Paper Group NANR 185
The University of Helsinki Submission to the WMT19 Parallel Corpus Filtering Task. SAPD：Soft Anchor-Point Detector. Latent semantic network induction in the context of linked example senses. Demo Application for LETO: Learning Engine Through Ontologies. Human-Guided Column Networks: Augmenting Deep Learning with Advice. Deli-Fisher GAN: Stable and …
The University of Helsinki Submission to the WMT19 Parallel Corpus Filtering Task
| Title | The University of Helsinki Submission to the WMT19 Parallel Corpus Filtering Task |
| Authors | Ra{'u}l V{'a}zquez, Umut Sulubacak, J{"o}rg Tiedemann |
| Abstract | This paper describes the University of Helsinki Language Technology group{'}s participation in the WMT 2019 parallel corpus filtering task. Our scores were produced using a two-step strategy. First, we individually applied a series of filters to remove the {`}bad{'} quality sentences. Then, we produced scores for each sentence by weighting these features with a classification model. This methodology allowed us to build a simple and reliable system that is easily adaptable to other language pairs. | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5441/ |
| https://www.aclweb.org/anthology/W19-5441 | |
| PWC | https://paperswithcode.com/paper/the-university-of-helsinki-submission-to-the |
| Repo | |
| Framework | |
SAPD：Soft Anchor-Point Detector
| Title | SAPD：Soft Anchor-Point Detector |
| Authors | Chenchen Zhu, Fangyi Chen, Zhiqiang Shen, Marios Savvides |
| Abstract | Recently, anchor-free detectors have shown great potential to outperform anchor-based detectors in terms of both accuracy and speed. In this work, we aim at finding a new balance of speed and accuracy for anchor-free detectors. Two questions are studied: 1) how to make the anchor-free detection head better? 2) how to utilize the power of feature pyramid better? We identify attention bias and feature selection as the main issues for these two questions respectively. We propose to address these issues with a novel training strategy that has two soften optimization techniques, i.e. soft-weighted anchor points and soft-selected pyramid levels. To evaluate the effectiveness, we train a single-stage anchor-free detector called Soft Anchor-Point Detector (SAPD). Experiments show that our concise SAPD pushes the envelope of speed/accuracy trade-off to a new level, outperforming recent state-of-the-art anchor-based and anchor-free, single-stage and multi-stage detectors. Without bells and whistles, our best model can achieve a single-model single-scale AP of 47.4% on COCO. Our fastest version can run up to 5x faster than other detectors with comparable accuracy. |
| Tasks | Feature Selection, Object Detection |
| Published | 2019-11-27 |
| URL | https://arxiv.org/abs/1911.12448 |
| https://arxiv.org/pdf/1911.12448.pdf | |
| PWC | https://paperswithcode.com/paper/sapdsoft-anchor-point-detector |
| Repo | |
| Framework | |
Latent semantic network induction in the context of linked example senses
| Title | Latent semantic network induction in the context of linked example senses |
| Authors | Hunter Heidenreich, Jake Williams |
| Abstract | The Princeton WordNet is a powerful tool for studying language and developing natural language processing algorithms. With significant work developing it further, one line considers its extension through aligning its expert-annotated structure with other lexical resources. In contrast, this work explores a completely data-driven approach to network construction, forming a wordnet using the entirety of the open-source, noisy, user-annotated dictionary, Wiktionary. Comparing baselines to WordNet, we find compelling evidence that our network induction process constructs a network with useful semantic structure. With thousands of semantically-linked examples that demonstrate sense usage from basic lemmas to multiword expressions (MWEs), we believe this work motivates future research. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5523/ |
| https://www.aclweb.org/anthology/D19-5523 | |
| PWC | https://paperswithcode.com/paper/latent-semantic-network-induction-in-the |
| Repo | |
| Framework | |
Demo Application for LETO: Learning Engine Through Ontologies
| Title | Demo Application for LETO: Learning Engine Through Ontologies |
| Authors | Suilan Estevez-Velarde, Andr{'e}s Montoyo, Yudivian Almeida-Cruz, Yoan Guti{'e}rrez, Alej Piad-Morffis, ro, Rafael Mu{~n}oz |
| Abstract | The massive amount of multi-formatted information available on the Web necessitates the design of software systems that leverage this information to obtain knowledge that is valid and useful. The main challenge is to discover relevant information and continuously update, enrich and integrate knowledge from various sources of structured and unstructured data. This paper presents the Learning Engine Through Ontologies(LETO) framework, an architecture for the continuous and incremental discovery of knowledge from multiple sources of unstructured and structured data. We justify the main design decision behind LETO{'}s architecture and evaluate the framework{'}s feasibility using the Internet Movie Data Base(IMDB) and Twitter as a practical application. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1032/ |
| https://www.aclweb.org/anthology/R19-1032 | |
