Paper Group NANR 148
Cyclic Guidance for Weakly Supervised Joint Detection and Segmentation. Thinning for Accelerating the Learning of Point Processes. Improving Word Embeddings Using Kernel PCA. Conceptual Change and Distributional Semantic Models: an Exploratory Study on Pitfalls and Possibilities. Extracting Complex Relations from Banking Documents. Structural Relat …
Cyclic Guidance for Weakly Supervised Joint Detection and Segmentation
| Title | Cyclic Guidance for Weakly Supervised Joint Detection and Segmentation |
| Authors | Yunhang Shen, Rongrong Ji, Yan Wang, Yongjian Wu, Liujuan Cao |
| Abstract | Weakly supervised learning has attracted growing research attention due to the significant saving in annotation cost for tasks that require intra-image annotations, such as object detection and semantic segmentation. To this end, existing weakly supervised object detection and semantic segmentation approaches follow an iterative label mining and model training pipeline. However, such a self-enforcement pipeline makes both tasks easy to be trapped in local minimums. In this paper, we join weakly supervised object detection and segmentation tasks with a multi-task learning scheme for the first time, which uses their respective failure patterns to complement each other’s learning. Such cross-task enforcement helps both tasks to leap out of their respective local minimums. In particular, we present an efficient and effective framework termed Weakly Supervised Joint Detection and Segmentation (WS-JDS). WS-JDS has two branches for the above two tasks, which share the same backbone network. In the learning stage, it uses the same cyclic training paradigm but with a specific loss function such that the two branches benefit each other. Extensive experiments have been conducted on the widely-used Pascal VOC and COCO benchmarks, which demonstrate that our model has achieved competitive performance with the state-of-the-art algorithms. |
| Tasks | Multi-Task Learning, Object Detection, Semantic Segmentation, Weakly Supervised Object Detection |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Shen_Cyclic_Guidance_for_Weakly_Supervised_Joint_Detection_and_Segmentation_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Shen_Cyclic_Guidance_for_Weakly_Supervised_Joint_Detection_and_Segmentation_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/cyclic-guidance-for-weakly-supervised-joint |
| Repo | |
| Framework | |
Thinning for Accelerating the Learning of Point Processes
| Title | Thinning for Accelerating the Learning of Point Processes |
| Authors | Tianbo Li, Yiping Ke |
| Abstract | This paper discusses one of the most fundamental issues about point processes that what is the best sampling method for point processes. We propose \textit{thinning} as a downsampling method for accelerating the learning of point processes. We find that the thinning operation preserves the structure of intensity, and is able to estimate parameters with less time and without much loss of accuracy. Theoretical results including intensity, parameter and gradient estimation on a thinned history are presented for point processes with decouplable intensities. A stochastic optimization algorithm based on the thinned gradient is proposed. Experimental results on synthetic and real-world datasets validate the effectiveness of thinning in the tasks of parameter and gradient estimation, as well as stochastic optimization. |
| Tasks | Point Processes, Stochastic Optimization |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8663-thinning-for-accelerating-the-learning-of-point-processes |
| http://papers.nips.cc/paper/8663-thinning-for-accelerating-the-learning-of-point-processes.pdf | |
| PWC | https://paperswithcode.com/paper/thinning-for-accelerating-the-learning-of |
| Repo | |
| Framework | |
Improving Word Embeddings Using Kernel PCA
| Title | Improving Word Embeddings Using Kernel PCA |
| Authors | Vishwani Gupta, Sven Giesselbach, Stefan R{"u}ping, Christian Bauckhage |
| Abstract | Word-based embedding approaches such as Word2Vec capture the meaning of words and relations between them, particularly well when trained with large text collections; however, they fail to do so with small datasets. Extensions such as fastText reduce the amount of data needed slightly, however, the joint task of learning meaningful morphology, syntactic and semantic representations still requires a lot of data. In this paper, we introduce a new approach to warm-start embedding models with morphological information, in order to reduce training time and enhance their performance. We use word embeddings generated using both word2vec and fastText models and enrich them with morphological information of words, derived from kernel principal component analysis (KPCA) of word similarity matrices. This can be seen as explicitly feeding the network morphological similarities and letting it learn semantic and syntactic similarities. Evaluating our models on word similarity and analogy tasks in English and German, we find that they not only achieve higher accuracies than the original skip-gram and fastText models but also require significantly less training data and time. Another benefit of our approach is that it is capable of generating a high-quality representation of infrequent words as, for example, found in very recent news articles with rapidly changing vocabularies. Lastly, we evaluate the different models on a downstream sentence classification task in which a CNN model is initialized with our embeddings and find promising results. |
