Paper Group NANR 201
OpenCeres: When Open Information Extraction Meets the Semi-Structured Web. Unsupervised Neural Machine Translation with Future Rewarding. Automated assessment of knowledge hierarchy evolution: comparing directed acyclic graphs. Neural Boxer at the IWCS Shared Task on DRS Parsing. Difference-Seeking Generative Adversarial Network. Transfer Learning …
OpenCeres: When Open Information Extraction Meets the Semi-Structured Web
| Title | OpenCeres: When Open Information Extraction Meets the Semi-Structured Web |
| Authors | Colin Lockard, Prashant Shiralkar, Xin Luna Dong |
| Abstract | Open Information Extraction (OpenIE), the problem of harvesting triples from natural language text whose predicate relations are not aligned to any pre-defined ontology, has been a popular subject of research for the last decade. However, this research has largely ignored the vast quantity of facts available in semi-structured webpages. In this paper, we define the problem of OpenIE from semi-structured websites to extract such facts, and present an approach for solving it. We also introduce a labeled evaluation dataset to motivate research in this area. Given a semi-structured website and a set of seed facts for some relations existing on its pages, we employ a semi-supervised label propagation technique to automatically create training data for the relations present on the site. We then use this training data to learn a classifier for relation extraction. Experimental results of this method on our new benchmark dataset obtained a precision of over 70{%}. A larger scale extraction experiment on 31 websites in the movie vertical resulted in the extraction of over 2 million triples. |
| Tasks | Open Information Extraction, Relation Extraction |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1309/ |
| https://www.aclweb.org/anthology/N19-1309 | |
| PWC | https://paperswithcode.com/paper/openceres-when-open-information-extraction |
| Repo | |
| Framework | |
Unsupervised Neural Machine Translation with Future Rewarding
| Title | Unsupervised Neural Machine Translation with Future Rewarding |
| Authors | Xiangpeng Wei, Yue Hu, Luxi Xing, Li Gao |
| Abstract | In this paper, we alleviate the local optimality of back-translation by learning a policy (takes the form of an encoder-decoder and is defined by its parameters) with future rewarding under the reinforcement learning framework, which aims to optimize the global word predictions for unsupervised neural machine translation. To this end, we design a novel reward function to characterize high-quality translations from two aspects: n-gram matching and semantic adequacy. The n-gram matching is defined as an alternative for the discrete BLEU metric, and the semantic adequacy is used to measure the adequacy of conveying the meaning of the source sentence to the target. During training, our model strives for earning higher rewards by learning to produce grammatically more accurate and semantically more adequate translations. Besides, a variational inference network (VIN) is proposed to constrain the corresponding sentences in two languages have the same or similar latent semantic code. On the widely used WMT{'}14 English-French, WMT{'}16 English-German and NIST Chinese-to-English benchmarks, our models respectively obtain 27.59/27.15, 19.65/23.42 and 22.40 BLEU points without using any labeled data, demonstrating consistent improvements over previous unsupervised NMT models. |
| Tasks | Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1027/ |
| https://www.aclweb.org/anthology/K19-1027 | |
| PWC | https://paperswithcode.com/paper/unsupervised-neural-machine-translation-with-3 |
| Repo | |
| Framework | |
Automated assessment of knowledge hierarchy evolution: comparing directed acyclic graphs
| Title | Automated assessment of knowledge hierarchy evolution: comparing directed acyclic graphs |
| Authors | Guruprasad Nayak, Sourav Dutta, Deepak Ajwani, Patrick Nicholson, Alessandra Sala |
| Abstract | Automated construction of knowledge hierarchies from huge data corpora is gaining increasing attention in recent years, in order to tackle the infeasibility of manually extracting and semantically linking millions of concepts. As a knowledge hierarchy evolves with these automated techniques, there is a need for measures to assess its temporal evolution, quantifying the similarities between different versions and identifying the relative growth of different subgraphs in the knowledge hierarchy. In this paper, we focus on measures that leverage structural properties of the knowledge hierarchy graph to assess the temporal changes. We propose a principled and scalable similarity measure, based on Katz similarity between concept nodes, for comparing different versions of a knowledge hierarchy, modeled as a generic directed acyclic graph. We present theoretical analysis to depict that the proposed measure accurately captures the salient properties of taxonomic hierarchies, assesses