Paper Group NANR 97
Team Bertha von Suttner at SemEval-2019 Task 4: Hyperpartisan News Detection using ELMo Sentence Representation Convolutional Network. An Iterative and Cooperative Top-Down and Bottom-Up Inference Network for Salient Object Detection. Word-Node2Vec: Improving Word Embedding with Document-Level Non-Local Word Co-occurrences. CUED@WMT19:EWC&LMs. Bai …
Team Bertha von Suttner at SemEval-2019 Task 4: Hyperpartisan News Detection using ELMo Sentence Representation Convolutional Network
| Title | Team Bertha von Suttner at SemEval-2019 Task 4: Hyperpartisan News Detection using ELMo Sentence Representation Convolutional Network |
| Authors | Ye Jiang, Johann Petrak, Xingyi Song, Kalina Bontcheva, Diana Maynard |
| Abstract | This paper describes the participation of team {``}bertha-von-suttner{''} in the SemEval2019 task 4 Hyperpartisan News Detection task. Our system uses sentence representations from averaged word embeddings generated from the pre-trained ELMo model with Convolutional Neural Networks and Batch Normalization for predicting hyperpartisan news. The final predictions were generated from the averaged predictions of an ensemble of models. With this architecture, our system ranked in first place, based on accuracy, the official scoring metric. | |
| Tasks | Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2146/ |
| https://www.aclweb.org/anthology/S19-2146 | |
| PWC | https://paperswithcode.com/paper/team-bertha-von-suttner-at-semeval-2019-task |
| Repo | |
| Framework | |
An Iterative and Cooperative Top-Down and Bottom-Up Inference Network for Salient Object Detection
| Title | An Iterative and Cooperative Top-Down and Bottom-Up Inference Network for Salient Object Detection |
| Authors | Wenguan Wang, Jianbing Shen, Ming-Ming Cheng, Ling Shao |
| Abstract | This paper presents a salient object detection method that integrates both top-down and bottom-up saliency inference in an iterative and cooperative manner. The top-down process is used for coarse-to-fine saliency estimation, where high-level saliency is gradually integrated with finer lower-layer features to obtain a fine-grained result. The bottom-up process infers the high-level, but rough saliency through gradually using upper-layer, semantically-richer features. These two processes are alternatively performed, where the bottom-up process uses the fine-grained saliency obtained from the top-down process to yield enhanced high-level saliency estimate, and the top-down process, in turn, is further benefited from the improved high-level information. The network layers in the bottom-up/top-down processes are equipped with recurrent mechanisms for layer-wise, step-by-step optimization. Thus, saliency information is effectively encouraged to flow in a bottom-up, top-down and intra-layer manner. We show that most other saliency models based on fully convolutional networks (FCNs) are essentially variants of our model. Extensive experiments on several famous benchmarks clearly demonstrate the superior performance, good generalization, and powerful learning ability of our proposed saliency inference framework. |
| Tasks | Object Detection, Saliency Prediction, Salient Object Detection |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Wang_An_Iterative_and_Cooperative_Top-Down_and_Bottom-Up_Inference_Network_for_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_An_Iterative_and_Cooperative_Top-Down_and_Bottom-Up_Inference_Network_for_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/an-iterative-and-cooperative-top-down-and |
| Repo | |
| Framework | |
Word-Node2Vec: Improving Word Embedding with Document-Level Non-Local Word Co-occurrences
| Title | Word-Node2Vec: Improving Word Embedding with Document-Level Non-Local Word Co-occurrences |
| Authors | Procheta Sen, Debasis Ganguly, Gareth Jones |
| Abstract | A standard word embedding algorithm, such as word2vec and glove, makes a strong assumption that words are likely to be semantically related only if they co-occur locally within a window of fixed size. However, this strong assumption may not capture the semantic association between words that co-occur frequently but non-locally within documents. In this paper, we propose a graph-based word embedding method, named {`}word-node2vec{'}. By relaxing the strong constraint of locality, our method is able to capture both the local and non-local co-occurrences. Word-node2vec constructs a graph where every node represents a word and an edge between two nodes represents a combination of both local (e.g. word2vec) and document-level co-occurrences. Our experiments show that word-node2vec outperforms word2vec and glove on a range of different tasks, such as predicting word-pair similarity, word analogy and concept categorization. | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1109/ |
| https://www.aclweb.org/anthology/N19-1109 | |
| PWC | https://paperswithcode.com/paper/word-node2vec-improving-word-embedding-with |
| Repo | |
| Framework | |
CUED@WMT19:EWC&LMs
| Title | CUED@WMT19:EWC&LMs |
| Authors | Felix Stahlberg, Danielle Saunders, Adri{`a} de Gispert, Bill Byrne |
