Paper Group NANR 245
Spot the Odd Man Out: Exploring the Associative Power of Lexical Resources. Towards Opinion Summarization of Customer Reviews. Voice Imitating Text-to-Speech Neural Networks. GraphBit: Bitwise Interaction Mining via Deep Reinforcement Learning. Neural Networks for irregularly observed continuous-time Stochastic Processes. Learning to Optimize Combi …
Spot the Odd Man Out: Exploring the Associative Power of Lexical Resources
| Title | Spot the Odd Man Out: Exploring the Associative Power of Lexical Resources |
| Authors | Gabriel Stanovsky, Mark Hopkins |
| Abstract | We propose Odd-Man-Out, a novel task which aims to test different properties of word representations. An Odd-Man-Out puzzle is composed of 5 (or more) words, and requires the system to choose the one which does not belong with the others. We show that this simple setup is capable of teasing out various properties of different popular lexical resources (like WordNet and pre-trained word embeddings), while being intuitive enough to annotate on a large scale. In addition, we propose a novel technique for training multi-prototype word representations, based on unsupervised clustering of ELMo embeddings, and show that it surpasses all other representations on all Odd-Man-Out collections. |
| Tasks | Natural Language Inference, Question Answering, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1182/ |
| https://www.aclweb.org/anthology/D18-1182 | |
| PWC | https://paperswithcode.com/paper/spot-the-odd-man-out-exploring-the |
| Repo | |
| Framework | |
Towards Opinion Summarization of Customer Reviews
| Title | Towards Opinion Summarization of Customer Reviews |
| Authors | Samuel Pecar |
| Abstract | In recent years, the number of texts has grown rapidly. For example, most review-based portals, like Yelp or Amazon, contain thousands of user-generated reviews. It is impossible for any human reader to process even the most relevant of these documents. The most promising tool to solve this task is a text summarization. Most existing approaches, however, work on small, homogeneous, English datasets, and do not account to multi-linguality, opinion shift, and domain effects. In this paper, we introduce our research plan to use neural networks on user-generated travel reviews to generate summaries that take into account shifting opinions over time. We outline future directions in summarization to address all of these issues. By resolving the existing problems, we will make it easier for users of review-sites to make more informed decisions. |
| Tasks | Abstractive Text Summarization, Decision Making, Text Summarization |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-3001/ |
| https://www.aclweb.org/anthology/P18-3001 | |
| PWC | https://paperswithcode.com/paper/towards-opinion-summarization-of-customer |
| Repo | |
| Framework | |
Voice Imitating Text-to-Speech Neural Networks
| Title | Voice Imitating Text-to-Speech Neural Networks |
| Authors | Younggun Lee, Taesu Kim, Soo-Young Lee |
| Abstract | We propose a neural text-to-speech (TTS) model that can imitate a new speaker’s voice using only a small amount of speech sample. We demonstrate voice imitation using only a 6-seconds long speech sample without any other information such as transcripts. Our model also enables voice imitation instantly without additional training of the model. We implemented the voice imitating TTS model by combining a speaker embedder network with a state-of-the-art TTS model, Tacotron. The speaker embedder network takes a new speaker’s speech sample and returns a speaker embedding. The speaker embedding with a target sentence are fed to Tacotron, and speech is generated with the new speaker’s voice. We show that the speaker embeddings extracted by the speaker embedder network can represent the latent structure in different voices. The generated speech samples from our model have comparable voice quality to the ones from existing multi-speaker TTS models. |
| Tasks | |
| Published | 2018-06-04 |
| URL | https://arxiv.org/abs/1806.00927 |
| https://arxiv.org/pdf/1806.00927 | |
| PWC | https://paperswithcode.com/paper/voice-imitating-text-to-speech-neural |
| Repo | |
| Framework | |
GraphBit: Bitwise Interaction Mining via Deep Reinforcement Learning
| Title | GraphBit: Bitwise Interaction Mining via Deep Reinforcement Learning |
| Authors | Yueqi Duan, Ziwei Wang, Jiwen Lu, Xudong Lin, Jie Zhou |