changes in the ordering of nodes, along with the logical subsumption of relationships among concepts. We also present a linear time variant of the measure, and show that our measures, unlike previous approaches, are tunable to cater to diverse application needs. We further show that our measure provides interpretability, thereby identifying the key structural and logical difference in the hierarchies. Experiments on a real DBpedia and biological knowledge hierarchy showcase that our measures accurately capture structural similarity, while providing enhanced scalability and tunability. Also, we demonstrate that the temporal evolution of different subgraphs in this knowledge hierarchy, as captured purely by our structural measure, corresponds well with the known disruptions in the related subject areas. |
| Tasks | Knowledge Graph Completion, Knowledge Graphs, Question Answering |
| Published | 2019-06-01 |
| URL | https://link.springer.com/article/10.1007/s10791-018-9345-y |
| https://www.researchgate.net/publication/329716534_Automated_assessment_of_knowledge_hierarchy_evolution_comparing_directed_acyclic_graphs | |
| PWC | https://paperswithcode.com/paper/automated-assessment-of-knowledge-hierarchy |
| Repo | |
| Framework | |
Neural Boxer at the IWCS Shared Task on DRS Parsing
| Title | Neural Boxer at the IWCS Shared Task on DRS Parsing |
| Authors | Rik van Noord |
| Abstract | This paper describes our participation in the shared task of Discourse Representation Structure parsing. It follows the work of Van Noord et al. (2018), who employed a neural sequence-to-sequence model to produce DRSs, also exploiting linguistic information with multiple encoders. We provide a detailed look in the performance of this model and show that (i) the benefit of the linguistic features is evident across a number of experiments which vary the amount of training data and (ii) the model can be improved by applying a number of postprocessing methods to fix ill-formed output. Our model ended up in second place in the competition, with an F-score of 84.5. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://www.aclweb.org/anthology/W19-1204/ |
| https://www.aclweb.org/anthology/W19-1204 | |
| PWC | https://paperswithcode.com/paper/neural-boxer-at-the-iwcs-shared-task-on-drs |
| Repo | |
| Framework | |
Difference-Seeking Generative Adversarial Network
| Title | Difference-Seeking Generative Adversarial Network |
| Authors | Yi-Lin Sung, Sung-Hsien Hsieh, Soo-Chang Pei, Chun-Shien Lu |
| Abstract | We propose a novel algorithm, Difference-Seeking Generative Adversarial Network (DSGAN), developed from traditional GAN. DSGAN considers the scenario that the training samples of target distribution, $p_{t}$, are difficult to collect. Suppose there are two distributions $p_{\bar{d}}$ and $p_{d}$ such that the density of the target distribution can be the differences between the densities of $p_{\bar{d}}$ and $p_{d}$. We show how to learn the target distribution $p_{t}$ only via samples from $p_{d}$ and $p_{\bar{d}}$ (relatively easy to obtain). DSGAN has the flexibility to produce samples from various target distributions (e.g. the out-of-distribution). Two key applications, semi-supervised learning and adversarial training, are taken as examples to validate the effectiveness of DSGAN. We also provide theoretical analyses about the convergence of DSGAN. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=ryxDUs05KQ |
| https://openreview.net/pdf?id=ryxDUs05KQ | |
| PWC | https://paperswithcode.com/paper/difference-seeking-generative-adversarial |
| Repo | |
| Framework | |
Transfer Learning from Pre-trained BERT for Pronoun Resolution
| Title | Transfer Learning from Pre-trained BERT for Pronoun Resolution |
| Authors | Xingce Bao, Qianqian Qiao |
| Abstract | The paper describes the submission of the team {``}We used bert!{''} to the shared task Gendered Pronoun Resolution (Pair pronouns to their correct entities). Our final submission model based on the fine-tuned BERT (Bidirectional Encoder Representations from Transformers) ranks 14th among 838 teams with a multi-class logarithmic loss of 0.208. In this work, contribution of transfer learning technique to pronoun resolution systems is investigated and the gender bias contained in classification models is evaluated. | |
| Tasks | Transfer Learning |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3812/ |
| https://www.aclweb.org/anthology/W19-3812 | |
| PWC | https://paperswithcode.com/paper/transfer-learning-from-pre-trained-bert-for |
| Repo | |
| Framework | |
PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data
| Title | PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data |
| Authors | Zheng Tang, Milind Naphade, Stan Birchfield, Jonathan Tremblay, William Hodge, Ratnesh Kumar, Shuo Wang, Xiaodong Yang |