| PWC | https://paperswithcode.com/paper/demo-application-for-leto-learning-engine |
| Repo | |
| Framework | |
Human-Guided Column Networks: Augmenting Deep Learning with Advice
| Title | Human-Guided Column Networks: Augmenting Deep Learning with Advice |
| Authors | Mayukh Das, Yang Yu, Devendra Singh Dhami, Gautam Kunapuli, Sriraam Natarajan |
| Abstract | While extremely successful in several applications, especially with low-level representations; sparse, noisy samples and structured domains (with multiple objects and interactions) are some of the open challenges in most deep models. Column Networks, a deep architecture, can succinctly capture such domain structure and interactions, but may still be prone to sub-optimal learning from sparse and noisy samples. Inspired by the success of human-advice guided learning in AI, especially in data-scarce domains, we propose Knowledge-augmented Column Networks that leverage human advice/knowledge for better learning with noisy/sparse samples. Our experiments demonstrate how our approach leads to either superior overall performance or faster convergence. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HJeOMhA5K7 |
| https://openreview.net/pdf?id=HJeOMhA5K7 | |
| PWC | https://paperswithcode.com/paper/human-guided-column-networks-augmenting-deep |
| Repo | |
| Framework | |
Deli-Fisher GAN: Stable and Efficient Image Generation With Structured Latent Generative Space
| Title | Deli-Fisher GAN: Stable and Efficient Image Generation With Structured Latent Generative Space |
| Authors | Boli Fang, Chuck Jia, Miao Jiang, Dhawal Chaturvedi |
| Abstract | Generative Adversarial Networks (GANs) are powerful tools for realistic image generation. However, a major drawback of GANs is that they are especially hard to train, often requiring large amounts of data and long training time. In this paper we propose the Deli-Fisher GAN, a GAN that generates photo-realistic images by enforcing structure on the latent generative space using similar approaches in \cite{deligan}. The structure of the latent space we consider in this paper is modeled as a mixture of Gaussians, whose parameters are learned in the training process. Furthermore, to improve stability and efficiency, we use the Fisher Integral Probability Metric as the divergence measure in our GAN model, instead of the Jensen-Shannon divergence. We show by experiments that the Deli-Fisher GAN performs better than DCGAN, WGAN, and the Fisher GAN as measured by inception score. |
| Tasks | Image Generation |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HyMuaiAqY7 |
| https://openreview.net/pdf?id=HyMuaiAqY7 | |
| PWC | https://paperswithcode.com/paper/deli-fisher-gan-stable-and-efficient-image |
| Repo | |
| Framework | |
Corpus-based Check-up for Thesaurus
| Title | Corpus-based Check-up for Thesaurus |
| Authors | Natalia Loukachevitch |
| Abstract | In this paper we discuss the usefulness of applying a checking procedure to existing thesauri. The procedure is based on the analysis of discrepancies of corpus-based and thesaurus-based word similarities. We applied the procedure to more than 30 thousand words of the Russian wordnet and found some serious errors in word sense description, including inaccurate relationships and missing senses of ambiguous words. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1577/ |
| https://www.aclweb.org/anthology/P19-1577 | |
| PWC | https://paperswithcode.com/paper/corpus-based-check-up-for-thesaurus |
| Repo | |
| Framework | |
The FEVER2.0 Shared Task
| Title | The FEVER2.0 Shared Task |
| Authors | James Thorne, Andreas Vlachos, Oana Cocarascu, Christos Christodoulopoulos, Arpit Mittal |
| Abstract | We present the results of the second Fact Extraction and VERification (FEVER2.0) Shared Task. The task challenged participants to both build systems to verify factoid claims using evidence retrieved from Wikipedia and to generate adversarial attacks against other participant{'}s systems. The shared task had three phases: \textit{building, breaking and fixing}. There were 8 systems in the builder{'}s round, three of which were new qualifying submissions for this shared task, and 5 adversaries generated instances designed to induce classification errors and one builder submitted a fixed system which had higher FEVER score and resilience than their first submission. All but one newly submitted systems attained FEVER scores higher than the best performing system from the first shared task and under adversarial evaluation, all systems exhibited losses in FEVER score. There was a great variety in adversarial attack types as well as the techniques used to generate the attacks, In this paper, we present the results of the shared task and a summary of the systems, highlighting commonalities and innovations among participating systems. |
| Tasks | Adversarial Attack |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6601/ |
| https://www.aclweb.org/anthology/D19-6601 | |
| PWC | https://paperswithcode.com/paper/the-fever20-shared-task |
| Repo | |
| Framework | |
Nuclei Segmentation via a Deep Panoptic Model with Semantic Feature Fusion
| Title | Nuclei Segmentation via a Deep Panoptic Model with Semantic Feature Fusion |
| Authors | Dongnan Liu, Donghao Zhang, Yang Song, Chaoyi Zhang, Fan Zhang, Lauren O’Donnell, Weidong Cai |
