Paper Group NANR 173
Pretraining Sentiment Classifiers with Unlabeled Dialog Data. Researching Less-Resourced Languages – the DigiSami Corpus. Efficient Global Point Cloud Registration by Matching Rotation Invariant Features Through Translation Search. Variance Regularized Counterfactual Risk Minimization via Variational Divergence Minimization. When does deep multi-t …
Pretraining Sentiment Classifiers with Unlabeled Dialog Data
| Title | Pretraining Sentiment Classifiers with Unlabeled Dialog Data |
| Authors | Toru Shimizu, Nobuyuki Shimizu, Hayato Kobayashi |
| Abstract | The huge cost of creating labeled training data is a common problem for supervised learning tasks such as sentiment classification. Recent studies showed that pretraining with unlabeled data via a language model can improve the performance of classification models. In this paper, we take the concept a step further by using a conditional language model, instead of a language model. Specifically, we address a sentiment classification task for a tweet analysis service as a case study and propose a pretraining strategy with unlabeled dialog data (tweet-reply pairs) via an encoder-decoder model. Experimental results show that our strategy can improve the performance of sentiment classifiers and outperform several state-of-the-art strategies including language model pretraining. |
| Tasks | Language Modelling, Sentiment Analysis |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-2121/ |
| https://www.aclweb.org/anthology/P18-2121 | |
| PWC | https://paperswithcode.com/paper/pretraining-sentiment-classifiers-with |
| Repo | |
| Framework | |
Researching Less-Resourced Languages – the DigiSami Corpus
| Title | Researching Less-Resourced Languages – the DigiSami Corpus |
| Authors | Kristiina Jokinen |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1534/ |
| https://www.aclweb.org/anthology/L18-1534 | |
| PWC | https://paperswithcode.com/paper/researching-less-resourced-languages-a-the |
| Repo | |
| Framework | |
Efficient Global Point Cloud Registration by Matching Rotation Invariant Features Through Translation Search
| Title | Efficient Global Point Cloud Registration by Matching Rotation Invariant Features Through Translation Search |
| Authors | Yinlong Liu, Chen Wang, Zhijian Song, Manning Wang |
| Abstract | Three-dimensional rigid point cloud registration has many applications in computer vision and robotics. Local methods tend to fail, causing global methods to be needed, when the relative transformation is large or the overlap ratio is small. Most existing global methods utilize BnB optimization over the 6D parameter space of SE(3). Such methods are usually very slow because the time complexity of BnB optimization is exponential in the dimensionality of the parameter space. In this paper, we decouple the optimization of translation and rotation, and we propose a fast BnB algorithm to globally optimize the 3D translation parameter first. The optimal rotation is then calculated by utilizing the global optimal translation found by the BnB algorithm. The separate optimization of translation and rotation is realized by using a newly proposed rotation invariant feature. Experiments on challenging data sets demonstrate that the proposed method outperforms state-of-the-art global methods in terms of both speed and accuracy. |
| Tasks | Point Cloud Registration |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Yinlong_Liu_Efficient_Global_Point_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Yinlong_Liu_Efficient_Global_Point_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-global-point-cloud-registration-by |
| Repo | |
| Framework | |
Variance Regularized Counterfactual Risk Minimization via Variational Divergence Minimization
| Title | Variance Regularized Counterfactual Risk Minimization via Variational Divergence Minimization |
| Authors | Hang Wu |
| Abstract | Off-policy learning, the task of evaluating and improving policies using historic data collected from a logging policy, is important because on-policy evaluation is usually expensive and has adverse impacts. One of the major challenge of off-policy learning is to derive counterfactual estimators that also has low variance and thus low generalization error. In this work, inspired by learning bounds for importance sampling problems, we present a new counterfactual learning principle for off-policy learning with bandit feedbacks.Our method regularizes the generalization error by minimizing the distribution divergence between the logging policy and the new policy, and removes the need for iterating through all training samples to compute sample variance regularization in prior work. With neural network policies, our end-to-end training algorithms using variational divergence minimization showed significant improvement over conventional baseline algorithms and is also consistent with our theoretical results. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=SyPMT6gAb |
| https://openreview.net/pdf?id=SyPMT6gAb | |
| PWC | https://paperswithcode.com/paper/variance-regularized-counterfactual-risk |
| Repo | |
| Framework | |
When does deep multi-task learning work for loosely related document classification tasks?
