Paper Group NAWR 6
An Open Corpus for Named Entity Recognition in Historic Newspapers. A Reading Comprehension Corpus for Machine Translation Evaluation. Normalising Medical Concepts in Social Media Texts by Learning Semantic Representation. Kyoto-NMT: a Neural Machine Translation implementation in Chainer. Learning a Lexicon and Translation Model from Phoneme Lattic …
An Open Corpus for Named Entity Recognition in Historic Newspapers
| Title | An Open Corpus for Named Entity Recognition in Historic Newspapers |
| Authors | Clemens Neudecker |
| Abstract | The availability of openly available textual datasets ({}corpora{''}) with highly accurate manual annotations ({}gold standard{''}) of named entities (e.g. persons, locations, organizations, etc.) is crucial in the training and evaluation of named entity recognition systems. Currently there are only few such datasets available on the web, and even less for texts containing historical spelling variation. The production and subsequent release into the public domain of four such datasets with 100 pages each for the languages Dutch, French, German (including Austrian) as part of the Europeana Newspapers project is expected to contribute to the further development and improvement of named entity recognition systems with a focus on historical content. This paper describes how these datasets were produced, what challenges were encountered in their creation and informs about their final quality and availability. |
| Tasks | Named Entity Recognition |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1689/ |
| https://www.aclweb.org/anthology/L16-1689 | |
| PWC | https://paperswithcode.com/paper/an-open-corpus-for-named-entity-recognition |
| Repo | https://github.com/EuropeanaNewspapers/ner-corpora |
| Framework | none |
A Reading Comprehension Corpus for Machine Translation Evaluation
| Title | A Reading Comprehension Corpus for Machine Translation Evaluation |
| Authors | Carolina Scarton, Lucia Specia |
| Abstract | Effectively assessing Natural Language Processing output tasks is a challenge for research in the area. In the case of Machine Translation (MT), automatic metrics are usually preferred over human evaluation, given time and budget constraints.However, traditional automatic metrics (such as BLEU) are not reliable for absolute quality assessment of documents, often producing similar scores for documents translated by the same MT system.For scenarios where absolute labels are necessary for building models, such as document-level Quality Estimation, these metrics can not be fully trusted. In this paper, we introduce a corpus of reading comprehension tests based on machine translated documents, where we evaluate documents based on answers to questions by fluent speakers of the target language. We describe the process of creating such a resource, the experiment design and agreement between the test takers. Finally, we discuss ways to convert the reading comprehension test into document-level quality scores. |
| Tasks | Machine Translation, Reading Comprehension |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1579/ |
| https://www.aclweb.org/anthology/L16-1579 | |
| PWC | https://paperswithcode.com/paper/a-reading-comprehension-corpus-for-machine |
| Repo | https://github.com/carolscarton/CREG-MT-eval |
| Framework | none |
Normalising Medical Concepts in Social Media Texts by Learning Semantic Representation
| Title | Normalising Medical Concepts in Social Media Texts by Learning Semantic Representation |
| Authors | Nut Limsopatham, Nigel Collier |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1096/ |
| https://www.aclweb.org/anthology/P16-1096 | |
| PWC | https://paperswithcode.com/paper/normalising-medical-concepts-in-social-media |
| Repo | https://github.com/nutli/concept_normalisation |
| Framework | tf |
Kyoto-NMT: a Neural Machine Translation implementation in Chainer
| Title | Kyoto-NMT: a Neural Machine Translation implementation in Chainer |
| Authors | Fabien Cromi{`e}res |
| Abstract | We present Kyoto-NMT, an open-source implementation of the Neural Machine Translation paradigm. This implementation is done in Python and Chainer, an easy-to-use Deep Learning Framework. |
| Tasks | Language Modelling, Machine Translation |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-2064/ |
| https://www.aclweb.org/anthology/C16-2064 | |
| PWC | https://paperswithcode.com/paper/kyoto-nmt-a-neural-machine-translation |
| Repo | https://github.com/fabiencro/knmt |
| Framework | none |
Learning a Lexicon and Translation Model from Phoneme Lattices