| Abstract | Two techniques provide the fabric of the Cambridge University Engineering Department{'}s (CUED) entry to the WMT19 evaluation campaign: elastic weight consolidation (EWC) and different forms of language modelling (LMs). We report substantial gains by fine-tuning very strong baselines on former WMT test sets using a combination of checkpoint averaging and EWC. A sentence-level Transformer LM and a document-level LM based on a modified Transformer architecture yield further gains. As in previous years, we also extract n-gram probabilities from SMT lattices which can be seen as a source-conditioned n-gram LM. |
| Tasks | Language Modelling |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5340/ |
| https://www.aclweb.org/anthology/W19-5340 | |
| PWC | https://paperswithcode.com/paper/cuedwmt19ewclms-1 |
| Repo | |
| Framework | |
Baidu Neural Machine Translation Systems for WMT19
| Title | Baidu Neural Machine Translation Systems for WMT19 |
| Authors | Meng Sun, Bojian Jiang, Hao Xiong, Zhongjun He, Hua Wu, Haifeng Wang |
| Abstract | In this paper we introduce the systems Baidu submitted for the WMT19 shared task on Chinese{\textless}-{\textgreater}English news translation. Our systems are based on the Transformer architecture with some effective improvements. Data selection, back translation, data augmentation, knowledge distillation, domain adaptation, model ensemble and re-ranking are employed and proven effective in our experiments. Our Chinese-{\textgreater}English system achieved the highest case-sensitive BLEU score among all constrained submissions, and our English-{\textgreater}Chinese system ranked the second in all submissions. |
| Tasks | Data Augmentation, Domain Adaptation, Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5341/ |
| https://www.aclweb.org/anthology/W19-5341 | |
| PWC | https://paperswithcode.com/paper/baidu-neural-machine-translation-systems-for |
| Repo | |
| Framework | |
Language-Agnostic Model for Aspect-Based Sentiment Analysis
| Title | Language-Agnostic Model for Aspect-Based Sentiment Analysis |
| Authors | Md Shad Akhtar, Abhishek Kumar, Asif Ekbal, Chris Biemann, Pushpak Bhattacharyya |
| Abstract | In this paper, we propose a language-agnostic deep neural network architecture for aspect-based sentiment analysis. The proposed approach is based on Bidirectional Long Short-Term Memory (Bi-LSTM) network, which is further assisted with extra hand-crafted features. We define three different architectures for the successful combination of word embeddings and hand-crafted features. We evaluate the proposed approach for six languages (i.e. English, Spanish, French, Dutch, German and Hindi) and two problems (i.e. aspect term extraction and aspect sentiment classification). Experiments show that the proposed model attains state-of-the-art performance in most of the settings. |
| Tasks | Aspect-Based Sentiment Analysis, Sentiment Analysis, Word Embeddings |
| Published | 2019-05-01 |
| URL | https://www.aclweb.org/anthology/W19-0413/ |
| https://www.aclweb.org/anthology/W19-0413 | |
| PWC | https://paperswithcode.com/paper/language-agnostic-model-for-aspect-based |
| Repo | |
| Framework | |
BeamSeg: A Joint Model for Multi-Document Segmentation and Topic Identification
| Title | BeamSeg: A Joint Model for Multi-Document Segmentation and Topic Identification |
| Authors | Pedro Mota, Maxine Eskenazi, Lu{'\i}sa Coheur |
| Abstract | We propose BeamSeg, a joint model for segmentation and topic identification of documents from the same domain. The model assumes that lexical cohesion can be observed across documents, meaning that segments describing the same topic use a similar lexical distribution over the vocabulary. The model implements lexical cohesion in an unsupervised Bayesian setting by drawing from the same language model segments with the same topic. Contrary to previous approaches, we assume that language models are not independent, since the vocabulary changes in consecutive segments are expected to be smooth and not abrupt. We achieve this by using a dynamic Dirichlet prior that takes into account data contributions from other topics. BeamSeg also models segment length properties of documents based on modality (textbooks, slides, \textit{etc.}). The evaluation is carried out in three datasets. In two of them, improvements of up to 4.8{%} and 7.3{%} are obtained in the segmentation and topic identifications tasks, indicating that both tasks should be jointly modeled. |
| Tasks | Language Modelling |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1054/ |
| https://www.aclweb.org/anthology/K19-1054 | |
| PWC | https://paperswithcode.com/paper/beamseg-a-joint-model-for-multi-document |
| Repo | |
| Framework | |
PerspectiveNet: A Scene-consistent Image Generator for New View Synthesis in Real Indoor Environments
| Title | PerspectiveNet: A Scene-consistent Image Generator for New View Synthesis in Real Indoor Environments |
| Authors | Ben Graham, David Novotny, Jeremy Reizenstein |
