Paper Group NANR 145
Learning Scene Geometry for Visual Localization in Challenging Conditions. CAiRE_HKUST at SemEval-2019 Task 3: Hierarchical Attention for Dialogue Emotion Classification. Proceedings of the Sixth Workshop on Computational Linguistics and Clinical Psychology. Improved Generalization of Arabic Text Classifiers. Multilingual prediction of Alzheimer’s …
Learning Scene Geometry for Visual Localization in Challenging Conditions
| Title | Learning Scene Geometry for Visual Localization in Challenging Conditions |
| Authors | Nathan Piasco, Desire Sidibe, Valerie Gouet-Brunet，Cedric Demonceaux1 |
| Abstract | We propose a new approach for outdoor large scale image based localization that can deal with challenging scenarios like cross-season, cross-weather, day/night and longterm localization. The key component of our method is a new learned global image descriptor, that can effectively benefit from scene geometry information during training. At test time, our system is capable of inferring the depth map related to the query image and use it to increase localization accuracy.We are able to increase recall@1 performances by 2.15% on cross-weather and long-term localization scenario and by 4.24% points on a challenging winter/summer localization sequence versus state-of-the-art methods. Our method can also use weakly annotated data to localize night images across a reference dataset of daytime images. |
| Tasks | Image-Based Localization, Visual Localization |
| Published | 2019-05-01 |
| URL | https://hal.archives-ouvertes.fr/hal-02057378/document |
| https://hal.archives-ouvertes.fr/hal-02057378/document | |
| PWC | https://paperswithcode.com/paper/learning-scene-geometry-for-visual |
| Repo | |
| Framework | |
CAiRE_HKUST at SemEval-2019 Task 3: Hierarchical Attention for Dialogue Emotion Classification
| Title | CAiRE_HKUST at SemEval-2019 Task 3: Hierarchical Attention for Dialogue Emotion Classification |
| Authors | Genta Indra Winata, Andrea Madotto, Zhaojiang Lin, Jamin Shin, Yan Xu, Peng Xu, Pascale Fung |
| Abstract | Detecting emotion from dialogue is a challenge that has not yet been extensively surveyed. One could consider the emotion of each dialogue turn to be independent, but in this paper, we introduce a hierarchical approach to classify emotion, hypothesizing that the current emotional state depends on previous latent emotions. We benchmark several feature-based classifiers using pre-trained word and emotion embeddings, state-of-the-art end-to-end neural network models, and Gaussian processes for automatic hyper-parameter search. In our experiments, hierarchical architectures consistently give significant improvements, and our best model achieves a 76.77{%} F1-score on the test set. |
| Tasks | Emotion Classification, Gaussian Processes |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2021/ |
| https://www.aclweb.org/anthology/S19-2021 | |
| PWC | https://paperswithcode.com/paper/caire_hkust-at-semeval-2019-task-3 |
| Repo | |
| Framework | |
Proceedings of the Sixth Workshop on Computational Linguistics and Clinical Psychology
| Title | Proceedings of the Sixth Workshop on Computational Linguistics and Clinical Psychology |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-3000/ |
| https://www.aclweb.org/anthology/W19-3000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-sixth-workshop-on-1 |
| Repo | |
| Framework | |
Improved Generalization of Arabic Text Classifiers
| Title | Improved Generalization of Arabic Text Classifiers |
| Authors | Alaa Khaddaj, Hazem Hajj, Wassim El-Hajj |
| Abstract | While transfer learning for text has been very active in the English language, progress in Arabic has been slow, including the use of Domain Adaptation (DA). Domain Adaptation is used to generalize the performance of any classifier by trying to balance the classifier{'}s accuracy for a particular task among different text domains. In this paper, we propose and evaluate two variants of a domain adaptation technique: the first is a base model called Domain Adversarial Neural Network (DANN), while the second is a variation that incorporates representational learning. Similar to previous approaches, we propose the use of proxy A-distance as a metric to assess the success of generalization. We make use of ArSentDLEV, a multi-topic dataset collected from the Levantine countries, to test the performance of the models. We show the superiority of the proposed method in accuracy and robustness when dealing with the Arabic language. |
| Tasks | Domain Adaptation, Transfer Learning |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4618/ |
| https://www.aclweb.org/anthology/W19-4618 | |
| PWC | https://paperswithcode.com/paper/improved-generalization-of-arabic-text |
| Repo | |
| Framework | |
Multilingual prediction of Alzheimer’s disease through domain adaptation and concept-based language modelling