| Tasks | Sentence Classification, Word Embeddings |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4323/ |
| https://www.aclweb.org/anthology/W19-4323 | |
| PWC | https://paperswithcode.com/paper/improving-word-embeddings-using-kernel-pca |
| Repo | |
| Framework | |
Conceptual Change and Distributional Semantic Models: an Exploratory Study on Pitfalls and Possibilities
| Title | Conceptual Change and Distributional Semantic Models: an Exploratory Study on Pitfalls and Possibilities |
| Authors | Pia Sommerauer, Antske Fokkens |
| Abstract | Studying conceptual change using embedding models has become increasingly popular in the Digital Humanities community while critical observations about them have received less attention. This paper investigates what the impact of known pitfalls can be on the conclusions drawn in a digital humanities study through the use case of {``}Racism{''}. In addition, we suggest an approach for modeling a complex concept in terms of words and relations representative of the conceptual system. Our results show that different models created from the same data yield different results, but also indicate that using different model architectures, comparing different corpora and comparing to control words and relations can help to identify which results are solid and which may be due to artefact. We propose guidelines to conduct similar studies, but also note that more work is needed to fully understand how we can distinguish artefacts from actual conceptual changes. | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4728/ |
| https://www.aclweb.org/anthology/W19-4728 | |
| PWC | https://paperswithcode.com/paper/conceptual-change-and-distributional-semantic |
| Repo | |
| Framework | |
Extracting Complex Relations from Banking Documents
| Title | Extracting Complex Relations from Banking Documents |
| Authors | Berke Oral, Erdem Emekligil, Se{\c{c}}il Arslan, G{"u}l{\c{s}}en Eryi{\u{g}}it |
| Abstract | In order to automate banking processes (e.g. payments, money transfers, foreign trade), we need to extract banking transactions from different types of mediums such as faxes, e-mails, and scanners. Banking orders may be considered as complex documents since they contain quite complex relations compared to traditional datasets used in relation extraction research. In this paper, we present our method to extract intersentential, nested and complex relations from banking orders, and introduce a relation extraction method based on maximal clique factorization technique. We demonstrate 11{%} error reduction over previous methods. |
| Tasks | Relation Extraction |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5101/ |
| https://www.aclweb.org/anthology/D19-5101 | |
| PWC | https://paperswithcode.com/paper/extracting-complex-relations-from-banking |
| Repo | |
| Framework | |
Structural Relational Reasoning of Point Clouds
| Title | Structural Relational Reasoning of Point Clouds |
| Authors | Yueqi Duan, Yu Zheng, Jiwen Lu, Jie Zhou, Qi Tian |
| Abstract | The symmetry for the corners of a box, the continuity for the surfaces of a monitor, the linkage between the torso and other body parts — it suggests that 3D objects may have common and underlying inner relations between local structures, and it is a fundamental ability for intelligent species to reason for them. In this paper, we propose an effective plug-and-play module called the structural relation network (SRN) to reason about the structural dependencies of local regions in 3D point clouds. Existing network architectures on point sets such as PointNet++ capture local structures individually, without considering their inner interactions. Instead, our SRN simultaneously exploits local information by modeling their geometrical and locational relations, which play critical roles for our humans to understand 3D objects. The proposed SRN module is simple, interpretable, and does not require any additional supervision signals, which can be easily equipped with the existing networks. Experimental results on benchmark datasets indicate promising boosts on the tasks of 3D point cloud classification and segmentation by capturing structural relations with the SRN module. |
| Tasks | Relational Reasoning |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Duan_Structural_Relational_Reasoning_of_Point_Clouds_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Duan_Structural_Relational_Reasoning_of_Point_Clouds_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/structural-relational-reasoning-of-point |
| Repo | |
| Framework | |
Action4D: Online Action Recognition in the Crowd and Clutter
| Title | Action4D: Online Action Recognition in the Crowd and Clutter |
| Authors | Quanzeng You, Hao Jiang |
