February 1, 2020

3186 words 15 mins read

Paper Group AWR 308

Airbnb Price Prediction Using Machine Learning and Sentiment Analysis. Information Bottleneck Methods on Convolutional Neural Networks. Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge. Modelling Stopping Criteria for Search Results using Poisson Processes. The Shmoop Corpus: A Dataset of Stories with …

Airbnb Price Prediction Using Machine Learning and Sentiment Analysis


Title	Airbnb Price Prediction Using Machine Learning and Sentiment Analysis
Authors	Pouya Rezazadeh Kalehbasti, Liubov Nikolenko, Hoormazd Rezaei
Abstract	Pricing a rental property on Airbnb is a challenging task for the owner as it determines the number of customers for the place. On the other hand, customers have to evaluate an offered price with minimal knowledge of an optimal value for the property. This paper aims to develop a reliable price prediction model using machine learning, deep learning, and natural language processing techniques to aid both the property owners and the customers with price evaluation given minimal available information about the property. Features of the rentals, owner characteristics, and the customer reviews will comprise the predictors, and a range of methods from linear regression to tree-based models, support-vector regression (SVR), K-means Clustering (KMC), and neural networks (NNs) will be used for creating the prediction model.
Tasks	Sentiment Analysis
Published	2019-07-29
URL	https://arxiv.org/abs/1907.12665v1
PDF	https://arxiv.org/pdf/1907.12665v1.pdf
PWC	https://paperswithcode.com/paper/airbnb-price-prediction-using-machine
Repo	https://github.com/PouyaREZ/AirBnbPricePrediction
Framework	none

Information Bottleneck Methods on Convolutional Neural Networks


Title	Information Bottleneck Methods on Convolutional Neural Networks
Authors	Junjie Li, Ding Liu
Abstract	Recent year, many researches attempt to open the black box of deep neural networks and propose a various of theories to understand it. Among them, information bottleneck theory (IB) claims that there are two distinct phases consisting of fitting phase and compression phase in the course of training. This statement attracts many attentions since its success in explaining the inner behavior of feedforward neural networks. In this paper, we employ IB theory to understand the dynamic behavior of convolutional neural networks (CNNs) and investigate how the fundamental features have impact on the performance of CNNs. In particular, through a series of experimental analysis on benchmark of MNIST and Fashion-MNIST, we demonstrate that the compression phase is not observed in all these cases. This show us the CNNs have a rather complicated behavior than feedforward neural networks.
Tasks
Published	2019-11-09
URL	https://arxiv.org/abs/1911.03722v1
PDF	https://arxiv.org/pdf/1911.03722v1.pdf
PWC	https://paperswithcode.com/paper/information-bottleneck-methods-on
Repo	https://github.com/mrJayLee/IB_ON_CNN
Framework	tf

Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge


Title	Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge
Authors	Ondřej Dušek, Jekaterina Novikova, Verena Rieser
Abstract	This paper provides a comprehensive analysis of the first shared task on End-to-End Natural Language Generation (NLG) and identifies avenues for future research based on the results. This shared task aimed to assess whether recent end-to-end NLG systems can generate more complex output by learning from datasets containing higher lexical richness, syntactic complexity and diverse discourse phenomena. Introducing novel automatic and human metrics, we compare 62 systems submitted by 17 institutions, covering a wide range of approaches, including machine learning architectures – with the majority implementing sequence-to-sequence models (seq2seq) – as well as systems based on grammatical rules and templates. Seq2seq-based systems have demonstrated a great potential for NLG in the challenge. We find that seq2seq systems generally score high in terms of word-overlap metrics and human evaluations of naturalness – with the winning SLUG system (Juraska et al., 2018) being seq2seq-based. However, vanilla seq2seq models often fail to correctly express a given meaning representation if they lack a strong semantic control mechanism applied during decoding. Moreover, seq2seq models can be outperformed by hand-engineered systems in terms of overall quality, as well as complexity, length and diversity of outputs. This research has influenced, inspired and motivated a number of recent studies outwith the original competition, which we also summarise as part of this paper.
Tasks	Text Generation
Published	2019-01-23
URL	https://arxiv.org/abs/1901.07931v3
PDF	https://arxiv.org/pdf/1901.07931v3.pdf
PWC	https://paperswithcode.com/paper/evaluating-the-state-of-the-art-of-end-to-end
Repo	https://github.com/tuetschek/e2e-eval
Framework	none

