Paper Group NANR 52
Joint Learning for Targeted Sentiment Analysis. Lifelong Learning via Progressive Distillation and Retrospection. Key-Word-Aware Network for Referring Expression Image Segmentation. Macquarie University at BioASQ 6b: Deep learning and deep reinforcement learning for query-based summarisation. A Large Multilingual and Multi-domain Dataset for Recomm …
Joint Learning for Targeted Sentiment Analysis
| Title | Joint Learning for Targeted Sentiment Analysis |
| Authors | Dehong Ma, Sujian Li, Houfeng Wang |
| Abstract | Targeted sentiment analysis (TSA) aims at extracting targets and classifying their sentiment classes. Previous works only exploit word embeddings as features and do not explore more potentials of neural networks when jointly learning the two tasks. In this paper, we carefully design the hierarchical stack bidirectional gated recurrent units (HSBi-GRU) model to learn abstract features for both tasks, and we propose a HSBi-GRU based joint model which allows the target label to have influence on their sentiment label. Experimental results on two datasets show that our joint learning model can outperform other baselines and demonstrate the effectiveness of HSBi-GRU in learning abstract features. |
| Tasks | Sentiment Analysis, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1504/ |
| https://www.aclweb.org/anthology/D18-1504 | |
| PWC | https://paperswithcode.com/paper/joint-learning-for-targeted-sentiment |
| Repo | |
| Framework | |
Lifelong Learning via Progressive Distillation and Retrospection
| Title | Lifelong Learning via Progressive Distillation and Retrospection |
| Authors | Saihui Hou, Xinyu Pan, Chen Change Loy, Zilei Wang, Dahua Lin |
| Abstract | Lifelong learning aims at adapting a learned model to new tasks while retaining the knowledge gained earlier. A key challenge for lifelong learning is how to strike a balance between the preservation on old tasks and the adaptation to a new one within a given model. Approaches that combine both objectives in training have been explored in previous works. Yet the performance still suffers from considerable degradation in a long sequence of tasks. In this work, we propose a novel approach to lifelong learning, which tries to seek a better balance between preservation and adaptation via two techniques: Distillation and Retrospection. Specifically, the target model adapts to the new task by knowledge distillation from an intermediate expert, while the previous knowledge is more effectively preserved by caching a small subset of data for old tasks. The combination of Distillation and Retrospection leads to a more gentle learning curve for the target model, and extensive experiments demonstrate that our approach can bring consistent improvements on both old and new tasks. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Saihui_Hou_Progressive_Lifelong_Learning_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Saihui_Hou_Progressive_Lifelong_Learning_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/lifelong-learning-via-progressive |
| Repo | |
| Framework | |
Key-Word-Aware Network for Referring Expression Image Segmentation
| Title | Key-Word-Aware Network for Referring Expression Image Segmentation |
| Authors | Hengcan Shi, Hongliang Li, Fanman Meng, Qingbo Wu |
| Abstract | Referring expression image segmentation aims to segment out the object referred by a natural language query expression. Without considering the specific properties of visual and textual information, existing works usually deal with this task by directly feeding a foreground/background classifier with cascaded image and text features, which are extracted from each image region and the whole query, respectively. On the one hand, they ignore that each word in a query expression makes different contributions to identify the desired object, which requires a differential treatment in extracting text feature. On the other hand, the relationships of different image regions are not considered as well, even though they are greatly important to eliminate the undesired foreground object in accordance with specific query. To address aforementioned issues, in this paper, we propose a key-word-aware network, which contains a query attention model and a key-word-aware visual context model. In extracting text features, the query attention model attends to assign higher weights for the words which are more important for identifying object. Meanwhile, the key-word-aware visual context model describes the relationships among different image regions, according to corresponding query. Our proposed method outperforms state-of-the-art methods on two referring expression image segmentation databases. |
| Tasks | Semantic Segmentation |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Hengcan_Shi_Key-Word-Aware_Network_for_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Hengcan_Shi_Key-Word-Aware_Network_for_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/key-word-aware-network-for-referring |