| Abstract | Given a set of a reference RGBD views of an indoor environment, and a new viewpoint, our goal is to predict the view from that location. Prior work on new-view generation has predominantly focused on significantly constrained scenarios, typically involving artificially rendered views of isolated CAD models. Here we tackle a much more challenging version of the problem. We devise an approach that exploits known geometric properties of the scene (per-frame camera extrinsics and depth) in order to warp reference views into the new ones. The defects in the generated views are handled by a novel RGBD inpainting network, PerspectiveNet, that is fine-tuned for a given scene in order to obtain images that are geometrically consistent with all the views in the scene camera system. Experiments conducted on the ScanNet and SceneNet datasets reveal performance superior to strong baselines. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8977-perspectivenet-a-scene-consistent-image-generator-for-new-view-synthesis-in-real-indoor-environments |
| http://papers.nips.cc/paper/8977-perspectivenet-a-scene-consistent-image-generator-for-new-view-synthesis-in-real-indoor-environments.pdf | |
| PWC | https://paperswithcode.com/paper/perspectivenet-a-scene-consistent-image |
| Repo | |
| Framework | |
FOCNet: A Fractional Optimal Control Network for Image Denoising
| Title | FOCNet: A Fractional Optimal Control Network for Image Denoising |
| Authors | Xixi Jia, Sanyang Liu, Xiangchu Feng, Lei Zhang |
| Abstract | Deep convolutional neural networks (DCNN) have been successfully used in many low-level vision problems such as image denoising. Recent studies on the mathematical foundation of DCNN has revealed that the forward propagation of DCNN corresponds to a dynamic system, which can be described by an ordinary differential equation (ODE) and solved by the optimal control method. However, most of these methods employ integer-order differential equation, which has local connectivity in time space and cannot describe the long-term memory of the system. Inspired by the fact that the fractional-order differential equation has long-term memory, in this paper we develop an advanced image denoising network, namely FOCNet, by solving a fractional optimal control (FOC) problem. Specifically, the network structure is designed based on the discretization of a fractional-order differential equation, which enjoys long-term memory in both forward and backward passes. Besides, multi-scale feature interactions are introduced into the FOCNet to strengthen the control of the dynamic system. Extensive experiments demonstrate the leading performance of the proposed FOCNet on image denoising. Code will be made available. |
| Tasks | Denoising, Image Denoising |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Jia_FOCNet_A_Fractional_Optimal_Control_Network_for_Image_Denoising_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Jia_FOCNet_A_Fractional_Optimal_Control_Network_for_Image_Denoising_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/focnet-a-fractional-optimal-control-network |
| Repo | |
| Framework | |
Integrating large-scale web data and curated corpus data in a search engine supporting German literacy education
| Title | Integrating large-scale web data and curated corpus data in a search engine supporting German literacy education |
| Authors | Sabrina Dittrich, Zarah Weiss, Hannes Schr{"o}ter, Detmar Meurers |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-6305/ |
| https://www.aclweb.org/anthology/W19-6305 | |
| PWC | https://paperswithcode.com/paper/integrating-large-scale-web-data-and-curated |
| Repo | |
| Framework | |
A Test Suite and Manual Evaluation of Document-Level NMT at WMT19
| Title | A Test Suite and Manual Evaluation of Document-Level NMT at WMT19 |
| Authors | Kate{\v{r}}ina Rysov{'a}, Magdal{'e}na Rysov{'a}, Tom{'a}{\v{s}} Musil, Lucie Pol{'a}kov{'a}, Ond{\v{r}}ej Bojar |
| Abstract | As the quality of machine translation rises and neural machine translation (NMT) is moving from sentence to document level translations, it is becoming increasingly difficult to evaluate the output of translation systems. We provide a test suite for WMT19 aimed at assessing discourse phenomena of MT systems participating in the News Translation Task. We have manually checked the outputs and identified types of translation errors that are relevant to document-level translation. |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5352/ |
| https://www.aclweb.org/anthology/W19-5352 | |
| PWC | https://paperswithcode.com/paper/a-test-suite-and-manual-evaluation-of-1 |
| Repo | |
| Framework | |
En-Ar Bilingual Word Embeddings without Word Alignment: Factors Effects
| Title | En-Ar Bilingual Word Embeddings without Word Alignment: Factors Effects |
| Authors | Taghreed Alqaisi, Simon O{'}Keefe |
| Abstract | This paper introduces the first attempt to investigate morphological segmentation on En-Ar bilingual word embeddings using bilingual word embeddings model without word alignment (BilBOWA). We investigate the effect of sentence length and embedding size on the learning process. Our experiment shows that using the D3 segmentation scheme improves the accuracy of learning bilingual word embeddings up to 10 percentage points compared to the ATB and D0 schemes in all different training settings. |