| Abstract | In this paper, we propose a GraphBit method to learn deep binary descriptors in a directed acyclic graph unsupervisedly, representing bitwise interactions as edges between the nodes of bits. Conventional binary representation learning methods enforce each element to be binarized into zero or one. However, there are elements lying in the boundary which suffer from doubtful binarization as ``ambiguous bits’'. Ambiguous bits fail to collect effective information for confident binarization, which are unreliable and sensitive to noise. We argue that there are implicit inner relationships between bits in binary descriptors, where the related bits can provide extra instruction as prior knowledge for ambiguity elimination. Specifically, we design a deep reinforcement learning model to learn the structure of the graph for bitwise interaction mining, reducing the uncertainty of binary codes by maximizing the mutual information with inputs and related bits, so that the ambiguous bits receive additional instruction from the graph for confident binarization. Due to the reliability of the proposed binary codes with bitwise interaction, we obtain an average improvement of 9.64%, 8.84% and 3.22% on the CIFAR-10, Brown and HPatches datasets respectively compared with the state-of-the-art unsupervised binary descriptors. | |
| Tasks | Representation Learning |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Duan_GraphBit_Bitwise_Interaction_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Duan_GraphBit_Bitwise_Interaction_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/graphbit-bitwise-interaction-mining-via-deep |
| Repo | |
| Framework | |
Neural Networks for irregularly observed continuous-time Stochastic Processes
| Title | Neural Networks for irregularly observed continuous-time Stochastic Processes |
| Authors | Francois W. Belletti, Alexander Ku, Joseph E. Gonzalez |
| Abstract | Designing neural networks for continuous-time stochastic processes is challenging, especially when observations are made irregularly. In this article, we analyze neural networks from a frame theoretic perspective to identify the sufficient conditions that enable smoothly recoverable representations of signals in L^2(R). Moreover, we show that, under certain assumptions, these properties hold even when signals are irregularly observed. As we converge to the family of (convolutional) neural networks that satisfy these conditions, we show that we can optimize our convolution filters while constraining them so that they effectively compute a Discrete Wavelet Transform. Such a neural network can efficiently divide the time-axis of a signal into orthogonal sub-spaces of different temporal scale and localization. We evaluate the resulting neural network on an assortment of synthetic and real-world tasks: parsimonious auto-encoding, video classification, and financial forecasting. |
| Tasks | Video Classification |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=S1fHmlbCW |
| https://openreview.net/pdf?id=S1fHmlbCW | |
| PWC | https://paperswithcode.com/paper/neural-networks-for-irregularly-observed |
| Repo | |
| Framework | |
Learning to Optimize Combinatorial Functions
| Title | Learning to Optimize Combinatorial Functions |
| Authors | Nir Rosenfeld, Eric Balkanski, Amir Globerson, Yaron Singer |
| Abstract | Submodular functions have become a ubiquitous tool in machine learning. They are learnable from data, and can be optimized efficiently and with guarantees. Nonetheless, recent negative results show that optimizing learned surrogates of submodular functions can result in arbitrarily bad approximations of the true optimum. Our goal in this paper is to highlight the source of this hardness, and propose an alternative criterion for optimizing general combinatorial functions from sampled data. We prove a tight equivalence showing that a class of functions is optimizable if and only if it can be learned. We provide efficient and scalable optimization algorithms for several function classes of interest, and demonstrate their utility on the task of optimally choosing trending social media items. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=1881 |
| http://proceedings.mlr.press/v80/rosenfeld18a/rosenfeld18a.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-optimize-combinatorial-functions |
| Repo | |
| Framework | |
Alpha-divergence bridges maximum likelihood and reinforcement learning in neural sequence generation
| Title | Alpha-divergence bridges maximum likelihood and reinforcement learning in neural sequence generation |