| Title | Multilingual prediction of Alzheimer’s disease through domain adaptation and concept-based language modelling |
| Authors | Kathleen C. Fraser, Nicklas Linz, Bai Li, Kristina Lundholm Fors, Frank Rudzicz, Alex K{"o}nig, ra, Alex, Jan ersson, Philippe Robert, Dimitrios Kokkinakis |
| Abstract | There is growing evidence that changes in speech and language may be early markers of dementia, but much of the previous NLP work in this area has been limited by the size of the available datasets. Here, we compare several methods of domain adaptation to augment a small French dataset of picture descriptions (n = 57) with a much larger English dataset (n = 550), for the task of automatically distinguishing participants with dementia from controls. The first challenge is to identify a set of features that transfer across languages; in addition to previously used features based on information units, we introduce a new set of features to model the order in which information units are produced by dementia patients and controls. These concept-based language model features improve classification performance in both English and French separately, and the best result (AUC = 0.89) is achieved using the multilingual training set with a combination of information and language model features. |
| Tasks | Domain Adaptation, Language Modelling |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1367/ |
| https://www.aclweb.org/anthology/N19-1367 | |
| PWC | https://paperswithcode.com/paper/multilingual-prediction-of-alzheimers-disease |
| Repo | |
| Framework | |
Building a De-identification System for Real Swedish Clinical Text Using Pseudonymised Clinical Text
| Title | Building a De-identification System for Real Swedish Clinical Text Using Pseudonymised Clinical Text |
| Authors | Hanna Berg, Taridzo Chomutare, Hercules Dalianis |
| Abstract | This article presents experiments with pseudonymised Swedish clinical text used as training data to de-identify real clinical text with the future aim to transfer non-sensitive training data to other hospitals. Conditional Random Fields (CFR) and Long Short-Term Memory (LSTM) machine learning algorithms were used to train de-identification models. The two models were trained on pseudonymised data and evaluated on real data. For benchmarking, models were also trained on real data, and evaluated on real data as well as trained on pseudonymised data and evaluated on pseudonymised data. CRF showed better performance for some PHI information like Date Part, First Name and Last Name; consistent with some reports in the literature. In contrast, poor performances on Location and Health Care Unit information were noted, partially due to the constrained vocabulary in the pseudonymised training data. It is concluded that it is possible to train transferable models based on pseudonymised Swedish clinical data, but even small narrative and distributional variation could negatively impact performance. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6215/ |
| https://www.aclweb.org/anthology/D19-6215 | |
| PWC | https://paperswithcode.com/paper/building-a-de-identification-system-for-real |
| Repo | |
| Framework | |
SYSTRAN @ WAT 2019: Russian-Japanese News Commentary task
| Title | SYSTRAN @ WAT 2019: Russian-Japanese News Commentary task |
| Authors | Jitao Xu, TuAnh Nguyen, MinhQuang Pham, Josep Crego, Jean Senellart |
| Abstract | This paper describes Systran{'}s submissions to WAT 2019 Russian-Japanese News Commentary task. A challenging translation task due to the extremely low resources available and the distance of the language pair. We have used the neural Transformer architecture learned over the provided resources and we carried out synthetic data generation experiments which aim at alleviating the data scarcity problem. Results indicate the suitability of the data augmentation experiments, enabling our systems to rank first according to automatic evaluations. |
| Tasks | Data Augmentation, Synthetic Data Generation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5225/ |
| https://www.aclweb.org/anthology/D19-5225 | |
| PWC | https://paperswithcode.com/paper/systran-wat-2019-russian-japanese-news |
| Repo | |
| Framework | |
Topic-Guided Coherence Modeling for Sentence Ordering by Preserving Global and Local Information
| Title | Topic-Guided Coherence Modeling for Sentence Ordering by Preserving Global and Local Information |
| Authors | Byungkook Oh, Seungmin Seo, Cheolheon Shin, Eunju Jo, Kyong-Ho Lee |
| Abstract | We propose a novel topic-guided coherence modeling (TGCM) for sentence ordering. Our attention based pointer decoder directly utilize sentence vectors in a permutation-invariant manner, without being compressed into a single fixed-length vector as the paragraph representation. Thus, TGCM can improve global dependencies among sentences and preserve relatively informative paragraph-level semantics. Moreover, to predict the next sentence, we capture topic-enhanced sentence-pair interactions between the current predicted sentence and each next-sentence candidate. With the coherent topical context matching, we promote local dependencies that help identify the tight semantic connections for sentence ordering. The experimental results show that TGCM outperforms state-of-the-art models from various perspectives. |