| Title | When does deep multi-task learning work for loosely related document classification tasks? |
| Authors | Emma Kerinec, Chlo{'e} Braud, Anders S{\o}gaard |
| Abstract | This work aims to contribute to our understanding of \textit{when} multi-task learning through parameter sharing in deep neural networks leads to improvements over single-task learning. We focus on the setting of learning from \textit{loosely related} tasks, for which no theoretical guarantees exist. We therefore approach the question empirically, studying which properties of datasets and single-task learning characteristics correlate with improvements from multi-task learning. We are the first to study this in a text classification setting and across more than 500 different task pairs. |
| Tasks | Document Classification, Machine Translation, Multi-Task Learning, Sentence Compression, Sentiment Analysis, Text Classification |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-5401/ |
| https://www.aclweb.org/anthology/W18-5401 | |
| PWC | https://paperswithcode.com/paper/when-does-deep-multi-task-learning-work-for |
| Repo | |
| Framework | |
DocUNet: Document Image Unwarping via a Stacked U-Net
| Title | DocUNet: Document Image Unwarping via a Stacked U-Net |
| Authors | Ke Ma, Zhixin Shu, Xue Bai, Jue Wang, Dimitris Samaras |
| Abstract | Capturing document images is a common way for digitizing and recording physical documents due to the ubiquitousness of mobile cameras. To make text recognition easier, it is often desirable to digitally flatten a document image when the physical document sheet is folded or curved. In this paper, we develop the first learning-based method to achieve this goal. We propose a stacked U-Net with intermediate supervision to directly predict the forward mapping from a distorted image to its rectified version. Because large-scale real-world data with ground truth deformation is difficult to obtain, we create a synthetic dataset with approximately 100 thousand images by warping non-distorted document images. The network is trained on this dataset with various data augmentations to improve its generalization ability. We further create a comprehensive benchmark that covers various real-world conditions. We evaluate the proposed model quantitatively and qualitatively on the proposed benchmark, and compare it with previous non-learning-based methods. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Ma_DocUNet_Document_Image_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Ma_DocUNet_Document_Image_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/docunet-document-image-unwarping-via-a |
| Repo | |
| Framework | |
Building Dialogue Structure from Discourse Tree of a Question
| Title | Building Dialogue Structure from Discourse Tree of a Question |
| Authors | Boris Galitsky, Dmitry Ilvovsky |
| Abstract | In this section we propose a reasoning-based approach to a dialogue management for a customer support chat bot. To build a dialogue scenario, we analyze the discourse tree (DT) of an initial query of a customer support dialogue that is frequently complex and multi-sentence. We then enforce rhetorical agreement between DT of the initial query and that of the answers, requests and responses. The chat bot finds answers, which are not only relevant by topic but also suitable for a given step of a conversation and match the question by style, communication means, experience level and other domain-independent attributes. We evaluate a performance of proposed algorithm in car repair domain and observe a 5 to 10{%} improvement for single and three-step dialogues respectively, in comparison with baseline approaches to dialogue management. |
| Tasks | Dialogue Management |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5703/ |
| https://www.aclweb.org/anthology/W18-5703 | |
| PWC | https://paperswithcode.com/paper/building-dialogue-structure-from-discourse |
| Repo | |
| Framework | |
A Methodology for Evaluating Interaction Strategies of Task-Oriented Conversational Agents
| Title | A Methodology for Evaluating Interaction Strategies of Task-Oriented Conversational Agents |
| Authors | Marco Guerini, Sara Falcone, Bernardo Magnini |