| Title | Learning a Lexicon and Translation Model from Phoneme Lattices |
| Authors | Oliver Adams, Graham Neubig, Trevor Cohn, Steven Bird, Quoc Truong Do, Satoshi Nakamura |
| Abstract | |
| Tasks | |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1263/ |
| https://www.aclweb.org/anthology/D16-1263 | |
| PWC | https://paperswithcode.com/paper/learning-a-lexicon-and-translation-model-from |
| Repo | https://github.com/oadams/latticetm |
| Framework | none |
Don’t Let Notes Be Misunderstood: A Negation Detection Method for Assessing Risk of Suicide in Mental Health Records
| Title | Don’t Let Notes Be Misunderstood: A Negation Detection Method for Assessing Risk of Suicide in Mental Health Records |
| Authors | George Gkotsis, Sumithra Velupillai, Anika Oellrich, Harry Dean, Maria Liakata, Rina Dutta |
| Abstract | |
| Tasks | Negation Detection |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0310/ |
| https://www.aclweb.org/anthology/W16-0310 | |
| PWC | https://paperswithcode.com/paper/dont-let-notes-be-misunderstood-a-negation |
| Repo | https://github.com/gkotsis/negation-detection |
| Framework | none |
Mnemonic Descent Method: A recurrent process applied for end-to-end face alignment
| Title | Mnemonic Descent Method: A recurrent process applied for end-to-end face alignment |
| Authors | G. Trigeorgis, P. Snape, M. A. Nicolaou, E. Antonakos, S. Zafeiriou |
| Abstract | Cascaded regression has recently become the method of choice for solving non-linear least squares problems such as deformable image alignment. Given a sizeable training set, cascaded regression learns a set of generic rules that are sequentially applied to minimise the least squares problem. Despite the success of cascaded regression for problems such as face alignment and head pose estimation, there are several shortcomings arising in the strategies proposed thus far. Specifically,(a) the regressors are learnt independently,(b) the descent directions may cancel one another out and (c) handcrafted features (eg, HoGs, SIFT etc.) are mainly used to drive the cascade, which may be sub-optimal for the task at hand. In this paper, we propose a combined and jointly trained convolutional recurrent neural network architecture that allows the training of an end-to-end to system that attempts to alleviate the aforementioned drawbacks. The recurrent module facilitates the joint optimisation of the regressors by assuming the cascades form a nonlinear dynamical system, in effect fully utilising the information between all cascade levels by introducing a memory unit that shares information across all levels. The convolutional module allows the network to extract features that are specialised for the task at hand and are experimentally shown to outperform hand-crafted features. We show that the application of the proposed architecture for the problem of face alignment results in a strong improvement over the current state-of-the-art. |
| Tasks | Face Alignment, Head Pose Estimation, Pose Estimation |
| Published | 2016-06-01 |
| URL | https://www.ibug.doc.ic.ac.uk/media/uploads/documents/trigeorgis2016mnemonic.pdf |
| https://www.ibug.doc.ic.ac.uk/media/uploads/documents/trigeorgis2016mnemonic.pdf | |
| PWC | https://paperswithcode.com/paper/mnemonic-descent-method-a-recurrent-process-1 |
| Repo | https://github.com/trigeorgis/mdm |
| Framework | tf |
Structure-From-Motion Revisited
| Title | Structure-From-Motion Revisited |
| Authors | Johannes L. Schonberger, Jan-Michael Frahm |
| Abstract | Incremental Structure-from-Motion is a prevalent strategy for 3D reconstruction from unordered image collections. While incremental reconstruction systems have tremendously advanced in all regards, robustness, accuracy, completeness, and scalability remain the key problems towards building a truly general-purpose pipeline. We propose a new SfM technique that improves upon the state of the art to make a further step towards this ultimate goal. The full reconstruction pipeline is released to the public as an open-source implementation. |
| Tasks | 3D Reconstruction |
| Published | 2016-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2016/html/Schonberger_Structure-From-Motion_Revisited_CVPR_2016_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2016/papers/Schonberger_Structure-From-Motion_Revisited_CVPR_2016_paper.pdf | |
| PWC | https://paperswithcode.com/paper/structure-from-motion-revisited |
| Repo | https://github.com/colmap/colmap |
| Framework | none |
Accumulated Stability Voting: A Robust Descriptor From Descriptors of Multiple Scales
