Paper Group NANR 133
Multilevel Heuristics for Rationale-Based Entity Relation Classification in Sentences. The Lovász-Softmax Loss: A Tractable Surrogate for the Optimization of the Intersection-Over-Union Measure in Neural Networks. Cyberbullying Intervention Based on Convolutional Neural Networks. Stock Movement Prediction from Tweets and Historical Prices. Deep Le …
Multilevel Heuristics for Rationale-Based Entity Relation Classification in Sentences
| Title | Multilevel Heuristics for Rationale-Based Entity Relation Classification in Sentences |
| Authors | Shiou Tian Hsu, M Chaudhary, ar, Nagiza Samatova |
| Abstract | Rationale-based models provide a unique way to provide justifiable results for relation classification models by identifying rationales (key words and phrases that a person can use to justify the relation in the sentence) during the process. However, existing generative networks used to extract rationales come with a trade-off between extracting diversified rationales and achieving good classification results. In this paper, we propose a multilevel heuristic approach to regulate rationale extraction to avoid extracting monotonous rationales without compromising classification performance. In our model, rationale selection is regularized by a semi-supervised process and features from different levels: word, syntax, sentence, and corpus. We evaluate our approach on the SemEval 2010 dataset that includes 19 relation classes and the quality of extracted rationales with our manually-labeled rationales. Experiments show a significant improvement in classification performance and a 20{%} gain in rationale interpretability compared to state-of-the-art approaches. |
| Tasks | Relation Classification |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1098/ |
| https://www.aclweb.org/anthology/C18-1098 | |
| PWC | https://paperswithcode.com/paper/multilevel-heuristics-for-rationale-based |
| Repo | |
| Framework | |
The Lovász-Softmax Loss: A Tractable Surrogate for the Optimization of the Intersection-Over-Union Measure in Neural Networks
| Title | The Lovász-Softmax Loss: A Tractable Surrogate for the Optimization of the Intersection-Over-Union Measure in Neural Networks |
| Authors | Maxim Berman, Amal Rannen Triki, Matthew B. Blaschko |
| Abstract | The Jaccard index, also referred to as the intersection-over-union score, is commonly employed in the evaluation of image segmentation results given its perceptual qualities, scale invariance - which lends appropriate relevance to small objects, and appropriate counting of false negatives, in comparison to per-pixel losses. We present a method for direct optimization of the mean intersection-over-union loss in neural networks, in the context of semantic image segmentation, based on the convex Lovász extension of submodular losses. The loss is shown to perform better with respect to the Jaccard index measure than the traditionally used cross-entropy loss. We show quantitative and qualitative differences between optimizing the Jaccard index per image versus optimizing the Jaccard index taken over an entire dataset. We evaluate the impact of our method in a semantic segmentation pipeline and show substantially improved intersection-over-union segmentation scores on the Pascal VOC and Cityscapes datasets using state-of-the-art deep learning segmentation architectures. |
| Tasks | Semantic Segmentation |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Berman_The_LovaSz-Softmax_Loss_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Berman_The_LovaSz-Softmax_Loss_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/the-lovasz-softmax-loss-a-tractable-surrogate-1 |
| Repo | |
| Framework | |
Cyberbullying Intervention Based on Convolutional Neural Networks
| Title | Cyberbullying Intervention Based on Convolutional Neural Networks |
| Authors | Qianjia Huang, Diana Inkpen, Jianhong Zhang, David Van Bruwaene |
| Abstract | This paper describes the process of building a cyberbullying intervention interface driven by a machine-learning based text-classification service. We make two main contributions. First, we show that cyberbullying can be identified in real-time before it takes place, with available machine learning and natural language processing tools. Second, we present a mechanism that provides individuals with early feedback about how other people would feel about wording choices in their messages before they are sent out. This interface not only gives a chance for the user to revise the text, but also provides a system-level flagging/intervention in a situation related to cyberbullying. |
| Tasks | Text Classification |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4405/ |
| https://www.aclweb.org/anthology/W18-4405 | |
| PWC | https://paperswithcode.com/paper/cyberbullying-intervention-based-on |
| Repo | |