| Authors | Sotetsu Koyamada, Yuta Kikuchi, Atsunori Kanemura, Shin-ichi Maeda, Shin Ishii |
| Abstract | Neural sequence generation is commonly approached by using maximum- likelihood (ML) estimation or reinforcement learning (RL). However, it is known that they have their own shortcomings; ML presents training/testing discrepancy, whereas RL suffers from sample inefficiency. We point out that it is difficult to resolve all of the shortcomings simultaneously because of a tradeoff between ML and RL. In order to counteract these problems, we propose an objective function for sequence generation using α-divergence, which leads to an ML-RL integrated method that exploits better parts of ML and RL. We demonstrate that the proposed objective function generalizes ML and RL objective functions because it includes both as its special cases (ML corresponds to α → 0 and RL to α → 1). We provide a proposition stating that the difference between the RL objective function and the proposed one monotonically decreases with increasing α. Experimental results on machine translation tasks show that minimizing the proposed objective function achieves better sequence generation performance than ML-based methods. |
| Tasks | Machine Translation |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=H1Nyf7W0Z |
| https://openreview.net/pdf?id=H1Nyf7W0Z | |
| PWC | https://paperswithcode.com/paper/alpha-divergence-bridges-maximum-likelihood |
| Repo | |
| Framework | |
Keyphrases Extraction from User-Generated Contents in Healthcare Domain Using Long Short-Term Memory Networks
| Title | Keyphrases Extraction from User-Generated Contents in Healthcare Domain Using Long Short-Term Memory Networks |
| Authors | Ilham Fathy Saputra, Rahmad Mahendra, Alfan Farizki Wicaksono |
| Abstract | We propose keyphrases extraction technique to extract important terms from the healthcare user-generated contents. We employ deep learning architecture, i.e. Long Short-Term Memory, and leverage word embeddings, medical concepts from a knowledge base, and linguistic components as our features. The proposed model achieves 61.37{%} F-1 score. Experimental results indicate that our proposed approach outperforms the baseline methods, i.e. RAKE and CRF, on the task of extracting keyphrases from Indonesian health forum posts. |
| Tasks | Question Answering, Text Classification, Text Summarization, Word Embeddings |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2304/ |
| https://www.aclweb.org/anthology/W18-2304 | |
| PWC | https://paperswithcode.com/paper/keyphrases-extraction-from-user-generated |
| Repo | |
| Framework | |
Teaching Machines to Understand Baseball Games: Large-Scale Baseball Video Database for Multiple Video Understanding Tasks
| Title | Teaching Machines to Understand Baseball Games: Large-Scale Baseball Video Database for Multiple Video Understanding Tasks |
| Authors | Minho Shim, Young Hwi Kim, Kyungmin Kim, Seon Joo Kim |
| Abstract | A major obstacle in teaching machines to understand videos is the lack of training data, as creating temporal annotations for long videos requires a huge amount of human effort. To this end, we introduce a new large-scale baseball video dataset called the BBDB, which is produced semi-automatically by using play-by-play texts available online. The BBDB contains 4200 hours of baseball game videos with 400k temporally annotated activity segments. The new dataset has several major challenging factors compared to other datasets: 1) the dataset contains a large number of visually similar segments with different labels. 2) It can be used for many video understanding tasks including video recognition, localization, text-video alignment, video highlight generation, and data imbalance problem. To observe the potential of the BBDB, we conducted extensive experiments by running many different types of video understanding algorithms on our new dataset. The database is available at https://sites.google.com/site/eccv2018bbdb/ |
| Tasks | Video Alignment, Video Recognition, Video Understanding |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Minho_Shim_Teaching_Machines_to_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Minho_Shim_Teaching_Machines_to_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/teaching-machines-to-understand-baseball |
| Repo | |
| Framework | |
Proportional Allocation: Simple, Distributed, and Diverse Matching with High Entropy