| Title | Accumulated Stability Voting: A Robust Descriptor From Descriptors of Multiple Scales |
| Authors | Tsun-Yi Yang, Yen-Yu Lin, Yung-Yu Chuang |
| Abstract | This paper proposes a novel local descriptor through accumulated stability voting (ASV). The stability of feature dimensions is measured by their differences across scales. To be more robust to noise, the stability is further quantized by thresholding. The principle of maximum entropy is utilized for determining the best thresholds for maximizing discriminant power of the resultant descriptor. Accumulating stability renders a real-valued descriptor and it can be converted into a binary descriptor by an additional thresholding process. The real-valued descriptor attains high matching accuracy while the binary descriptor makes a good compromise between storage and accuracy. Our descriptors are simple yet effective, and easy to implement. In addition, our descriptors require no training. Experiments on popular benchmarks demonstrate the effectiveness of our descriptors and their superiority to the state-of-the-art descriptors. |
| Tasks | |
| Published | 2016-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2016/html/Yang_Accumulated_Stability_Voting_CVPR_2016_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2016/papers/Yang_Accumulated_Stability_Voting_CVPR_2016_paper.pdf | |
| PWC | https://paperswithcode.com/paper/accumulated-stability-voting-a-robust |
| Repo | https://github.com/shamangary/ASV |
| Framework | none |
Robust Gram Embeddings
| Title | Robust Gram Embeddings |
| Authors | Taygun Keke{\c{c}}, David M. J. Tax |
| Abstract | |
| Tasks | Sarcasm Detection, Sentiment Analysis, Word Embeddings |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1113/ |
| https://www.aclweb.org/anthology/D16-1113 | |
| PWC | https://paperswithcode.com/paper/robust-gram-embeddings |
| Repo | https://github.com/taygunk/robust_gram_embeddings |
| Framework | none |
Joint Event Extraction via Recurrent Neural Networks
| Title | Joint Event Extraction via Recurrent Neural Networks |
| Authors | Thien Huu Nguyen, Kyunghyun Cho, Ralph Grishman |
| Abstract | |
| Tasks | Structured Prediction |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1034/ |
| https://www.aclweb.org/anthology/N16-1034 | |
| PWC | https://paperswithcode.com/paper/joint-event-extraction-via-recurrent-neural |
| Repo | https://github.com/anoperson/jointEE-NN |
| Framework | none |
Learning compact binary descriptors with unsupervised deep neural networks
| Title | Learning compact binary descriptors with unsupervised deep neural networks |
| Authors | Kevin Lin; Jiwen Lu; Chu-Song Chen; Jie Zhou |
| Abstract | In this paper, we propose a new unsupervised deep learning approach called DeepBit to learn compact binary descriptor for efficient visual object matching. Unlike most existing binary descriptors which were designed with random projections or linear hash functions, we develop a deep neural network to learn binary descriptors in an unsupervised manner. We enforce three criterions on binary codes which are learned at the top layer of our network: 1) minimal loss quantization, 2) evenly distributed codes and 3) uncorrelated bits. Then, we learn the parameters of the networks with a back-propagation technique. Experimental results on three different visual analysis tasks including image matching, image retrieval, and object recognition clearly demonstrate the effectiveness of the proposed approach. |
| Tasks | Image Retrieval, Object Recognition, Quantization |
| Published | 2016-06-01 |
| URL | https://ieeexplore.ieee.org/document/7780502/ |
| https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Lin_Learning_Compact_Binary_CVPR_2016_paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-compact-binary-descriptors-with-1 |
| Repo | https://github.com/kevinlin311tw/cvpr16-deepbit |
| Framework | none |
A Multilingual, Multi-style and Multi-granularity Dataset for Cross-language Textual Similarity Detection
| Title | A Multilingual, Multi-style and Multi-granularity Dataset for Cross-language Textual Similarity Detection |
| Authors | J{'e}r{'e}my Ferrero, Fr{'e}d{'e}ric Agn{`e}s, Laurent Besacier, Didier Schwab |