| Abstract | In task-oriented conversational agents, more attention has been usually devoted to assessing task effectiveness, rather than to \textit{how} the task is achieved. However, conversational agents are moving towards more complex and human-like interaction capabilities (e.g. the ability to use a formal/informal register, to show an empathetic behavior), for which standard evaluation methodologies may not suffice. In this paper, we provide a novel methodology to assess - in a completely controlled way - the impact on the quality of experience of agent{'}s interaction strategies. The methodology is based on a within subject design, where two slightly different transcripts of the same interaction with a conversational agent are presented to the user. Through a series of pilot experiments we prove that this methodology allows fast and cheap experimentation/evaluation, focusing on aspects that are overlooked by current methods. |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5704/ |
| https://www.aclweb.org/anthology/W18-5704 | |
| PWC | https://paperswithcode.com/paper/a-methodology-for-evaluating-interaction |
| Repo | |
| Framework | |
From Lexical Functional Grammar to Enhanced Universal Dependencies
| Title | From Lexical Functional Grammar to Enhanced Universal Dependencies |
| Authors | Adam Przepi{'o}rkowski, Agnieszka Patejuk |
| Abstract | This is a summary of an invited talk. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4902/ |
| https://www.aclweb.org/anthology/W18-4902 | |
| PWC | https://paperswithcode.com/paper/from-lexical-functional-grammar-to-enhanced |
| Repo | |
| Framework | |
Iterative Back-Translation for Neural Machine Translation
| Title | Iterative Back-Translation for Neural Machine Translation |
| Authors | Vu Cong Duy Hoang, Philipp Koehn, Gholamreza Haffari, Trevor Cohn |
| Abstract | We present iterative back-translation, a method for generating increasingly better synthetic parallel data from monolingual data to train neural machine translation systems. Our proposed method is very simple yet effective and highly applicable in practice. We demonstrate improvements in neural machine translation quality in both high and low resourced scenarios, including the best reported BLEU scores for the WMT 2017 German↔English tasks. |
| Tasks | Machine Translation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2703/ |
| https://www.aclweb.org/anthology/W18-2703 | |
| PWC | https://paperswithcode.com/paper/iterative-back-translation-for-neural-machine |
| Repo | |
| Framework | |
Curriculum Learning Based on Reward Sparseness for Deep Reinforcement Learning of Task Completion Dialogue Management
| Title | Curriculum Learning Based on Reward Sparseness for Deep Reinforcement Learning of Task Completion Dialogue Management |
| Authors | Atsushi Saito |
| Abstract | Learning from sparse and delayed reward is a central issue in reinforcement learning. In this paper, to tackle reward sparseness problem of task oriented dialogue management, we propose a curriculum based approach on the number of slots of user goals. This curriculum makes it possible to learn dialogue management for sets of user goals with large number of slots. We also propose a dialogue policy based on progressive neural networks whose modules with parameters are appended with previous parameters fixed as the curriculum proceeds, and this policy improves performances over the one with single set of parameters. |
| Tasks | Dialogue Management, Information Retrieval, Question Answering, Text Generation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5707/ |
| https://www.aclweb.org/anthology/W18-5707 | |
| PWC | https://paperswithcode.com/paper/curriculum-learning-based-on-reward |
| Repo | |
| Framework | |
A theory on the absence of spurious solutions for nonconvex and nonsmooth optimization
| Title | A theory on the absence of spurious solutions for nonconvex and nonsmooth optimization |
| Authors | Cedric Josz, Yi Ouyang, Richard Zhang, Javad Lavaei, Somayeh Sojoudi |
| Abstract | We study the set of continuous functions that admit no spurious local optima (i.e. local minima that are not global minima) which we term global functions. They satisfy various powerful properties for analyzing nonconvex and nonsmooth optimization problems. For instance, they satisfy a theorem akin to the fundamental uniform limit theorem in the analysis regarding continuous functions. Global functions are also endowed with useful properties regarding the composition of functions and change of variables. Using these new results, we show that a class of non-differentiable nonconvex optimization problems arising in tensor decomposition applications are global functions. This is the first result concerning nonconvex methods for nonsmooth objective functions. Our result provides a theoretical guarantee for the widely-used $\ell_1$ norm to avoid outliers in nonconvex optimization. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7511-a-theory-on-the-absence-of-spurious-solutions-for-nonconvex-and-nonsmooth-optimization |