| Tasks | Word Alignment, Word Embeddings |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4611/ |
| https://www.aclweb.org/anthology/W19-4611 | |
| PWC | https://paperswithcode.com/paper/en-ar-bilingual-word-embeddings-without-word |
| Repo | |
| Framework | |
ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models
| Title | ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models |
| Authors | Andrei Barbu, David Mayo, Julian Alverio, William Luo, Christopher Wang, Dan Gutfreund, Josh Tenenbaum, Boris Katz |
| Abstract | We collect a large real-world test set, ObjectNet, for object recognition with controls where object backgrounds, rotations, and imaging viewpoints are random. Most scientific experiments have controls, confounds which are removed from the data, to ensure that subjects cannot perform a task by exploiting trivial correlations in the data. Historically, large machine learning and computer vision datasets have lacked such controls. This has resulted in models that must be fine-tuned for new datasets and perform better on datasets than in real-world applications. When tested on ObjectNet, object detectors show a 40-45% drop in performance, with respect to their performance on other benchmarks, due to the controls for biases. Controls make ObjectNet robust to fine-tuning showing only small performance increases. We develop a highly automated platform that enables gathering datasets with controls by crowdsourcing image capturing and annotation. ObjectNet is the same size as the ImageNet test set (50,000 images), and by design does not come paired with a training set in order to encourage generalization. The dataset is both easier than ImageNet (objects are largely centered and unoccluded) and harder (due to the controls). Although we focus on object recognition here, data with controls can be gathered at scale using automated tools throughout machine learning to generate datasets that exercise models in new ways thus providing valuable feedback to researchers. This work opens up new avenues for research in generalizable, robust, and more human-like computer vision and in creating datasets where results are predictive of real-world performance. |
| Tasks | Object Recognition |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9142-objectnet-a-large-scale-bias-controlled-dataset-for-pushing-the-limits-of-object-recognition-models |
| http://papers.nips.cc/paper/9142-objectnet-a-large-scale-bias-controlled-dataset-for-pushing-the-limits-of-object-recognition-models.pdf | |
| PWC | https://paperswithcode.com/paper/objectnet-a-large-scale-bias-controlled |
| Repo | |
| Framework | |
ParaCrawl: Web-scale parallel corpora for the languages of the EU
| Title | ParaCrawl: Web-scale parallel corpora for the languages of the EU |
| Authors | Miquel Espl{`a}, Mikel Forcada, Gema Ram{'\i}rez-S{'a}nchez, Hieu Hoang |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6721/ |
| https://www.aclweb.org/anthology/W19-6721 | |
| PWC | https://paperswithcode.com/paper/paracrawl-web-scale-parallel-corpora-for-the |
| Repo | |
| Framework | |
Mutual Learning of Complementary Networks via Residual Correction for Improving Semi-Supervised Classification
| Title | Mutual Learning of Complementary Networks via Residual Correction for Improving Semi-Supervised Classification |
| Authors | Si Wu, Jichang Li, Cheng Liu, Zhiwen Yu, Hau-San Wong |
| Abstract | Deep mutual learning jointly trains multiple essential networks having similar properties to improve semi-supervised classification. However, the commonly used consistency regularization between the outputs of the networks may not fully leverage the difference between them. In this paper, we explore how to capture the complementary information to enhance mutual learning. For this purpose, we propose a complementary correction network (CCN), built on top of the essential networks, to learn the mapping from the output of one essential network to the ground truth label, conditioned on the features learnt by another. To make the second essential network increasingly complementary to the first one, this network is supervised by the corrected predictions. As a result, minimizing the prediction divergence between the two complementary networks can lead to significant performance gains in semi-supervised learning. Our experimental results demonstrate that the proposed approach clearly improves mutual learning between essential networks, and achieves state-of-the-art results on multiple semi-supervised classification benchmarks. In particular, the test error rates are reduced from previous 21.23% and 14.65% to 12.05% and 10.37% on CIFAR-10 with 1000 and 2000 labels, respectively. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Wu_Mutual_Learning_of_Complementary_Networks_via_Residual_Correction_for_Improving_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Wu_Mutual_Learning_of_Complementary_Networks_via_Residual_Correction_for_Improving_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/mutual-learning-of-complementary-networks-via |
| Repo | |
| Framework | |