| Framework | |
Stock Movement Prediction from Tweets and Historical Prices
| Title | Stock Movement Prediction from Tweets and Historical Prices |
| Authors | Yumo Xu, Shay B. Cohen |
| Abstract | Stock movement prediction is a challenging problem: the market is highly stochastic, and we make temporally-dependent predictions from chaotic data. We treat these three complexities and present a novel deep generative model jointly exploiting text and price signals for this task. Unlike the case with discriminative or topic modeling, our model introduces recurrent, continuous latent variables for a better treatment of stochasticity, and uses neural variational inference to address the intractable posterior inference. We also provide a hybrid objective with temporal auxiliary to flexibly capture predictive dependencies. We demonstrate the state-of-the-art performance of our proposed model on a new stock movement prediction dataset which we collected. |
| Tasks | Feature Engineering, Stock Market Prediction, Stock Trend Prediction, Time Series, Topic Models |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1183/ |
| https://www.aclweb.org/anthology/P18-1183 | |
| PWC | https://paperswithcode.com/paper/stock-movement-prediction-from-tweets-and |
| Repo | |
| Framework | |
Deep Learning for Conversational AI
| Title | Deep Learning for Conversational AI |
| Authors | Pei-Hao Su, Nikola Mrk{\v{s}}i{'c}, I{~n}igo Casanueva, Ivan Vuli{'c} |
| Abstract | Spoken Dialogue Systems (SDS) have great commercial potential as they promise to revolutionise the way in which humans interact with machines. The advent of deep learning led to substantial developments in this area of NLP research, and the goal of this tutorial is to familiarise the research community with the recent advances in what some call the most difficult problem in NLP. From a research perspective, the design of spoken dialogue systems provides a number of significant challenges, as these systems depend on: a) solving several difficult NLP and decision-making tasks; and b) combining these into a functional dialogue system pipeline. A key long-term goal of dialogue system research is to enable open-domain systems that can converse about arbitrary topics and assist humans with completing a wide range of tasks. Furthermore, such systems need to autonomously learn on-line to improve their performance and recover from errors using both signals from their environment and from implicit and explicit user feedback. While the design of such systems has traditionally been modular, domain and language-specific, advances in deep learning have alleviated many of the design problems. The main purpose of this tutorial is to encourage dialogue research in the NLP community by providing the research background, a survey of available resources, and giving key insights to application of state-of-the-art SDS methodology into industry-scale conversational AI systems. We plan to introduce researchers to the pipeline framework for modelling goal-oriented dialogue systems, which includes three key components: 1) Language Understanding; 2) Dialogue Management; and 3) Language Generation. The differences between goal-oriented dialogue systems and chat-bot style conversational agents will be explained in order to show the motivation behind the design of both, with the main focus on the pipeline SDS framework. For each key component, we will define the research problem, provide a brief literature review and introduce the current state-of-the-art approaches. Complementary resources (e.g. available datasets and toolkits) will also be discussed. Finally, future work, outstanding challenges, and current industry practices will be presented. All of the presented material will be made available online for future reference. |
| Tasks | Decision Making, Dialogue Management, Dialogue State Tracking, Goal-Oriented Dialogue Systems, Spoken Dialogue Systems, Text Generation |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-6006/ |
| https://www.aclweb.org/anthology/N18-6006 | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-conversational-ai |
| Repo | |
| Framework | |
Contextual Pricing for Lipschitz Buyers
| Title | Contextual Pricing for Lipschitz Buyers |
| Authors | Jieming Mao, Renato Leme, Jon Schneider |