| Abstract | In comparison with person re-identification (ReID), which has been widely studied in the research community, vehicle ReID has received less attention. Vehicle ReID is challenging due to 1) high intra-class variability (caused by the dependency of shape and appearance on viewpoint), and 2) small inter-class variability (caused by the similarity in shape and appearance between vehicles produced by different manufacturers). To address these challenges, we propose a Pose-Aware Multi-Task Re-Identification (PAMTRI) framework. This approach includes two innovations compared with previous methods. First, it overcomes viewpoint-dependency by explicitly reasoning about vehicle pose and shape via keypoints, heatmaps and segments from pose estimation. Second, it jointly classifies semantic vehicle attributes (colors and types) while performing ReID, through multi-task learning with the embedded pose representations. Since manually labeling images with detailed pose and attribute information is prohibitive, we create a large-scale highly randomized synthetic dataset with automatically annotated vehicle attributes for training. Extensive experiments validate the effectiveness of each proposed component, showing that PAMTRI achieves significant improvement over state-of-the-art on two mainstream vehicle ReID benchmarks: VeRi and CityFlow-ReID. |
| Tasks | Multi-Task Learning, Person Re-Identification, Pose Estimation, Vehicle Re-Identification |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Tang_PAMTRI_Pose-Aware_Multi-Task_Learning_for_Vehicle_Re-Identification_Using_Highly_Randomized_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Tang_PAMTRI_Pose-Aware_Multi-Task_Learning_for_Vehicle_Re-Identification_Using_Highly_Randomized_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/pamtri-pose-aware-multi-task-learning-for |
| Repo | |
| Framework | |
Bigger versus Similar: Selecting a Background Corpus for First Story Detection Based on Distributional Similarity
| Title | Bigger versus Similar: Selecting a Background Corpus for First Story Detection Based on Distributional Similarity |
| Authors | Fei Wang, Robert J. Ross, John D. Kelleher |
| Abstract | The current state of the art for First Story Detection (FSD) are nearest neighbour-based models with traditional term vector representations; however, one challenge faced by FSD models is that the document representation is usually defined by the vocabulary and term frequency from a background corpus. Consequently, the ideal background corpus should arguably be both large-scale to ensure adequate term coverage, and similar to the target domain in terms of the language distribution. However, given these two factors cannot always be mutually satisfied, in this paper we examine whether the distributional similarity of common terms is more important than the scale of common terms for FSD. As a basis for our analysis we propose a set of metrics to quantitatively measure the scale of common terms and the distributional similarity between corpora. Using these metrics we rank different background corpora relative to a target corpus. We also apply models based on different background corpora to the FSD task. Our results show that term distributional similarity is more predictive of good FSD performance than the scale of common terms; and, thus we demonstrate that a smaller recent domain-related corpus will be more suitable than a very large-scale general corpus for FSD. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1150/ |
| https://www.aclweb.org/anthology/R19-1150 | |
| PWC | https://paperswithcode.com/paper/bigger-versus-similar-selecting-a-background |
| Repo | |
| Framework | |
AdaptiveFace: Adaptive Margin and Sampling for Face Recognition
| Title | AdaptiveFace: Adaptive Margin and Sampling for Face Recognition |
| Authors | Hao Liu, Xiangyu Zhu, Zhen Lei, Stan Z. Li |
| Abstract | Training large-scale unbalanced data is the central topic in face recognition. In the past two years, face recognition has achieved remarkable improvements due to the introduction of margin based Softmax loss. However, these methods have an implicit assumption that all the classes possess sufficient samples to describe its distribution, so that a manually set margin is enough to equally squeeze each intra-class variations. However, real face datasets are highly unbalanced, which means the classes have tremendously different numbers of samples. In this paper, we argue that the margin should be adapted to different classes. We propose the Adaptive Margin Softmax to adjust the margins for different classes adaptively. In addition to the unbalance challenge, face data always consists of large-scale classes and samples. Smartly selecting valuable classes and samples to participate in the training makes the training more effective and efficient. To this end, we also make the sampling process adaptive in two folds: Firstly, we propose the Hard Prototype Mining to adaptively select a small number of hard classes to participate in classification. Secondly, for data sampling, we introduce the Adaptive Data Sampling to find valuable samples for training adaptively. We combine these three parts together as AdaptiveFace. Extensive analysis and experiments on LFW, LFW BLUFR and MegaFace show that our method performs better than state-of-the-art methods using the same network architecture and training dataset. Code is available at https://github.com/haoliu1994/AdaptiveFace. |