| Tasks | Sentence Ordering |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1232/ |
| https://www.aclweb.org/anthology/D19-1232 | |
| PWC | https://paperswithcode.com/paper/topic-guided-coherence-modeling-for-sentence |
| Repo | |
| Framework | |
Learning Relationships for Multi-View 3D Object Recognition
| Title | Learning Relationships for Multi-View 3D Object Recognition |
| Authors | Ze Yang, Liwei Wang |
| Abstract | Recognizing 3D object has attracted plenty of attention recently, and view-based methods have achieved best results until now. However, previous view-based methods ignore the region-to-region and view-to-view relationships between different view images, which are crucial for multi-view 3D object representation. To tackle this problem, we propose a Relation Network to effectively connect corresponding regions from different viewpoints, and therefore reinforce the information of individual view image. In addition, the Relation Network exploits the inter-relationships over a group of views, and integrates those views to obtain a discriminative 3D object representation. Systematic experiments conducted on ModelNet dataset demonstrate the effectiveness of our proposed methods for both 3D object recognition and retrieval tasks. |
| Tasks | 3D Object Recognition, Object Recognition |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Yang_Learning_Relationships_for_Multi-View_3D_Object_Recognition_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Yang_Learning_Relationships_for_Multi-View_3D_Object_Recognition_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-relationships-for-multi-view-3d |
| Repo | |
| Framework | |
Arabic Dialect Identification for Travel and Twitter Text
| Title | Arabic Dialect Identification for Travel and Twitter Text |
| Authors | Pruthwik Mishra, V Mujadia, an |
| Abstract | This paper presents the results of the experiments done as a part of MADAR Shared Task in WANLP 2019 on Arabic Fine-Grained Dialect Identification. Dialect Identification is one of the prominent tasks in the field of Natural language processing where the subsequent language modules can be improved based on it. We explored the use of different features like char, word n-gram, language model probabilities, etc on different classifiers. Results show that these features help to improve dialect classification accuracy. Results also show that traditional machine learning classifier tends to perform better when compared to neural network models on this task in a low resource setting. |
| Tasks | Language Modelling |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4628/ |
| https://www.aclweb.org/anthology/W19-4628 | |
| PWC | https://paperswithcode.com/paper/arabic-dialect-identification-for-travel-and |
| Repo | |
| Framework | |
Adaptive Transfer Network for Cross-Domain Person Re-Identification
| Title | Adaptive Transfer Network for Cross-Domain Person Re-Identification |
| Authors | Jiawei Liu, Zheng-Jun Zha, Di Chen, Richang Hong, Meng Wang |
| Abstract | Recent deep learning based person re-identification approaches have steadily improved the performance for benchmarks, however they often fail to generalize well from one domain to another. In this work, we propose a novel adaptive transfer network (ATNet) for effective cross-domain person re-identification. ATNet looks into the essential causes of domain gap and addresses it following the principle of “divide-and-conquer”. It decomposes the complicated cross-domain transfer into a set of factor-wise sub-transfers, each of which concentrates on style transfer with respect to a certain imaging factor, e.g., illumination, resolution and camera view etc. An adaptive ensemble strategy is proposed to fuse factor-wise transfers by perceiving the affect magnitudes of various factors on images. Such “decomposition-and-ensemble” strategy gives ATNet the capability of precise style transfer at factor level and eventually effective transfer across domains. In particular, ATNet consists of a transfer network composed by multiple factor-wise CycleGANs and an ensemble CycleGAN as well as a selection network that infers the affects of different factors on transferring each image. Extensive experimental results on three widely-used datasets, i.e., Market-1501, DukeMTMC-reID and PRID2011 have demonstrated the effectiveness of the proposed ATNet with significant performance improvements over state-of-the-art methods. |