| Repo | |
| Framework | |
Macquarie University at BioASQ 6b: Deep learning and deep reinforcement learning for query-based summarisation
| Title | Macquarie University at BioASQ 6b: Deep learning and deep reinforcement learning for query-based summarisation |
| Authors | Diego Moll{'a} |
| Abstract | This paper describes Macquarie University{'}s contribution to the BioASQ Challenge (BioASQ 6b, Phase B). We focused on the extraction of the ideal answers, and the task was approached as an instance of query-based multi-document summarisation. In particular, this paper focuses on the experiments related to the deep learning and reinforcement learning approaches used in the submitted runs. The best run used a deep learning model under a regression-based framework. The deep learning architecture used features derived from the output of LSTM chains on word embeddings, plus features based on similarity with the query, and sentence position. The reinforcement learning approach was a proof-of-concept prototype that trained a global policy using REINFORCE. The global policy was implemented as a neural network that used tf.idf features encoding the candidate sentence, question, and context. |
| Tasks | Question Answering, Word Embeddings |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-5303/ |
| https://www.aclweb.org/anthology/W18-5303 | |
| PWC | https://paperswithcode.com/paper/macquarie-university-at-bioasq-6b-deep |
| Repo | |
| Framework | |
A Large Multilingual and Multi-domain Dataset for Recommender Systems
| Title | A Large Multilingual and Multi-domain Dataset for Recommender Systems |
| Authors | Giorgia Di Tommaso, Stefano Faralli, Paola Velardi |
| Abstract | |
| Tasks | Recommendation Systems |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1444/ |
| https://www.aclweb.org/anthology/L18-1444 | |
| PWC | https://paperswithcode.com/paper/a-large-multilingual-and-multi-domain-dataset |
| Repo | |
| Framework | |
Interpreting Deep Classification Models With Bayesian Inference
| Title | Interpreting Deep Classification Models With Bayesian Inference |
| Authors | Hanshu Yan, Jiashi Feng |
| Abstract | In this paper, we propose a novel approach to interpret a well-trained classification model through systematically investigating effects of its hidden units on prediction making. We search for the core hidden units responsible for predicting inputs as the class of interest under the generative Bayesian inference framework. We model such a process of unit selection as an Indian Buffet Process, and derive a simplified objective function via the MAP asymptotic technique. The induced binary optimization problem is efficiently solved with a continuous relaxation method by attaching a Switch Gate layer to the hidden layers of interest. The resulted interpreter model is thus end-to-end optimized via standard gradient back-propagation. Experiments are conducted with two popular deep convolutional classifiers, respectively well-trained on the MNIST dataset and the CI- FAR10 dataset. The results demonstrate that the proposed interpreter successfully finds the core hidden units most responsible for prediction making. The modified model, only with the selected units activated, can hold correct predictions at a high rate. Besides, this interpreter model is also able to extract the most informative pixels in the images by connecting a Switch Gate layer to the input layer. |
| Tasks | Bayesian Inference |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=H1vCXOe0b |
| https://openreview.net/pdf?id=H1vCXOe0b | |
| PWC | https://paperswithcode.com/paper/interpreting-deep-classification-models-with |
| Repo | |
| Framework | |
NLP Lean Programming Framework: Developing NLP Applications More Effectively
| Title | NLP Lean Programming Framework: Developing NLP Applications More Effectively |
| Authors | Marc Schreiber, Bodo Kraft, Albert Z{"u}ndorf |
| Abstract | This paper presents NLP Lean Programming framework (NLPf), a new framework for creating custom Natural Language Processing (NLP) models and pipelines by utilizing common software development build systems. This approach allows developers to train and integrate domain-specific NLP pipelines into their applications seamlessly. Additionally, NLPf provides an annotation tool which improves the annotation process significantly by providing a well-designed GUI and sophisticated way of using input devices. Due to NLPf{'}s properties developers and domain experts are able to build domain-specific NLP application more effectively. Project page: \url{https://gitlab.com/schrieveslaach/NLPf} Video Tutorial: \url{https://www.youtube.com/watch?v=44UJspVebTA} (Demonstration starts at 11:40 min) This paper is related to: - Interfaces and resources to support linguistic annotation - Software architectures and reusable components - Software tools for evaluation or error analysis |