| Tasks | Face Recognition |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Liu_AdaptiveFace_Adaptive_Margin_and_Sampling_for_Face_Recognition_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Liu_AdaptiveFace_Adaptive_Margin_and_Sampling_for_Face_Recognition_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/adaptiveface-adaptive-margin-and-sampling-for |
| Repo | |
| Framework | |
Co-Saliency Detection via Mask-Guided Fully Convolutional Networks With Multi-Scale Label Smoothing
| Title | Co-Saliency Detection via Mask-Guided Fully Convolutional Networks With Multi-Scale Label Smoothing |
| Authors | Kaihua Zhang, Tengpeng Li, Bo Liu, Qingshan Liu |
| Abstract | In image co-saliency detection problem, one critical issue is how to model the concurrent pattern of the co-salient parts, which appears both within each image and across all the relevant images. In this paper, we propose a hierarchical image co-saliency detection framework as a coarse to fine strategy to capture this pattern. We first propose a mask-guided fully convolutional network structure to generate the initial co-saliency detection result. The mask is used for background removal and it is learned from the high-level feature response maps of the pre-trained VGG-net output. We next propose a multi-scale label smoothing model to further refine the detection result. The proposed model jointly optimizes the label smoothness of pixels and superpixels. Experiment results on three popular image co-saliency detection benchmark datasets including iCoseg, MSRC and Cosal2015 demonstrate the remarkable performance compared with the state-of-the-art methods. |
| Tasks | Co-Saliency Detection, Saliency Detection |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Zhang_Co-Saliency_Detection_via_Mask-Guided_Fully_Convolutional_Networks_With_Multi-Scale_Label_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhang_Co-Saliency_Detection_via_Mask-Guided_Fully_Convolutional_Networks_With_Multi-Scale_Label_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/co-saliency-detection-via-mask-guided-fully |
| Repo | |
| Framework | |
Flare in Interference-Based Hyperspectral Cameras
| Title | Flare in Interference-Based Hyperspectral Cameras |
| Authors | Eden Sassoon, Yoav Y. Schechner, Tali Treibitz |
| Abstract | Stray light (flare) is formed inside cameras by internal reflections between optical elements. We point out a flare effect of significant magnitude and implication to snapshot hyperspectral imagers. Recent technologies enable placing interference-based filters on individual pixels in imaging sensors. These filters have narrow transmission bands around custom wavelengths and high transmission efficiency. Cameras using arrays of such filters are compact, robust and fast. However, as opposed to traditional broad-band filters, which often absorb unwanted light, narrow band-pass interference filters reflect non-transmitted light. This is a source of very significant flare which biases hyperspectral measurements. The bias in any pixel depends on spectral content in other pixels. We present a theoretical image formation model for this effect, and quantify it through simulations and experiments. In addition, we test deflaring of signals affected by such flare. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Sassoon_Flare_in_Interference-Based_Hyperspectral_Cameras_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Sassoon_Flare_in_Interference-Based_Hyperspectral_Cameras_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/flare-in-interference-based-hyperspectral |
| Repo | |
| Framework | |
VERI-Wild: A Large Dataset and a New Method for Vehicle Re-Identification in the Wild
| Title | VERI-Wild: A Large Dataset and a New Method for Vehicle Re-Identification in the Wild |
| Authors | Yihang Lou, Yan Bai, Jun Liu, Shiqi Wang, Lingyu Duan |
| Abstract | Vehicle Re-identification (ReID) is of great significance to the intelligent transportation and public security. However, many challenging issues of Vehicle ReID in real-world scenarios have not been fully investigated, e.g., the high viewpoint variations, extreme illumination conditions, complex backgrounds, and different camera sources. To promote the research of vehicle ReID in the wild, we collect a new dataset called VERI-Wild with the following distinct features: 1) The vehicle images are captured by a large surveillance system containing 174 cameras covering a large urban district (more than 200km^2) The camera network continuously captures vehicles for 24 hours in each day and lasts for 1 month. 3) It is the first vehicle ReID dataset that is collected from unconstrained conditionsns. It is also a large dataset containing more than 400 thousand images of 40 thousand vehicle IDs. In this paper, we also propose a new method for vehicle ReID, in which, the ReID model is coupled into a Feature Distance Adversarial Network (FDA-Net), and a novel feature distance adversary scheme is designed to generate hard negative samples in feature space to facilitate ReID model training. The comprehensive results show the effectiveness of our method on the proposed dataset and the other two existing datasets. |