| http://papers.nips.cc/paper/7511-a-theory-on-the-absence-of-spurious-solutions-for-nonconvex-and-nonsmooth-optimization.pdf | |
| PWC | https://paperswithcode.com/paper/a-theory-on-the-absence-of-spurious-solutions |
| Repo | |
| Framework | |
Uncalibrated Photometric Stereo Under Natural Illumination
| Title | Uncalibrated Photometric Stereo Under Natural Illumination |
| Authors | Zhipeng Mo, Boxin Shi, Feng Lu, Sai-Kit Yeung, Yasuyuki Matsushita |
| Abstract | This paper presents a photometric stereo method that works with unknown natural illuminations without any calibration object. To solve this challenging problem, we propose the use of an equivalent directional lighting model for small surface patches consisting of slowly varying normals, and solve each patch up to an arbitrary rotation ambiguity. Our method connects the resulting patches and unifies the local ambiguities to a global rotation one through angular distance propagation defined over the whole surface. After applying the integrability constraint, our final solution contains only a binary ambiguity, which could be easily removed. Experiments using both synthetic and real-world datasets show our method provides even comparable results to calibrated methods |
| Tasks | Calibration |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Mo_Uncalibrated_Photometric_Stereo_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Mo_Uncalibrated_Photometric_Stereo_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/uncalibrated-photometric-stereo-under-natural |
| Repo | |
| Framework | |
Geometrically Coupled Monte Carlo Sampling
| Title | Geometrically Coupled Monte Carlo Sampling |
| Authors | Mark Rowland, Krzysztof M. Choromanski, François Chalus, Aldo Pacchiano, Tamas Sarlos, Richard E. Turner, Adrian Weller |
| Abstract | Monte Carlo sampling in high-dimensional, low-sample settings is important in many machine learning tasks. We improve current methods for sampling in Euclidean spaces by avoiding independence, and instead consider ways to couple samples. We show fundamental connections to optimal transport theory, leading to novel sampling algorithms, and providing new theoretical grounding for existing strategies. We compare our new strategies against prior methods for improving sample efficiency, including QMC, by studying discrepancy. We explore our findings empirically, and observe benefits of our sampling schemes for reinforcement learning and generative modelling. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7304-geometrically-coupled-monte-carlo-sampling |
| http://papers.nips.cc/paper/7304-geometrically-coupled-monte-carlo-sampling.pdf | |
| PWC | https://paperswithcode.com/paper/geometrically-coupled-monte-carlo-sampling |
| Repo | |
| Framework | |
A Computational Approach to Feature Extraction for Identification of Suicidal Ideation in Tweets
| Title | A Computational Approach to Feature Extraction for Identification of Suicidal Ideation in Tweets |
| Authors | Ramit Sawhney, Manch, Prachi a, Raj Singh, Swati Aggarwal |
| Abstract | Technological advancements in the World Wide Web and social networks in particular coupled with an increase in social media usage has led to a positive correlation between the exhibition of Suicidal ideation on websites such as Twitter and cases of suicide. This paper proposes a novel supervised approach for detecting suicidal ideation in content on Twitter. A set of features is proposed for training both linear and ensemble classifiers over a dataset of manually annotated tweets. The performance of the proposed methodology is compared against four baselines that utilize varying approaches to validate its utility. The results are finally summarized by reflecting on the effect of the inclusion of the proposed features one by one for suicidal ideation detection. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-3013/ |
| https://www.aclweb.org/anthology/P18-3013 | |
| PWC | https://paperswithcode.com/paper/a-computational-approach-to-feature |
| Repo | |
| Framework | |