Modelling Stopping Criteria for Search Results using Poisson Processes


Title	Modelling Stopping Criteria for Search Results using Poisson Processes
Authors	Alison Sneyd, Mark Stevenson
Abstract	Text retrieval systems often return large sets of documents, particularly when applied to large collections. Stopping criteria can reduce the number of these documents that need to be manually evaluated for relevance by predicting when a suitable level of recall has been achieved. In this work, a novel method for determining a stopping criterion is proposed that models the rate at which relevant documents occur using a Poisson process. This method allows a user to specify both a minimum desired level of recall to achieve and a desired probability of having achieved it. We evaluate our method on a public dataset and compare it with previous techniques for determining stopping criteria.
Tasks
Published	2019-09-13
URL	https://arxiv.org/abs/1909.06239v1
PDF	https://arxiv.org/pdf/1909.06239v1.pdf
PWC	https://paperswithcode.com/paper/modelling-stopping-criteria-for-search
Repo	https://github.com/alisonsneyd/poisson_stopping_method
Framework	none

The Shmoop Corpus: A Dataset of Stories with Loosely Aligned Summaries


Title	The Shmoop Corpus: A Dataset of Stories with Loosely Aligned Summaries
Authors	Atef Chaudhury, Makarand Tapaswi, Seung Wook Kim, Sanja Fidler
Abstract	Understanding stories is a challenging reading comprehension problem for machines as it requires reading a large volume of text and following long-range dependencies. In this paper, we introduce the Shmoop Corpus: a dataset of 231 stories that are paired with detailed multi-paragraph summaries for each individual chapter (7,234 chapters), where the summary is chronologically aligned with respect to the story chapter. From the corpus, we construct a set of common NLP tasks, including Cloze-form question answering and a simplified form of abstractive summarization, as benchmarks for reading comprehension on stories. We then show that the chronological alignment provides a strong supervisory signal that learning-based methods can exploit leading to significant improvements on these tasks. We believe that the unique structure of this corpus provides an important foothold towards making machine story comprehension more approachable.
Tasks	Abstractive Text Summarization, Question Answering, Reading Comprehension
Published	2019-12-30
URL	https://arxiv.org/abs/1912.13082v2
PDF	https://arxiv.org/pdf/1912.13082v2.pdf
PWC	https://paperswithcode.com/paper/the-shmoop-corpus-a-dataset-of-stories-with
Repo	https://github.com/achaudhury/shmoop-corpus
Framework	none

A Simple and Effective Framework for Pairwise Deep Metric Learning


Title	A Simple and Effective Framework for Pairwise Deep Metric Learning
Authors	Qi Qi, Yan Yan, Zixuan Wu, Xiaoyu Wang, Tianbao Yang
Abstract	Deep metric learning (DML) has received much attention in deep learning due to its wide applications in computer vision. Previous studies have focused on designing complicated losses and hard example mining methods, which are mostly heuristic and lack of theoretical understanding. In this paper, we cast DML as a simple pairwise binary classification problem that classifies a pair of examples as similar or dissimilar. It identifies the most critical issue in this problem–imbalanced data pairs. To tackle this issue, we propose a simple and effective framework to sample pairs in a batch of data for updating the model. The key to this framework is to define a robust loss for all pairs over a mini-batch of data, which is formulated by distributionally robust optimization. The flexibility in constructing the uncertainty decision set of the dual variable allows us to recover state-of-the-art complicated losses and also to induce novel variants. Empirical studies on several benchmark data sets demonstrate that our simple and effective method outperforms the state-of-the-art results. Codes are available at: https://github.com/qiqi-helloworld/A-Simple-and-Effective-Framework-for-Pairewise-Distance-Metric-Learning
Tasks	Metric Learning
Published	2019-12-24
URL	https://arxiv.org/abs/1912.11194v2
PDF	https://arxiv.org/pdf/1912.11194v2.pdf
PWC	https://paperswithcode.com/paper/a-simple-and-effective-framework-for-pairwise-1
Repo	https://github.com/qiqi-helloworld/A-Simple-and-Effective-Framework-for-Pairewise-Distance-Metric-Learning
Framework	pytorch

Exploring Diseases and Syndromes in Neurology Case Reports from 1955 to 2017 with Text Mining


