforms various other algorithms while being highly scalable to large datasets and trees. Further, the same algorithm can handle a sparsity penalty, so it can learn sparse oblique trees, having a structure that is a subset of the original tree and few nonzero parameters. This combines the best of axis-aligned and oblique trees: flexibility to model correlated data, low generalization error, fast inference and interpretable nodes that involve only a few features in their decision. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7397-alternating-optimization-of-decision-trees-with-application-to-learning-sparse-oblique-trees |
| http://papers.nips.cc/paper/7397-alternating-optimization-of-decision-trees-with-application-to-learning-sparse-oblique-trees.pdf | |
| PWC | https://paperswithcode.com/paper/alternating-optimization-of-decision-trees |
| Repo | |
| Framework | |
Censoring Representations with Multiple-Adversaries over Random Subspaces
| Title | Censoring Representations with Multiple-Adversaries over Random Subspaces |
| Authors | Yusuke Iwasawa, Kotaro Nakayama, Yutaka Matsuo |
| Abstract | Adversarial feature learning (AFL) is one of the promising ways for explicitly constrains neural networks to learn desired representations; for example, AFL could help to learn anonymized representations so as to avoid privacy issues. AFL learn such a representations by training the networks to deceive the adversary that predict the sensitive information from the network, and therefore, the success of the AFL heavily relies on the choice of the adversary. This paper proposes a novel design of the adversary, {\em multiple adversaries over random subspaces} (MARS) that instantiate the concept of the {\em volunerableness}. The proposed method is motivated by an assumption that deceiving an adversary could fail to give meaningful information if the adversary is easily fooled, and adversary rely on single classifier suffer from this issues. In contrast, the proposed method is designed to be less vulnerable, by utilizing the ensemble of independent classifiers where each classifier tries to predict sensitive variables from a different {\em subset} of the representations. The empirical validations on three user-anonymization tasks show that our proposed method achieves state-of-the-art performances in all three datasets without significantly harming the utility of data. This is significant because it gives new implications about designing the adversary, which is important to improve the performance of AFL. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=ByuP8yZRb |
| https://openreview.net/pdf?id=ByuP8yZRb | |
| PWC | https://paperswithcode.com/paper/censoring-representations-with-multiple |
| Repo | |
| Framework | |
Adding Syntactic Annotations to Flickr30k Entities Corpus for Multimodal Ambiguous Prepositional-Phrase Attachment Resolution
| Title | Adding Syntactic Annotations to Flickr30k Entities Corpus for Multimodal Ambiguous Prepositional-Phrase Attachment Resolution |
| Authors | Sebastien Delecraz, Alexis Nasr, Frederic Bechet, Benoit Favre |
| Abstract | |
| Tasks | Prepositional Phrase Attachment, Text Generation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1716/ |
| https://www.aclweb.org/anthology/L18-1716 | |
| PWC | https://paperswithcode.com/paper/adding-syntactic-annotations-to-flickr30k |
| Repo | |
| Framework | |
A Swedish Cookie-Theft Corpus
| Title | A Swedish Cookie-Theft Corpus |
| Authors | Dimitrios Kokkinakis, Kristina Lundholm Fors, Kathleen Fraser, Arto Nordlund |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1200/ |
| https://www.aclweb.org/anthology/L18-1200 | |
| PWC | https://paperswithcode.com/paper/a-swedish-cookie-theft-corpus |
| Repo | |
| Framework | |