| Abstract | Recognizing every person’s action in a crowded and cluttered environment is a challenging task in computer vision. We propose to tackle this challenging problem using a holistic 4D “scan” of a cluttered scene to include every detail about the people and environment. This leads to a new problem, i.e., recognizing multiple people’s actions in the cluttered 4D representation. At the first step, we propose a new method to track people in 4D, which can reliably detect and follow each person in real time. Then, we build a new deep neural network, the Action4DNet, to recognize the action of each tracked person. Such a model gives reliable and accurate results in the real-world settings. We also design an adaptive 3D convolution layer and a novel discriminative temporal feature learning objective to further improve the performance of our model. Our method is invariant to camera view angles, resistant to clutter and able to handle crowd. The experimental results show that the proposed method is fast, reliable and accurate. Our method paves the way to action recognition in the real-world applications and is ready to be deployed to enable smart homes, smart factories and smart stores. |
| Tasks | Temporal Action Localization |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/You_Action4D_Online_Action_Recognition_in_the_Crowd_and_Clutter_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/You_Action4D_Online_Action_Recognition_in_the_Crowd_and_Clutter_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/action4d-online-action-recognition-in-the |
| Repo | |
| Framework | |
REVISTING NEGATIVE TRANSFER USING ADVERSARIAL LEARNING
| Title | REVISTING NEGATIVE TRANSFER USING ADVERSARIAL LEARNING |
| Authors | Saneem Ahmed Chemmengath, Samarth Bharadwaj, Suranjana Samanta, Karthik Sankaranarayanan |
| Abstract | An unintended consequence of feature sharing is the model fitting to correlated tasks within the dataset, termed negative transfer. In this paper, we revisit the problem of negative transfer in multitask setting and find that its corrosive effects are applicable to a wide range of linear and non-linear models, including neural networks. We first study the effects of negative transfer in a principled way and show that previously proposed counter-measures are insufficient, particularly for trainable features. We propose an adversarial training approach to mitigate the effects of negative transfer by viewing the problem in a domain adaptation setting. Finally, empirical results on attribute prediction multi-task on AWA and CUB datasets further validate the need for correcting negative sharing in an end-to-end manner. |
| Tasks | Domain Adaptation |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HJgJS30qtm |
| https://openreview.net/pdf?id=HJgJS30qtm | |
| PWC | https://paperswithcode.com/paper/revisting-negative-transfer-using-adversarial |
| Repo | |
| Framework | |
IIT Gandhinagar at SemEval-2019 Task 3: Contextual Emotion Detection Using Deep Learning
| Title | IIT Gandhinagar at SemEval-2019 Task 3: Contextual Emotion Detection Using Deep Learning |
| Authors | Arik Pamnani, Rajat Goel, Jayesh Choudhari, Mayank Singh |
| Abstract | Recent advancements in Internet and Mobile infrastructure have resulted in the development of faster and efficient platforms of communication. These platforms include speech, facial and text-based conversational mediums. Majority of these are text-based messaging platforms. Development of Chatbots that automatically understand latent emotions in the textual message is a challenging task. In this paper, we present an automatic emotion detection system that aims to detect the emotion of a person textually conversing with a chatbot. We explore deep learning techniques such as CNN and LSTM based neural networks and outperformed the baseline score by 14{%}. The trained model and code are kept in public domain. |
| Tasks | Chatbot |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2039/ |
| https://www.aclweb.org/anthology/S19-2039 | |
| PWC | https://paperswithcode.com/paper/iit-gandhinagar-at-semeval-2019-task-3 |
| Repo | |
| Framework | |
Better to Follow, Follow to Be Better: Towards Precise Supervision of Feature Super-Resolution for Small Object Detection
| Title | Better to Follow, Follow to Be Better: Towards Precise Supervision of Feature Super-Resolution for Small Object Detection |
| Authors | Junhyug Noh, Wonho Bae, Wonhee Lee, Jinhwan Seo, Gunhee Kim |
| Abstract | In spite of recent success of proposal-based CNN models for object detection, it is still difficult to detect small objects due to the limited and distorted information that small region of interests (RoI) contain. One way to alleviate this issue is to enhance the features of small RoIs using a super-resolution (SR) technique. We investigate how to improve feature-level super-resolution especially for small object detection, and discover its performance can be significantly improved by (i) utilizing proper high-resolution target features as supervision signals for training of a SR model and (ii) matching the relative receptive fields of training pairs of input low-resolution features and target high-resolution features. We propose a novel feature-level super-resolution approach that not only correctly addresses these two desiderata but also is integrable with any proposal-based detectors with feature pooling. In our experiments, our approach significantly improves the performance of Faster R-CNN on three benchmarks of Tsinghua-Tencent 100K, PASCAL VOC and MS COCO. The improvement for small objects is remarkably large, and encouragingly, those for medium and large objects are nontrivial too. As a result, we achieve new state-of-the-art performance on Tsinghua-Tencent 100K and highly competitive results on both PASCAL VOC and MS COCO. |