Title	Exploring Diseases and Syndromes in Neurology Case Reports from 1955 to 2017 with Text Mining
Authors	Amir Karami, Mehdi Ghasemi, Souvik Sen, Marcos Moraes, Vishal Shah
Abstract	Background: A large number of neurology case reports have been published, but it is a challenging task for human medical experts to explore all of these publications. Text mining offers a computational approach to investigate neurology literature and capture meaningful patterns. The overarching goal of this study is to provide a new perspective on case reports of neurological disease and syndrome analysis over the last six decades using text mining. Methods: We extracted diseases and syndromes (DsSs) from more than 65,000 neurology case reports from 66 journals in PubMed over the last six decades from 1955 to 2017. Text mining was applied to reports on the detected DsSs to investigate high-frequency DsSs, categorize them, and explore the linear trends over the 63-year time frame. Results: The text mining methods explored high-frequency neurologic DsSs and their trends and the relationships between them from 1955 to 2017. We detected more than 18,000 unique DsSs and found 10 categories of neurologic DsSs. While the trend analysis showed the increasing trends in the case reports for top-10 high-frequency DsSs, the categories had mixed trends. Conclusion: Our study provided new insights into the application of text mining methods to investigate DsSs in a large number of medical case reports that occur over several decades. The proposed approach can be used to provide a macro level analysis of medical literature by discovering interesting patterns and tracking them over several years to help physicians explore these case reports more efficiently.
Tasks
Published	2019-05-23
URL	https://arxiv.org/abs/1906.03183v1
PDF	https://arxiv.org/pdf/1906.03183v1.pdf
PWC	https://paperswithcode.com/paper/exploring-diseases-and-syndromes-in-neurology
Repo	https://github.com/amir-karami/MedicalCaseReport-Diseases
Framework	none

Learning Neural Causal Models from Unknown Interventions


Title	Learning Neural Causal Models from Unknown Interventions
Authors	Nan Rosemary Ke, Olexa Bilaniuk, Anirudh Goyal, Stefan Bauer, Hugo Larochelle, Chris Pal, Yoshua Bengio
Abstract	Meta-learning over a set of distributions can be interpreted as learning different types of parameters corresponding to short-term vs long-term aspects of the mechanisms underlying the generation of data. These are respectively captured by quickly-changing parameters and slowly-changing meta-parameters. We present a new framework for meta-learning causal models where the relationship between each variable and its parents is modeled by a neural network, modulated by structural meta-parameters which capture the overall topology of a directed graphical model. Our approach avoids a discrete search over models in favour of a continuous optimization procedure. We study a setting where interventional distributions are induced as a result of a random intervention on a single unknown variable of an unknown ground truth causal model, and the observations arising after such an intervention constitute one meta-example. To disentangle the slow-changing aspects of each conditional from the fast-changing adaptations to each intervention, we parametrize the neural network into fast parameters and slow meta-parameters. We introduce a meta-learning objective that favours solutions robust to frequent but sparse interventional distribution change, and which generalize well to previously unseen interventions. Optimizing this objective is shown experimentally to recover the structure of the causal graph.
Tasks	Meta-Learning
Published	2019-10-02
URL	https://arxiv.org/abs/1910.01075v1
PDF	https://arxiv.org/pdf/1910.01075v1.pdf
PWC	https://paperswithcode.com/paper/learning-neural-causal-models-from-unknown-1
Repo	https://github.com/nke001/causal_learning_unknown_interventions
Framework	pytorch

Structured Prediction with Projection Oracles


Title	Structured Prediction with Projection Oracles
Authors	Mathieu Blondel
Abstract	We propose in this paper a general framework for deriving loss functions for structured prediction. In our framework, the user chooses a convex set including the output space and provides an oracle for projecting onto that set. Given that oracle, our framework automatically generates a corresponding convex and smooth loss function. As we show, adding a projection as output layer provably makes the loss smaller. We identify the marginal polytope, the output space’s convex hull, as the best convex set on which to project. However, because the projection onto the marginal polytope can sometimes be expensive to compute, we allow to use any convex superset instead, with potentially cheaper-to-compute projection. Since efficient projection algorithms are available for numerous convex sets, this allows us to construct loss functions for a variety of tasks. On the theoretical side, when combined with calibrated decoding, we prove that our loss functions can be used as a consistent surrogate for a (potentially non-convex) target loss function of interest. We demonstrate our losses on label ranking, ordinal regression and multilabel classification, confirming the improved accuracy enabled by projections.
Tasks	Structured Prediction
Published	2019-10-24
URL	https://arxiv.org/abs/1910.11369v2
PDF	https://arxiv.org/pdf/1910.11369v2.pdf
PWC	https://paperswithcode.com/paper/structured-prediction-with-projection-oracles
Repo	https://github.com/mblondel/projection-losses
Framework	none

Improving Knowledge-aware Dialogue Generation via Knowledge Base Question Answering