| Tasks | Named Entity Recognition |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-5001/ |
| https://www.aclweb.org/anthology/N18-5001 | |
| PWC | https://paperswithcode.com/paper/nlp-lean-programming-framework-developing-nlp |
| Repo | |
| Framework | |
Solving Data Sparsity for Aspect Based Sentiment Analysis Using Cross-Linguality and Multi-Linguality
| Title | Solving Data Sparsity for Aspect Based Sentiment Analysis Using Cross-Linguality and Multi-Linguality |
| Authors | Md Shad Akhtar, Palaash Sawant, Sukanta Sen, Asif Ekbal, Pushpak Bhattacharyya |
| Abstract | Efficient word representations play an important role in solving various problems related to Natural Language Processing (NLP), data mining, text mining etc. The issue of data sparsity poses a great challenge in creating efficient word representation model for solving the underlying problem. The problem is more intensified in resource-poor scenario due to the absence of sufficient amount of corpus. In this work we propose to minimize the effect of data sparsity by leveraging bilingual word embeddings learned through a parallel corpus. We train and evaluate Long Short Term Memory (LSTM) based architecture for aspect level sentiment classification. The neural network architecture is further assisted by the hand-crafted features for the prediction. We show the efficacy of the proposed model against state-of-the-art methods in two experimental setups i.e. multi-lingual and cross-lingual. |
| Tasks | Aspect-Based Sentiment Analysis, Sentiment Analysis, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1053/ |
| https://www.aclweb.org/anthology/N18-1053 | |
| PWC | https://paperswithcode.com/paper/solving-data-sparsity-for-aspect-based |
| Repo | |
| Framework | |
Annotating Spin in Biomedical Scientific Publications : the case of Random Controlled Trials (RCTs)
| Title | Annotating Spin in Biomedical Scientific Publications : the case of Random Controlled Trials (RCTs) |
| Authors | Anna Koroleva, Patrick Paroubek |
| Abstract | |
| Tasks | Decision Making |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1080/ |
| https://www.aclweb.org/anthology/L18-1080 | |
| PWC | https://paperswithcode.com/paper/annotating-spin-in-biomedical-scientific |
| Repo | |
| Framework | |
Planar Shape Detection at Structural Scales
| Title | Planar Shape Detection at Structural Scales |
| Authors | Hao Fang, Florent Lafarge, Mathieu Desbrun |
| Abstract | Interpreting 3D data such as point clouds or surface meshes depends heavily on the scale of observation. Yet, existing algorithms for shape detection rely on trial-and-error parameter tunings to output configurations representative of a structural scale. We present a framework to automatically extract a set of representations that capture the shape and structure of man-made objects at different key abstraction levels. A shape-collapsing process first generates a fine-to-coarse sequence of shape representations by exploiting local planarity. This sequence is then analyzed to identify significant geometric variations between successive representations through a supervised energy minimization. Our framework is flexible enough to learn how to detect both existing structural formalisms such as the CityGML Levels Of Details, and expert-specified levels of abstraction. Experiments on different input data and classes of man-made objects, as well as comparisons with existing shape detection methods, illustrate the strengths of our approach in terms of efficiency and flexibility. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Fang_Planar_Shape_Detection_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Fang_Planar_Shape_Detection_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/planar-shape-detection-at-structural-scales |
| Repo | |
| Framework | |
Context Refinement for Object Detection
| Title | Context Refinement for Object Detection |
| Authors | Zhe Chen, Shaoli Huang, Dacheng Tao |
| Abstract | Current two-stage object detectors, which consists of a region proposal stage and a refinement stage, may produce unreliable results due to ill-localized proposed regions. To address this problem, we propose a context refinement algorithm that explores rich contextual information to better refine each proposed region. In particular, we first identify neighboring regions that may contain useful contexts and then perform refinement based on the extracted and unified contextual information. In practice, our method effectively improves the quality of the final detection results as well as region proposals. Empirical studies show that context refinement yields substantial and consistent improvements over different baseline detectors. Moreover, the proposed algorithm brings around 3% performance gain on PASCAL VOC benchmark and around 6% gain on MS COCO benchmark respectively. |