| Tasks | Vehicle Re-Identification |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Lou_VERI-Wild_A_Large_Dataset_and_a_New_Method_for_Vehicle_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Lou_VERI-Wild_A_Large_Dataset_and_a_New_Method_for_Vehicle_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/veri-wild-a-large-dataset-and-a-new-method |
| Repo | |
| Framework | |
Unsupervised Learning of PCFGs with Normalizing Flow
| Title | Unsupervised Learning of PCFGs with Normalizing Flow |
| Authors | Lifeng Jin, Finale Doshi-Velez, Timothy Miller, Lane Schwartz, William Schuler |
| Abstract | Unsupervised PCFG inducers hypothesize sets of compact context-free rules as explanations for sentences. PCFG induction not only provides tools for low-resource languages, but also plays an important role in modeling language acquisition (Bannard et al., 2009; Abend et al. 2017). However, current PCFG induction models, using word tokens as input, are unable to incorporate semantics and morphology into induction, and may encounter issues of sparse vocabulary when facing morphologically rich languages. This paper describes a neural PCFG inducer which employs context embeddings (Peters et al., 2018) in a normalizing flow model (Dinh et al., 2015) to extend PCFG induction to use semantic and morphological information. Linguistically motivated sparsity and categorical distance constraints are imposed on the inducer as regularization. Experiments show that the PCFG induction model with normalizing flow produces grammars with state-of-the-art accuracy on a variety of different languages. Ablation further shows a positive effect of normalizing flow, context embeddings and proposed regularizers. |
| Tasks | Language Acquisition |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1234/ |
| https://www.aclweb.org/anthology/P19-1234 | |
| PWC | https://paperswithcode.com/paper/unsupervised-learning-of-pcfgs-with |
| Repo | |
| Framework | |
CECL at SemEval-2019 Task 3: Using Surface Learning for Detecting Emotion in Textual Conversations
| Title | CECL at SemEval-2019 Task 3: Using Surface Learning for Detecting Emotion in Textual Conversations |
| Authors | Yves Bestgen |
| Abstract | This paper describes the system developed by the Centre for English Corpus Linguistics for the SemEval-2019 Task 3: EmoContext. It aimed at classifying the emotion of a user utterance in a textual conversation as happy, sad, angry or other. It is based on a large number of feature types, mainly unigrams and bigrams, which were extracted by a SAS program. The usefulness of the different feature types was evaluated by means of Monte-Carlo resampling tests. As this system does not rest on any deep learning component, which is currently considered as the state-of-the-art approach, it can be seen as a possible point of comparison for such kind of systems. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2022/ |
| https://www.aclweb.org/anthology/S19-2022 | |
| PWC | https://paperswithcode.com/paper/cecl-at-semeval-2019-task-3-using-surface |
| Repo | |
| Framework | |
Book QA: Stories of Challenges and Opportunities
| Title | Book QA: Stories of Challenges and Opportunities |
| Authors | Stefanos Angelidis, Lea Frermann, Diego Marcheggiani, Roi Blanco, Llu{'\i}s M{`a}rquez |
| Abstract | We present a system for answering questions based on the full text of books (BookQA), which first selects book passages given a question at hand, and then uses a memory network to reason and predict an answer. To improve generalization, we pretrain our memory network using artificial questions generated from book sentences. We experiment with the recently published NarrativeQA corpus, on the subset of Who questions, which expect book characters as answers. We experimentally show that BERT-based retrieval and pretraining improve over baseline results significantly. At the same time, we confirm that NarrativeQA is a highly challenging data set, and that there is need for novel research in order to achieve high-precision BookQA results. We analyze some of the bottlenecks of the current approach, and we argue that more research is needed on text representation, retrieval of relevant passages, and reasoning, including commonsense knowledge. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5811/ |
| https://www.aclweb.org/anthology/D19-5811 | |
| PWC | https://paperswithcode.com/paper/book-qa-stories-of-challenges-and |
| Repo | |
| Framework | |