Title	Improving Knowledge-aware Dialogue Generation via Knowledge Base Question Answering
Authors	Jian Wang, Junhao Liu, Wei Bi, Xiaojiang Liu, Kejing He, Ruifeng Xu, Min Yang
Abstract	Neural network models usually suffer from the challenge of incorporating commonsense knowledge into the open-domain dialogue systems. In this paper, we propose a novel knowledge-aware dialogue generation model (called TransDG), which transfers question representation and knowledge matching abilities from knowledge base question answering (KBQA) task to facilitate the utterance understanding and factual knowledge selection for dialogue generation. In addition, we propose a response guiding attention and a multi-step decoding strategy to steer our model to focus on relevant features for response generation. Experiments on two benchmark datasets demonstrate that our model has robust superiority over compared methods in generating informative and fluent dialogues. Our code is available at https://github.com/siat-nlp/TransDG.
Tasks	Dialogue Generation, Knowledge Base Question Answering, Question Answering
Published	2019-12-16
URL	https://arxiv.org/abs/1912.07491v1
PDF	https://arxiv.org/pdf/1912.07491v1.pdf
PWC	https://paperswithcode.com/paper/improving-knowledge-aware-dialogue-generation
Repo	https://github.com/siat-nlp/TransDG
Framework	tf

TutorialVQA: Question Answering Dataset for Tutorial Videos


Title	TutorialVQA: Question Answering Dataset for Tutorial Videos
Authors	Anthony Colas, Seokhwan Kim, Franck Dernoncourt, Siddhesh Gupte, Daisy Zhe Wang, Doo Soon Kim
Abstract	Despite the number of currently available datasets on video question answering, there still remains a need for a dataset involving multi-step and non-factoid answers. Moreover, relying on video transcripts remains an under-explored topic. To adequately address this, We propose a new question answering task on instructional videos, because of their verbose and narrative nature. While previous studies on video question answering have focused on generating a short text as an answer, given a question and video clip, our task aims to identify a span of a video segment as an answer which contains instructional details with various granularities. This work focuses on screencast tutorial videos pertaining to an image editing program. We introduce a dataset, TutorialVQA, consisting of about 6,000manually collected triples of (video, question, answer span). We also provide experimental results with several baselines algorithms using the video transcripts. The results indicate that the task is challenging and call for the investigation of new algorithms.
Tasks	Question Answering, Video Question Answering
Published	2019-12-02
URL	https://arxiv.org/abs/1912.01046v1
PDF	https://arxiv.org/pdf/1912.01046v1.pdf
PWC	https://paperswithcode.com/paper/tutorialvqa-question-answering-dataset-for
Repo	https://github.com/acolas1/TutorialVQAData
Framework	none

Using Panoramic Videos for Multi-person Localization and Tracking in a 3D Panoramic Coordinate


Title	Using Panoramic Videos for Multi-person Localization and Tracking in a 3D Panoramic Coordinate
Authors	Fan Yang, Feiran Li, Yang Wu, Sakriani Sakti, Satoshi Nakamura
Abstract	3D panoramic multi-person localization and tracking are prominent in many applications, however, conventional methods using LiDAR equipment could be economically expensive and also computationally inefficient due to the processing of point cloud data. In this work, we propose an effective and efficient approach at a low cost. First, we obtain panoramic videos with four normal cameras. Then, we transform human locations from a 2D panoramic image coordinate to a 3D panoramic camera coordinate using camera geometry and human bio-metric property (i.e., height). Finally, we generate 3D tracklets by associating human appearance and 3D trajectory. We verify the effectiveness of our method on three datasets including a new one built by us, in terms of 3D single-view multi-person localization, 3D single-view multi-person tracking, and 3D panoramic multi-person localization and tracking. Our code and dataset are available at \url{https://github.com/fandulu/MPLT}.
Tasks
Published	2019-11-24
URL	https://arxiv.org/abs/1911.10535v5
PDF	https://arxiv.org/pdf/1911.10535v5.pdf
PWC	https://paperswithcode.com/paper/using-panoramic-videos-for-multi-person
Repo	https://github.com/fandulu/MPLT
Framework	pytorch