| Abstract | We investigate the problem of learning a Lipschitz function from binary feedback. In this problem, a learner is trying to learn a Lipschitz function $f:[0,1]^d \rightarrow [0,1]$ over the course of $T$ rounds. On round $t$, an adversary provides the learner with an input $x_t$, the learner submits a guess $y_t$ for $f(x_t)$, and learns whether $y_t > f(x_t)$ or $y_t \leq f(x_t)$. The learner’s goal is to minimize their total loss $\sum_t\ell(f(x_t), y_t)$ (for some loss function $\ell$). The problem is motivated by \textit{contextual dynamic pricing}, where a firm must sell a stream of differentiated products to a collection of buyers with non-linear valuations for the items and observes only whether the item was sold or not at the posted price. For the symmetric loss $\ell(f(x_t), y_t) = \vert f(x_t) - y_t \vert$, we provide an algorithm for this problem achieving total loss $O(\log T)$ when $d=1$ and $O(T^{(d-1)/d})$ when $d>1$, and show that both bounds are tight (up to a factor of $\sqrt{\log T}$). For the pricing loss function $\ell(f(x_t), y_t) = f(x_t) - y_t {\bf 1}{y_t \leq f(x_t)}$ we show a regret bound of $O(T^{d/(d+1)})$ and show that this bound is tight. We present improved bounds in the special case of a population of linear buyers. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7807-contextual-pricing-for-lipschitz-buyers |
| http://papers.nips.cc/paper/7807-contextual-pricing-for-lipschitz-buyers.pdf | |
| PWC | https://paperswithcode.com/paper/contextual-pricing-for-lipschitz-buyers |
| Repo | |
| Framework | |
Automatic Input Enrichment for Selecting Reading Material: An Online Study with English Teachers
| Title | Automatic Input Enrichment for Selecting Reading Material: An Online Study with English Teachers |
| Authors | Maria Chinkina, Ankita Oswal, Detmar Meurers |
| Abstract | Input material at the appropriate level is crucial for language acquisition. Automating the search for such material can systematically and efficiently support teachers in their pedagogical practice. This is the goal of the computational linguistic task of automatic input enrichment (Chinkina {&} Meurers, 2016): It analyzes and re-ranks a collection of texts in order to prioritize those containing target linguistic forms. In the online study described in the paper, we collected 240 responses from English teachers in order to investigate whether they preferred automatic input enrichment over web search when selecting reading material for class. Participants demonstrated a general preference for the material provided by an automatic input enrichment system. It was also rated significantly higher than the texts retrieved by a standard web search engine with regard to the representation of linguistic forms and equivalent with regard to the relevance of the content to the topic. We discuss the implications of the results for language teaching and consider the potential strands of future research. |
| Tasks | Language Acquisition |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0504/ |
| https://www.aclweb.org/anthology/W18-0504 | |
| PWC | https://paperswithcode.com/paper/automatic-input-enrichment-for-selecting |
| Repo | |
| Framework | |
Hyperparameter Optimization for Tracking With Continuous Deep Q-Learning
| Title | Hyperparameter Optimization for Tracking With Continuous Deep Q-Learning |
| Authors | Xingping Dong, Jianbing Shen, Wenguan Wang, Yu Liu, Ling Shao, Fatih Porikli |
| Abstract | Hyperparameters are numerical presets whose values are assigned prior to the commencement of the learning process. Selecting appropriate hyperparameters is critical for the accuracy of tracking algorithms, yet it is difficult to determine their optimal values, in particular, adaptive ones for each specific video sequence. Most hyperparameter optimization algorithms depend on searching a generic range and they are imposed blindly on all sequences. Here, we propose a novel hyperparameter optimization method that can find optimal hyperparameters for a given sequence using an action-prediction network leveraged on Continuous Deep Q-Learning. Since the common state-spaces for object tracking tasks are significantly more complex than the ones in traditional control problems, existing Continuous Deep Q-Learning algorithms cannot be directly applied. To overcome this challenge, we introduce an efficient heuristic to accelerate the convergence behavior. We evaluate our method on several tracking benchmarks and demonstrate its superior performance. |
| Tasks | Hyperparameter Optimization, Object Tracking, Q-Learning |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Dong_Hyperparameter_Optimization_for_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Dong_Hyperparameter_Optimization_for_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/hyperparameter-optimization-for-tracking-with |
| Repo | |
| Framework | |
The Mutex Watershed: Efficient, Parameter-Free Image Partitioning
| Title | The Mutex Watershed: Efficient, Parameter-Free Image Partitioning |
| Authors | Steffen Wolf, Constantin Pape, Alberto Bailoni, Nasim Rahaman, Anna Kreshuk, Ullrich Kothe, FredA. Hamprecht |