| Title | Proportional Allocation: Simple, Distributed, and Diverse Matching with High Entropy |
| Authors | Shipra Agrawal, Morteza Zadimoghaddam, Vahab Mirrokni |
| Abstract | Inspired by many applications of bipartite matching in online advertising and machine learning, we study a simple and natural iterative proportional allocation algorithm: Maintain a priority score $\priority_a$ for each node $a\in \mathds{A}$ on one side of the bipartition, initialized as $\priority_a=1$. Iteratively allocate the nodes $i\in \impressions$ on the other side to eligible nodes in $\mathds{A}$ in proportion of their priority scores. After each round, for each node $a\in \mathds{A}$, decrease or increase the score $\priority_a$ based on whether it is over- or under- allocated. Our first result is that this simple, distributed algorithm converges to a $(1-\epsilon)$-approximate fractional $b$-matching solution in $O({\log n\over \epsilon^2} )$ rounds. We also extend the proportional allocation algorithm and convergence results to the maximum weighted matching problem, and show that the algorithm can be naturally tuned to produce maximum matching with high entropy. High entropy, in turn, implies additional desirable properties of this matching, e.g., it satisfies certain diversity and fairness (aka anonymity) properties that are desirable in a variety of applications in online advertising and machine learning. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2388 |
| http://proceedings.mlr.press/v80/agrawal18b/agrawal18b.pdf | |
| PWC | https://paperswithcode.com/paper/proportional-allocation-simple-distributed |
| Repo | |
| Framework | |
Fast and Accurate Text Classification: Skimming, Rereading and Early Stopping
| Title | Fast and Accurate Text Classification: Skimming, Rereading and Early Stopping |
| Authors | Keyi Yu, Yang Liu, Alexander G. Schwing, Jian Peng |
| Abstract | Recent advances in recurrent neural nets (RNNs) have shown much promise in many applications in natural language processing. For most of these tasks, such as sentiment analysis of customer reviews, a recurrent neural net model parses the entire review before forming a decision. We argue that reading the entire input is not always necessary in practice, since a lot of reviews are often easy to classify, i.e., a decision can be formed after reading some crucial sentences or words in the provided text. In this paper, we present an approach of fast reading for text classification. Inspired by several well-known human reading techniques, our approach implements an intelligent recurrent agent which evaluates the importance of the current snippet in order to decide whether to make a prediction, or to skip some texts, or to re-read part of the sentence. Our agent uses an RNN module to encode information from the past and the current tokens, and applies a policy module to form decisions. With an end-to-end training algorithm based on policy gradient, we train and test our agent on several text classification datasets and achieve both higher efficiency and better accuracy compared to previous approaches. |
| Tasks | Sentiment Analysis, Text Classification |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=ryZ8sz-Ab |
| https://openreview.net/pdf?id=ryZ8sz-Ab | |
| PWC | https://paperswithcode.com/paper/fast-and-accurate-text-classification |
| Repo | |
| Framework | |
Practical exact algorithm for trembling-hand equilibrium refinements in games
| Title | Practical exact algorithm for trembling-hand equilibrium refinements in games |
| Authors | Gabriele Farina, Nicola Gatti, Tuomas Sandholm |
| Abstract | Nash equilibrium strategies have the known weakness that they do not prescribe rational play in situations that are reached with zero probability according to the strategies themselves, for example, if players have made mistakes. Trembling-hand refinements—such as extensive-form perfect equilibria and quasi-perfect equilibria—remedy this problem in sound ways. Despite their appeal, they have not received attention in practice since no known algorithm for computing them scales beyond toy instances. In this paper, we design an exact polynomial-time algorithm for finding trembling-hand equilibria in zero-sum extensive-form games. It is several orders of magnitude faster than the best prior ones, numerically stable, and quickly solves game instances with tens of thousands of nodes in the game tree. It enables, for the first time, the use of trembling-hand refinements in practice. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7751-practical-exact-algorithm-for-trembling-hand-equilibrium-refinements-in-games |