AutoSlim: Towards One-Shot Architecture Search for Channel Numbers


Title	AutoSlim: Towards One-Shot Architecture Search for Channel Numbers
Authors	Jiahui Yu, Thomas Huang
Abstract	We study how to set channel numbers in a neural network to achieve better accuracy under constrained resources (e.g., FLOPs, latency, memory footprint or model size). A simple and one-shot solution, named AutoSlim, is presented. Instead of training many network samples and searching with reinforcement learning, we train a single slimmable network to approximate the network accuracy of different channel configurations. We then iteratively evaluate the trained slimmable model and greedily slim the layer with minimal accuracy drop. By this single pass, we can obtain the optimized channel configurations under different resource constraints. We present experiments with MobileNet v1, MobileNet v2, ResNet-50 and RL-searched MNasNet on ImageNet classification. We show significant improvements over their default channel configurations. We also achieve better accuracy than recent channel pruning methods and neural architecture search methods. Notably, by setting optimized channel numbers, our AutoSlim-MobileNet-v2 at 305M FLOPs achieves 74.2% top-1 accuracy, 2.4% better than default MobileNet-v2 (301M FLOPs), and even 0.2% better than RL-searched MNasNet (317M FLOPs). Our AutoSlim-ResNet-50 at 570M FLOPs, without depthwise convolutions, achieves 1.3% better accuracy than MobileNet-v1 (569M FLOPs). Code and models will be available at: https://github.com/JiahuiYu/slimmable_networks
Tasks	Neural Architecture Search
Published	2019-03-27
URL	https://arxiv.org/abs/1903.11728v2
PDF	https://arxiv.org/pdf/1903.11728v2.pdf
PWC	https://paperswithcode.com/paper/network-slimming-by-slimmable-networks
Repo	https://github.com/JiahuiYu/slimmable_networks
Framework	pytorch

Using Laplacian Spectrum as Graph Feature Representation


Title	Using Laplacian Spectrum as Graph Feature Representation
Authors	Edouard Pineau
Abstract	Graphs possess exotic features like variable size and absence of natural ordering of the nodes that make them difficult to analyze and compare. To circumvent this problem and learn on graphs, graph feature representation is required. A good graph representation must satisfy the preservation of structural information, with two particular key attributes: consistency under deformation and invariance under isomorphism. While state-of-the-art methods seek such properties with powerful graph neural-networks, we propose to leverage a simple graph feature: the graph Laplacian spectrum (GLS). We first remind and show that GLS satisfies the aforementioned key attributes, using a graph perturbation approach. In particular, we derive bounds for the distance between two GLS that are related to the \textit{divergence to isomorphism}, a standard computationally expensive graph divergence. We finally experiment GLS as graph representation through consistency tests and classification tasks, and show that it is a strong graph feature representation baseline.
Tasks
Published	2019-12-02
URL	https://arxiv.org/abs/1912.00735v1
PDF	https://arxiv.org/pdf/1912.00735v1.pdf
PWC	https://paperswithcode.com/paper/using-laplacian-spectrum-as-graph-feature
Repo	https://github.com/benedekrozemberczki/karateclub
Framework	none

Progressive Perception-Oriented Network for Single Image Super-Resolution


Title	Progressive Perception-Oriented Network for Single Image Super-Resolution
Authors	Zheng Hui, Jie Li, Xinbo Gao, Xiumei Wang
Abstract	Recently, it has been shown that deep neural networks can significantly improve the performance of single image super-resolution (SISR). Numerous studies have focused on raising the quantitative quality of super-resolved (SR) images. However, these methods that target PSNR maximization usually produce smooth images at large upscaling factor. The introduction of generative adversarial networks (GANs) can mitigate this issue and show impressive results with synthetic high-frequency textures. Nevertheless, these GAN-based approaches always tend to add fake textures and even artifacts to make the SR image of visually higher-resolution. In this paper, we propose a novel perceptual image super-resolution method that progressively generates visually high-quality results by constructing a stage-wise network. Specifically, the first phase concentrates on minimizing pixel-wise error and the second stage utilizes the features extracted by the previous stage to pursue results with better structural retention. The final stage employs fine structure features distilled by the second phase to produce more realistic results. In this way, we can maintain the pixel and structure level information in the perceptual image as much as possible. It is worth note that the proposed method can build three types of images in a feed-forward process. Also, we explore a new generator that adopts multi-scale hierarchical features fusion. Extensive experiments on benchmark datasets show that our approach is superior to the state-of-the-art methods. Code is available at https://github.com/Zheng222/PPON.
Tasks	Image Super-Resolution, Super-Resolution
Published	2019-07-24
URL	https://arxiv.org/abs/1907.10399v1
PDF	https://arxiv.org/pdf/1907.10399v1.pdf
PWC	https://paperswithcode.com/paper/progressive-perception-oriented-network-for
Repo	https://github.com/Zheng222/PPON
Framework	pytorch