| Abstract | Automated detection and segmentation of individual nuclei in histopathology images is important for cancer diagnosis and prognosis. Due to the high variability of nuclei appearances and numerous overlapping objects, this task still remains challenging. eep learning based semantic and instance segmentation models have been proposed to address the challenges, but these methods tend to concentrate on either the global or local features and hence still suffer from information loss. In this work, we propose a panoptic segmentation model which incorporates an auxiliary semantic segmentation branch with the instance branch to integrate global and local features. Furthermore, we design a feature map fusion mechanism in the instance branch and a new mask generator to prevent information loss. Experimental results on three different histopathology datasets demonstrate that our method outperforms the state-of-the-art nuclei segmentation methods and popular semantic and instance segmentation models by a large margin. |
| Tasks | Instance Segmentation, Nuclear Segmentation, Panoptic Segmentation, Semantic Segmentation |
| Published | 2019-08-10 |
| URL | https://www.researchgate.net/publication/334843766_Nuclei_Segmentation_via_a_Deep_Panoptic_Model_with_Semantic_Feature_Fusion |
| https://www.ijcai.org/proceedings/2019/0121.pdf | |
| PWC | https://paperswithcode.com/paper/nuclei-segmentation-via-a-deep-panoptic-model |
| Repo | |
| Framework | |
A Spreading Activation Framework for Tracking Conceptual Complexity of Texts
| Title | A Spreading Activation Framework for Tracking Conceptual Complexity of Texts |
| Authors | Ioana Hulpu{\textcommabelow{s}}, Sanja {\v{S}}tajner, Heiner Stuckenschmidt |
| Abstract | We propose an unsupervised approach for assessing conceptual complexity of texts, based on spreading activation. Using DBpedia knowledge graph as a proxy to long-term memory, mentioned concepts become activated and trigger further activation as the text is sequentially traversed. Drawing inspiration from psycholinguistic theories of reading comprehension, we model memory processes such as semantic priming, sentence wrap-up, and forgetting. We show that our models capture various aspects of conceptual text complexity and significantly outperform current state of the art. |
| Tasks | Reading Comprehension |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1377/ |
| https://www.aclweb.org/anthology/P19-1377 | |
| PWC | https://paperswithcode.com/paper/a-spreading-activation-framework-for-tracking |
| Repo | |
| Framework | |
Learning Shape-Aware Embedding for Scene Text Detection
| Title | Learning Shape-Aware Embedding for Scene Text Detection |
| Authors | Zhuotao Tian, Michelle Shu, Pengyuan Lyu, Ruiyu Li, Chao Zhou, Xiaoyong Shen, Jiaya Jia |
| Abstract | We address the problem of detecting scene text in arbitrary shapes, which is a challenging task due to the high variety and complexity of the scene. Specifically, we treat text detection as instance segmentation and propose a segmentation-based framework, which extracts each text instance as an independent connected component. To distinguish different text instances, our method maps pixels onto an embedding space where pixels belonging to the same text are encouraged to appear closer to each other and vise versa. In addition, we introduce a Shape-Aware Loss to make training adaptively accommodate various aspect ratios of text instances and the tiny gaps among them, and a new post-processing pipeline to yield precise bounding box predictions. Experimental results on three challenging datasets (ICDAR15, MSRA-TD500 and CTW1500) demonstrate the effectiveness of our work. |
| Tasks | Instance Segmentation, Scene Text Detection, Semantic Segmentation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Tian_Learning_Shape-Aware_Embedding_for_Scene_Text_Detection_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Tian_Learning_Shape-Aware_Embedding_for_Scene_Text_Detection_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-shape-aware-embedding-for-scene-text |
| Repo | |
| Framework | |
Opinions Summarization: Aspect Similarity Recognition Relaxes The Constraint of Predefined Aspects
| Title | Opinions Summarization: Aspect Similarity Recognition Relaxes The Constraint of Predefined Aspects |
| Authors | Nguyen Huy Tien, Le Tung Thanh, Nguyen Minh Le |
| Abstract | Recently research in opinions summarization focuses on rating expressions by aspects and/or sentiments they carry. To extract aspects of an expression, most studies require a predefined list of aspects or at least the number of aspects. Instead of extracting aspects, we rate expressions by aspect similarity recognition (ASR), which evaluates whether two expressions share at least one aspect. This subtask relaxes the limitation of predefining aspects and makes our opinions summarization applicable in domain adaptation. For the ASR subtask, we propose an attention-cell LSTM model, which integrates attention signals into the LSTM gates. According to the experimental results, the attention-cell LSTM works efficiently for learning latent aspects between two sentences in both settings of in-domain and cross-domain. In addition, the proposed extractive summarization method using ASR shows significant improvements over baselines on the Opinosis corpus. |