| http://papers.nips.cc/paper/7751-practical-exact-algorithm-for-trembling-hand-equilibrium-refinements-in-games.pdf | |
| PWC | https://paperswithcode.com/paper/practical-exact-algorithm-for-trembling-hand |
| Repo | |
| Framework | |
Controlling Length in Abstractive Summarization Using a Convolutional Neural Network
| Title | Controlling Length in Abstractive Summarization Using a Convolutional Neural Network |
| Authors | Yizhu Liu, Zhiyi Luo, Kenny Zhu |
| Abstract | Convolutional neural networks (CNNs) have met great success in abstractive summarization, but they cannot effectively generate summaries of desired lengths. Because generated summaries are used in difference scenarios which may have space or length constraints, the ability to control the summary length in abstractive summarization is an important problem. In this paper, we propose an approach to constrain the summary length by extending a convolutional sequence to sequence model. The results show that this approach generates high-quality summaries with user defined length, and outperforms the baselines consistently in terms of ROUGE score, length variations and semantic similarity. |
| Tasks | Abstractive Text Summarization, Machine Translation, Semantic Similarity, Semantic Textual Similarity |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1444/ |
| https://www.aclweb.org/anthology/D18-1444 | |
| PWC | https://paperswithcode.com/paper/controlling-length-in-abstractive |
| Repo | |
| Framework | |
Learning Representations for Faster Similarity Search
| Title | Learning Representations for Faster Similarity Search |
| Authors | Ludwig Schmidt, Kunal Talwar |
| Abstract | In high dimensions, the performance of nearest neighbor algorithms depends crucially on structure in the data. While traditional nearest neighbor datasets consisted mostly of hand-crafted feature vectors, an increasing number of datasets comes from representations learned with neural networks. We study the interaction between nearest neighbor algorithms and neural networks in more detail. We find that the network architecture can significantly influence the efficacy of nearest neighbor algorithms even when the classification accuracy is unchanged. Based on our experiments, we propose a number of training modifications that lead to significantly better datasets for nearest neighbor algorithms. Our modifications lead to learned representations that can accelerate nearest neighbor queries by 5x. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=SkrHeXbCW |
| https://openreview.net/pdf?id=SkrHeXbCW | |
| PWC | https://paperswithcode.com/paper/learning-representations-for-faster |
| Repo | |
| Framework | |
Fast Greedy MAP Inference for Determinantal Point Process to Improve Recommendation Diversity
| Title | Fast Greedy MAP Inference for Determinantal Point Process to Improve Recommendation Diversity |
| Authors | Laming Chen, Guoxin Zhang, Eric Zhou |
| Abstract | The determinantal point process (DPP) is an elegant probabilistic model of repulsion with applications in various machine learning tasks including summarization and search. However, the maximum a posteriori (MAP) inference for DPP which plays an important role in many applications is NP-hard, and even the popular greedy algorithm can still be too computationally expensive to be used in large-scale real-time scenarios. To overcome the computational challenge, in this paper, we propose a novel algorithm to greatly accelerate the greedy MAP inference for DPP. In addition, our algorithm also adapts to scenarios where the repulsion is only required among nearby few items in the result sequence. We apply the proposed algorithm to generate relevant and diverse recommendations. Experimental results show that our proposed algorithm is significantly faster than state-of-the-art competitors, and provides a better relevance-diversity trade-off on several public datasets, which is also confirmed in an online A/B test. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7805-fast-greedy-map-inference-for-determinantal-point-process-to-improve-recommendation-diversity |
| http://papers.nips.cc/paper/7805-fast-greedy-map-inference-for-determinantal-point-process-to-improve-recommendation-diversity.pdf | |
| PWC | https://paperswithcode.com/paper/fast-greedy-map-inference-for-determinantal |
| Repo | |
| Framework | |