| Abstract | Image partitioning, or segmentation without semantics, is the task of decomposing an image into distinct segments; or equivalently, the task of detecting closed contours in an image. Most prior work either requires seeds, one per segment; or a threshold; or formulates the task as an NP-hard signed graph partitioning problem. Here, we propose an algorithm with empirically linearithmic complexity. Unlike seeded watershed, the algorithm can accommodate not only attractive but also repulsive cues, allowing it to find a previously unspecified number of segments without the need for explicit seeds or a tunable threshold. The algorithm itself, which we dub âmutex watershedâ, is closely related to a minimal spanning tree computation. It is deterministic and easy to implement. When presented with short-range attractive and long-range repulsive cues from a deep neural network, the mutex watershed gives results that currently define the state-of-the-art in the competitive ISBI 2012 EM segmentation benchmark. These results are also better than those obtained from other recently proposed clustering strategies operating on the very same network outputs. |
| Tasks | graph partitioning |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Steffen_Wolf_The_Mutex_Watershed_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Steffen_Wolf_The_Mutex_Watershed_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/the-mutex-watershed-efficient-parameter-free |
| Repo | |
| Framework | |
ResBinNet: Residual Binary Neural Network
| Title | ResBinNet: Residual Binary Neural Network |
| Authors | Mohammad Ghasemzadeh, Mohammad Samragh, Farinaz Koushanfar |
| Abstract | Recent efforts on training light-weight binary neural networks offer promising execution/memory efficiency. This paper introduces ResBinNet, which is a composition of two interlinked methodologies aiming to address the slow convergence speed and limited accuracy of binary convolutional neural networks. The first method, called residual binarization, learns a multi-level binary representation for the features within a certain neural network layer. The second method, called temperature adjustment, gradually binarizes the weights of a particular layer. The two methods jointly learn a set of soft-binarized parameters that improve the convergence rate and accuracy of binary neural networks. We corroborate the applicability and scalability of ResBinNet by implementing a prototype hardware accelerator. The accelerator is reconfigurable in terms of the numerical precision of the binarized features, offering a trade-off between runtime and inference accuracy. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=SJtfOEn6- |
| https://openreview.net/pdf?id=SJtfOEn6- | |
| PWC | https://paperswithcode.com/paper/resbinnet-residual-binary-neural-network |
| Repo | |
| Framework | |
Ambulatory Atrial Fibrillation Monitoring Using Wearable Photoplethysmography with Deep Learning
| Title | Ambulatory Atrial Fibrillation Monitoring Using Wearable Photoplethysmography with Deep Learning |
| Authors | Maxime Voisin, Yichen Shen, Alireza Aliamiri, Anand Avati, Awni Hannun, Andrew Ng |
| Abstract | We develop an algorithm that accurately detects Atrial Fibrillation (AF) episodes from photoplethysmograms (PPG) recorded in ambulatory free-living conditions. We collect and annotate a dataset containing more than 4000 hours of PPG recorded from a wrist-worn device. Using a 50-layer convolutional neural network, we achieve a test AUC of 95% and show robustness to motion artifacts inherent to PPG signals. Continuous and accurate detection of AF from PPG has the potential to transform consumer wearable devices into clinically useful medical monitoring tools. |
| Tasks | Photoplethysmography (PPG) |
| Published | 2018-11-12 |
| URL | https://arxiv.org/abs/1811.07774 |
| https://arxiv.org/pdf/1811.07774 | |
| PWC | https://paperswithcode.com/paper/ambulatory-atrial-fibrillation-monitoring |
| Repo | |
| Framework | |
Learning Compressible 360° Video Isomers
| Title | Learning Compressible 360° Video Isomers |
| Authors | Yu-Chuan Su, Kristen Grauman |
| Abstract | Standard video encoders developed for conventional narrow field-of-view video are widely applied to 360° video as well, with reasonable results. However, while this approach commits arbitrarily to a projection of the spherical frames, we observe that some orientations of a 360° video, once projected, are more compressible than others. We introduce an approach to predict the sphere rotation that will yield the maximal compression rate. Given video clips in their original encoding, a convolutional neural network learns the association between a clipâs visual content and its compressibility at different rotations of a cubemap projection. Given a novel video, our learning-based approach efficiently infers the most compressible direction in one shot, without repeated rendering and compression of the source video. We validate our idea on thousands of video clips and multiple popular video codecs. The results show that this untapped dimension of 360° compression has substantial potentialââgoodâ rotations are typically 8â10% more compressible than bad ones, and our learning approach can predict them reliably 82% of the time. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Su_Learning_Compressible_360deg_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Su_Learning_Compressible_360deg_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-compressible-360a-video-isomers |