| Tasks | Object Detection, Small Object Detection, Super-Resolution |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Noh_Better_to_Follow_Follow_to_Be_Better_Towards_Precise_Supervision_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Noh_Better_to_Follow_Follow_to_Be_Better_Towards_Precise_Supervision_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/better-to-follow-follow-to-be-better-towards |
| Repo | |
| Framework | |
Meteor++ 2.0: Adopt Syntactic Level Paraphrase Knowledge into Machine Translation Evaluation
| Title | Meteor++ 2.0: Adopt Syntactic Level Paraphrase Knowledge into Machine Translation Evaluation |
| Authors | Yinuo Guo, Junfeng Hu |
| Abstract | This paper describes Meteor++ 2.0, our submission to the WMT19 Metric Shared Task. The well known Meteor metric improves machine translation evaluation by introducing paraphrase knowledge. However, it only focuses on the lexical level and utilizes consecutive n-grams paraphrases. In this work, we take into consideration syntactic level paraphrase knowledge, which sometimes may be skip-grams. We describe how such knowledge can be extracted from Paraphrase Database (PPDB) and integrated into Meteor-based metrics. Experiments on WMT15 and WMT17 evaluation datasets show that the newly proposed metric outperforms all previous versions of Meteor. |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5357/ |
| https://www.aclweb.org/anthology/W19-5357 | |
| PWC | https://paperswithcode.com/paper/meteor-20-adopt-syntactic-level-paraphrase |
| Repo | |
| Framework | |
Neural Machine Translation of Literary Texts from English to Slovene
| Title | Neural Machine Translation of Literary Texts from English to Slovene |
| Authors | Taja Kuzman, {{\v{S}}pela Vintar}, Mihael Ar{\v{c}}an |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7301/ |
| https://www.aclweb.org/anthology/W19-7301 | |
| PWC | https://paperswithcode.com/paper/neural-machine-translation-of-literary-texts |
| Repo | |
| Framework | |
Mimic and Rephrase: Reflective Listening in Open-Ended Dialogue
| Title | Mimic and Rephrase: Reflective Listening in Open-Ended Dialogue |
| Authors | Justin Dieter, Tian Wang, Arun Tejasvi Chaganty, Gabor Angeli, Angel X. Chang |
| Abstract | Reflective listening{–}demonstrating that you have heard your conversational partner{–}is key to effective communication. Expert human communicators often mimic and rephrase their conversational partner, e.g., when responding to sentimental stories or to questions they don{'}t know the answer to. We introduce a new task and an associated dataset wherein dialogue agents similarly mimic and rephrase a user{'}s request to communicate sympathy (I{'}m sorry to hear that) or lack of knowledge (I do not know that). We study what makes a rephrasal response good against a set of qualitative metrics. We then evaluate three models for generating responses: a syntax-aware rule-based system, a seq2seq LSTM neural models with attention (S2SA), and the same neural model augmented with a copy mechanism (S2SA+C). In a human evaluation, we find that S2SA+C and the rule-based system are comparable and approach human-generated response quality. In addition, experiences with a live deployment of S2SA+C in a customer support setting suggest that this generation task is a practical contribution to real world conversational agents. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1037/ |
| https://www.aclweb.org/anthology/K19-1037 | |
| PWC | https://paperswithcode.com/paper/mimic-and-rephrase-reflective-listening-in |
| Repo | |
| Framework | |
When less is more in Neural Quality Estimation of Machine Translation. An industry case study
| Title | When less is more in Neural Quality Estimation of Machine Translation. An industry case study |
| Authors | Dimitar Shterionov, F{'e}lix Do Carmo, Joss Moorkens, Eric Paquin, Dag Schmidtke, Declan Groves, Andy Way |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6738/ |
| https://www.aclweb.org/anthology/W19-6738 | |
| PWC | https://paperswithcode.com/paper/when-less-is-more-in-neural-quality |
| Repo | |
| Framework | |
GEM: Generative Enhanced Model for adversarial attacks
| Title | GEM: Generative Enhanced Model for adversarial attacks |
| Authors | Piotr Niewinski, Maria Pszona, Maria Janicka |
| Abstract | We present our Generative Enhanced Model (GEM) that we used to create samples awarded the first prize on the FEVER 2.0 Breakers Task. GEM is the extended language model developed upon GPT-2 architecture. The addition of novel target vocabulary input to the already existing context input enabled controlled text generation. The training procedure resulted in creating a model that inherited the knowledge of pretrained GPT-2, and therefore was ready to generate natural-like English sentences in the task domain with some additional control. As a result, GEM generated malicious claims that mixed facts from various articles, so it became difficult to classify their truthfulness. |
| Tasks | Language Modelling, Text Generation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6604/ |
| https://www.aclweb.org/anthology/D19-6604 | |
| PWC | https://paperswithcode.com/paper/gem-generative-enhanced-model-for-adversarial |
| Repo | |
| Framework | |