| Tasks | Person Re-Identification, Style Transfer |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Liu_Adaptive_Transfer_Network_for_Cross-Domain_Person_Re-Identification_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Liu_Adaptive_Transfer_Network_for_Cross-Domain_Person_Re-Identification_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-transfer-network-for-cross-domain |
| Repo | |
| Framework | |
SimVecs: Similarity-Based Vectors for Utterance Representation in Conversational AI Systems
| Title | SimVecs: Similarity-Based Vectors for Utterance Representation in Conversational AI Systems |
| Authors | Ashraf Mahgoub, Youssef Shahin, Riham Mansour, Saurabh Bagchi |
| Abstract | Conversational AI systems are gaining a lot of attention recently in both industrial and scientific domains, providing a natural way of interaction between customers and adaptive intelligent systems. A key requirement in these systems is the ability to understand the user{'}s intent and provide adequate responses to them. One of the greatest challenges of language understanding (LU) services is efficient utterance (sentence) representation in vector space, which is an essential step for most ML tasks. In this paper, we propose a novel approach for generating vector space representations of utterances using pair-wise similarity metrics. The proposed approach uses only a few corpora to tune the weights of the similarity metric without relying on external general purpose ontologies. Our experiments confirm that the generated vectors can improve the performance of LU services in unsupervised, semi-supervised and supervised learning tasks. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1066/ |
| https://www.aclweb.org/anthology/K19-1066 | |
| PWC | https://paperswithcode.com/paper/simvecs-similarity-based-vectors-for |
| Repo | |
| Framework | |
Designing a Frame-Semantic Machine Translation Evaluation Metric
| Title | Designing a Frame-Semantic Machine Translation Evaluation Metric |
| Authors | Oliver Czulo, Tiago Torrent, Ely Matos, Alex Costa, re Diniz da, Debanjana Kar |
| Abstract | We propose a metric for machine translation evaluation based on frame semantics which does not require the use of reference translations or human corrections, but is aimed at comparing original and translated output directly. The metrics is described on the basis of an existing manual frame-semantic annotation of a parallel corpus with an English original and a Brazilian Portuguese and a German translation. We discuss implications of our metrics design, including the potential of scaling it for multiple languages. |
| Tasks | Machine Translation |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8704/ |
| https://www.aclweb.org/anthology/W19-8704 | |
| PWC | https://paperswithcode.com/paper/designing-a-frame-semantic-machine |
| Repo | |
| Framework | |
Fast and Practical Neural Architecture Search
| Title | Fast and Practical Neural Architecture Search |
| Authors | Jiequan Cui, Pengguang Chen, Ruiyu Li, Shu Liu, Xiaoyong Shen, Jiaya Jia |
| Abstract | In this paper, we propose a fast and practical neural architecture search (FPNAS) framework for automatic network design. FPNAS aims to discover extremely efficient networks with less than 300M FLOPs. Different from previous NAS methods, our approach searches for the whole network architecture to guarantee block diversity instead of stacking a set of similar blocks repeatedly. We model the search process as a bi-level optimization problem and propose an approximation solution. On CIFAR-10, our approach is capable of design networks with comparable performance to state-of-the-arts while using orders of magnitude less computational resource with only 20 GPU hours. Experimental results on ImageNet and ADE20K datasets further demonstrate transferability of the searched networks. |
| Tasks | Neural Architecture Search |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Cui_Fast_and_Practical_Neural_Architecture_Search_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Cui_Fast_and_Practical_Neural_Architecture_Search_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/fast-and-practical-neural-architecture-search |
| Repo | |
| Framework | |
No Army, No Navy: BERT Semi-Supervised Learning of Arabic Dialects
| Title | No Army, No Navy: BERT Semi-Supervised Learning of Arabic Dialects |
| Authors | Chiyu Zhang, Muhammad Abdul-Mageed |
| Abstract | We present our deep leaning system submitted to MADAR shared task 2 focused on twitter user dialect identification. We develop tweet-level identification models based on GRUs and BERT in supervised and semi-supervised set-tings. We then introduce a simple, yet effective, method of porting tweet-level labels at the level of users. Our system ranks top 1 in the competition, with 71.70{%} macro F1 score and 77.40{%} accuracy. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4637/ |
| https://www.aclweb.org/anthology/W19-4637 | |
| PWC | https://paperswithcode.com/paper/no-army-no-navy-bert-semi-supervised-learning |
| Repo | |
| Framework | |