| Repo | |
| Framework | |
Moon IME: Neural-based Chinese Pinyin Aided Input Method with Customizable Association
| Title | Moon IME: Neural-based Chinese Pinyin Aided Input Method with Customizable Association |
| Authors | Yafang Huang, Zuchao Li, Zhuosheng Zhang, Hai Zhao |
| Abstract | Chinese pinyin input method engine (IME) lets user conveniently input Chinese into a computer by typing pinyin through the common keyboard. In addition to offering high conversion quality, modern pinyin IME is supposed to aid user input with extended association function. However, existing solutions for such functions are roughly based on oversimplified matching algorithms at word-level, whose resulting products provide limited extension associated with user inputs. This work presents the Moon IME, a pinyin IME that integrates the attention-based neural machine translation (NMT) model and Information Retrieval (IR) to offer amusive and customizable association ability. The released IME is implemented on Windows via text services framework. |
| Tasks | Information Retrieval, Machine Translation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-4024/ |
| https://www.aclweb.org/anthology/P18-4024 | |
| PWC | https://paperswithcode.com/paper/moon-ime-neural-based-chinese-pinyin-aided |
| Repo | |
| Framework | |
A Knowledge-Augmented Neural Network Model for Implicit Discourse Relation Classification
| Title | A Knowledge-Augmented Neural Network Model for Implicit Discourse Relation Classification |
| Authors | Yudai Kishimoto, Yugo Murawaki, Sadao Kurohashi |
| Abstract | Identifying discourse relations that are not overtly marked with discourse connectives remains a challenging problem. The absence of explicit clues indicates a need for the combination of world knowledge and weak contextual clues, which can hardly be learned from a small amount of manually annotated data. In this paper, we address this problem by augmenting the input text with external knowledge and context and by adopting a neural network model that can effectively handle the augmented text. Experiments show that external knowledge did improve the classification accuracy. Contextual information provided no significant gain for implicit discourse relations, but it did for explicit ones. |
| Tasks | Implicit Discourse Relation Classification, Machine Translation, Relation Classification, Sentiment Analysis |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1049/ |
| https://www.aclweb.org/anthology/C18-1049 | |
| PWC | https://paperswithcode.com/paper/a-knowledge-augmented-neural-network-model |
| Repo | |
| Framework | |
Who Feels What and Why? Annotation of a Literature Corpus with Semantic Roles of Emotions
| Title | Who Feels What and Why? Annotation of a Literature Corpus with Semantic Roles of Emotions |
| Authors | Evgeny Kim, Roman Klinger |
| Abstract | Most approaches to emotion analysis in fictional texts focus on detecting the emotion expressed in text. We argue that this is a simplification which leads to an overgeneralized interpretation of the results, as it does not take into account who experiences an emotion and why. Emotions play a crucial role in the interaction between characters and the events they are involved in. Until today, no specific corpora that capture such an interaction were available for literature. We aim at filling this gap and present a publicly available corpus based on Project Gutenberg, REMAN (Relational EMotion ANnotation), manually annotated for spans which correspond to emotion trigger phrases and entities/events in the roles of experiencers, targets, and causes of the emotion. We provide baseline results for the automatic prediction of these relational structures and show that emotion lexicons are not able to encompass the high variability of emotion expressions and demonstrate that statistical models benefit from joint modeling of emotions with its roles in all subtasks. The corpus that we provide enables future research on the recognition of emotions and associated entities in text. It supports qualitative literary studies and digital humanities. The corpus is available at http://www.ims.uni-stuttgart.de/data/reman . |
| Tasks | Emotion Recognition |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1114/ |
| https://www.aclweb.org/anthology/C18-1114 | |
| PWC | https://paperswithcode.com/paper/who-feels-what-and-why-annotation-of-a |
| Repo | |
| Framework | |