| Tasks | Domain Adaptation |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1058/ |
| https://www.aclweb.org/anthology/R19-1058 | |
| PWC | https://paperswithcode.com/paper/opinions-summarization-aspect-similarity |
| Repo | |
| Framework | |
Pre-trained Contextualized Character Embeddings Lead to Major Improvements in Time Normalization: a Detailed Analysis
| Title | Pre-trained Contextualized Character Embeddings Lead to Major Improvements in Time Normalization: a Detailed Analysis |
| Authors | Dongfang Xu, Egoitz Laparra, Steven Bethard |
| Abstract | Recent studies have shown that pre-trained contextual word embeddings, which assign the same word different vectors in different contexts, improve performance in many tasks. But while contextual embeddings can also be trained at the character level, the effectiveness of such embeddings has not been studied. We derive character-level contextual embeddings from Flair (Akbik et al., 2018), and apply them to a time normalization task, yielding major performance improvements over the previous state-of-the-art: 51{%} error reduction in news and 33{%} in clinical notes. We analyze the sources of these improvements, and find that pre-trained contextual character embeddings are more robust to term variations, infrequent terms, and cross-domain changes. We also quantify the size of context that pre-trained contextual character embeddings take advantage of, and show that such embeddings capture features like part-of-speech and capitalization. |
| Tasks | Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-1008/ |
| https://www.aclweb.org/anthology/S19-1008 | |
| PWC | https://paperswithcode.com/paper/pre-trained-contextualized-character |
| Repo | |
| Framework | |
ClusterSLAM: A SLAM Backend for Simultaneous Rigid Body Clustering and Motion Estimation
| Title | ClusterSLAM: A SLAM Backend for Simultaneous Rigid Body Clustering and Motion Estimation |
| Authors | Jiahui Huang, Sheng Yang, Zishuo Zhao, Yu-Kun Lai, Shi-Min Hu |
| Abstract | We present a practical backend for stereo visual SLAM which can simultaneously discover individual rigid bodies and compute their motions in dynamic environments. While recent factor graph based state optimization algorithms have shown their ability to robustly solve SLAM problems by treating dynamic objects as outliers, the dynamic motions are rarely considered. In this paper, we exploit the consensus of 3D motions among the landmarks extracted from the same rigid body for clustering and estimating static and dynamic objects in a unified manner. Specifically, our algorithm builds a noise-aware motion affinity matrix upon landmarks, and uses agglomerative clustering for distinguishing those rigid bodies. Accompanied by a decoupled factor graph optimization for revising their shape and trajectory, we obtain an iterative scheme to update both cluster assignments and motion estimation reciprocally. Evaluations on both synthetic scenes and KITTI demonstrate the capability of our approach, and further experiments considering online efficiency also show the effectiveness of our method for simultaneous tracking of ego-motion and multiple objects. |
| Tasks | Motion Estimation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Huang_ClusterSLAM_A_SLAM_Backend_for_Simultaneous_Rigid_Body_Clustering_and_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Huang_ClusterSLAM_A_SLAM_Backend_for_Simultaneous_Rigid_Body_Clustering_and_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/clusterslam-a-slam-backend-for-simultaneous |
| Repo | |
| Framework | |
Neighborhood Preserving Hashing for Scalable Video Retrieval
| Title | Neighborhood Preserving Hashing for Scalable Video Retrieval |
| Authors | Shuyan Li, Zhixiang Chen, Jiwen Lu, Xiu Li, Jie Zhou |
| Abstract | In this paper, we propose a Neighborhood Preserving Hashing (NPH) method for scalable video retrieval in an unsupervised manner. Unlike most existing deep video hashing methods which indiscriminately compress an entire video into a binary code, we embed the spatial-temporal neighborhood information into the encoding network such that the neighborhood-relevant visual content of a video can be preferentially encoded into a binary code under the guidance of the neighborhood information. Specifically, we propose a neighborhood attention mechanism which focuses on partial useful content of each input frame conditioned on the neighborhood information. We then integrate the neighborhood attention mechanism into an RNN-based reconstruction scheme to encourage the binary codes to capture the spatial-temporal structure in a video which is consistent with that in the neighborhood. As a consequence, the learned hashing functions can map similar videos to similar binary codes. Extensive experiments on three widely-used benchmark datasets validate the effectiveness of our proposed approach. |
| Tasks | Video Retrieval |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Li_Neighborhood_Preserving_Hashing_for_Scalable_Video_Retrieval_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Li_Neighborhood_Preserving_Hashing_for_Scalable_Video_Retrieval_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/neighborhood-preserving-hashing-for-scalable |
| Repo | |
| Framework | |