| Tasks | Object Detection |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Zhe_Chen_Context_Refinement_for_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Zhe_Chen_Context_Refinement_for_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/context-refinement-for-object-detection |
| Repo | |
| Framework | |
Robust Anchor Embedding for Unsupervised Video Person Re-Identification in the Wild
| Title | Robust Anchor Embedding for Unsupervised Video Person Re-Identification in the Wild |
| Authors | Mang Ye, Xiangyuan Lan, Pong C. Yuen |
| Abstract | This paper addresses the scalability and robustness issues of estimating labels from imbalanced unlabeled data for unsupervised video-based person re-identification (re-ID). To achieve it, we propose a novel Robust AnChor Embedding (RACE) framework via deep feature representation learning for large-scale unsupervised video re-ID. Within this framework, anchor sequences representing different persons are firstly selected to formulate an anchor graph which also initializes the CNN model to get discriminative feature representations for later label estimation. To accurately estimate labels from unlabeled sequences with noisy frames, robust anchor embedding is introduced based on the regularized affine hull. Efficiency is ensured with kNN anchors embedding instead of the whole anchor set under manifold assumptions. After that, a robust and efficient top-k counts label prediction strategy is proposed to predict the labels of unlabeled image sequences. With the newly estimated labeled sequences, the unified anchor embedding framework enables the feature learning process to be further facilitated. Extensive experimental results on the large-scale dataset show that the proposed method outperforms existing unsupervised video re-ID methods. |
| Tasks | Person Re-Identification, Representation Learning, Video-Based Person Re-Identification |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Mang_YE_Robust_Anchor_Embedding_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Mang_YE_Robust_Anchor_Embedding_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/robust-anchor-embedding-for-unsupervised |
| Repo | |
| Framework | |
Sanaphor++: Combining Deep Neural Networks with Semantics for Coreference Resolution
| Title | Sanaphor++: Combining Deep Neural Networks with Semantics for Coreference Resolution |
| Authors | Julien Plu, Roman Prokofyev, Alberto Tonon, Philippe Cudr{'e}-Mauroux, Djellel Eddine Difallah, Rapha{"e}l Troncy, Giuseppe Rizzo |
| Abstract | |
| Tasks | Coreference Resolution, Entity Linking, Named Entity Recognition |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1063/ |
| https://www.aclweb.org/anthology/L18-1063 | |
| PWC | https://paperswithcode.com/paper/sanaphor-combining-deep-neural-networks-with |
| Repo | |
| Framework | |
A Framework for the Needs of Different Types of Users in Multilingual Semantic Enrichment
| Title | A Framework for the Needs of Different Types of Users in Multilingual Semantic Enrichment |
| Authors | Jan Nehring, Felix Sasaki |
| Abstract | |
| Tasks | Entity Linking, Machine Translation, Sentiment Analysis |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1087/ |
| https://www.aclweb.org/anthology/L18-1087 | |
| PWC | https://paperswithcode.com/paper/a-framework-for-the-needs-of-different-types |
| Repo | |
| Framework | |
Into the Twilight Zone: Depth Estimation using Joint Structure-Stereo Optimization
| Title | Into the Twilight Zone: Depth Estimation using Joint Structure-Stereo Optimization |
| Authors | Aashish Sharma, Loong-Fah Cheong |
| Abstract | We present a joint Structure-Stereo optimization model that is robust for disparity estimation under low-light conditions. Eschewing the traditional denoising approach - which we show to be ineffective for stereo due to its artefacts and the questionable use of the PSNR metric, we propose to instead rely on structures comprising of piecewise constant regions and principal edges in the given image, as these are the important regions for extracting disparity information. We also judiciously retain the coarser textures for stereo matching, discarding the finer textures as they are apt to be inextricably mixed with noise. This selection process in the structure-texture decomposition step is aided by the stereo matching constraint in our joint Structure-Stereo formulation. The resulting optimization problem is complex but we are able to decompose it into sub-problems that admit relatively standard solutions. Our experiments confirm that our joint model significantly outperforms the baseline methods on both synthetic and real noise datasets. |
| Tasks | Denoising, Depth Estimation, Disparity Estimation, Stereo Matching, Stereo Matching Hand |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Aashish_Sharma_Into_the_Twilight_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Aashish_Sharma_Into_the_Twilight_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/into-the-twilight-zone-depth-estimation-using |
| Repo | |
| Framework | |