| Abstract | In this paper we describe our effort to create a dataset for the evaluation of cross-language textual similarity detection. We present preexisting corpora and their limits and we explain the various gathered resources to overcome these limits and build our enriched dataset. The proposed dataset is multilingual, includes cross-language alignment for different granularities (from chunk to document), is based on both parallel and comparable corpora and contains human and machine translated texts. Moreover, it includes texts written by multiple types of authors (from average to professionals). With the obtained dataset, we conduct a systematic and rigorous evaluation of several state-of-the-art cross-language textual similarity detection methods. The evaluation results are reviewed and discussed. Finally, dataset and scripts are made publicly available on GitHub: http://github.com/FerreroJeremy/Cross-Language-Dataset. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1657/ |
| https://www.aclweb.org/anthology/L16-1657 | |
| PWC | https://paperswithcode.com/paper/a-multilingual-multi-style-and-multi |
| Repo | https://github.com/FerreroJeremy/Cross-Language-Dataset |
| Framework | none |
Dynamic Image Networks for Action Recognition
| Title | Dynamic Image Networks for Action Recognition |
| Authors | Hakan Bilen, Basura Fernando, Efstratios Gavves, Andrea Vedaldi, Stephen Gould |
| Abstract | We introduce the concept of dynamic image, a novel compact representation of videos useful for video analysis especially when convolutional neural networks (CNNs) are used. The dynamic image is based on the rank pooling concept and is obtained through the parameters of a ranking machine that encodes the temporal evolution of the frames of the video. Dynamic images are obtained by directly applying rank pooling on the raw image pixels of a video producing a single RGB image per video. This idea is simple but powerful as it enables the use of existing CNN models directly on video data with fine-tuning. We present an efficient and effective approximate rank pooling operator, speeding it up orders of magnitude compared to rank pooling. Our new approximate rank pooling CNN layer allows us to generalize dynamic images to dynamic feature maps and we demonstrate the power of our new representations on standard benchmarks in action recognition achieving state-of-the-art performance. |
| Tasks | Temporal Action Localization |
| Published | 2016-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2016/html/Bilen_Dynamic_Image_Networks_CVPR_2016_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2016/papers/Bilen_Dynamic_Image_Networks_CVPR_2016_paper.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-image-networks-for-action-recognition |
| Repo | https://github.com/hbilen/dynamic-image-nets |
| Framework | none |
Structural Deep Network Embedding
| Title | Structural Deep Network Embedding |
| Authors | Daixin Wang1, Peng Cui1, Wenwu Zhu1 |
| Abstract | Networkembeddingisanimportantmethodtolearnlow-dimensional representations of vertexes in networks, aiming to capture and preserve the network structure. Almost all the existing network embeddingmethodsadoptshallowmodels. However,sincetheunderlyingnetworkstructureiscomplex, shallowmodelscannotcapture the highly non-linear network structure, resulting in sub-optimal network representations. Therefore, how to find a method that is able to effectively capture the highly non-linear network structure and preserve the global and local structure is an open yet important problem. To solve this problem, in this paper we propose a StructuralDeepNetworkEmbeddingmethod,namelySDNE.More specifically, we first propose a semi-supervised deep model, which has multiple layers of non-linear functions, thereby being able to capture the highly non-linear network structure. Then we propose to exploit the first-order and second-order proximity jointly to preserve the network structure. The second-order proximity is used bytheunsupervisedcomponenttocapturetheglobalnetworkstructure. Whilethefirst-orderproximityisusedasthesupervisedinformation in the supervised component to preserve the local network structure. By jointly optimizing them in the semi-supervised deep model, our method can preserve both the local and global network structureandisrobusttosparsenetworks. Empirically,weconduct the experiments on five real-world networks, including a language network, a citation network and three social networks. The results show that compared to the baselines, our method can reconstruct the original network significantly better and achieves substantial gains in three applications, i.e. multi-label classification, link prediction and visualization. |
| Tasks | Graph Classification, Link Prediction, Network Embedding |
| Published | 2016-06-01 |
| URL | https://www.kdd.org/kdd2016/papers/files/rfp0191-wangAemb.pdf |
| https://www.kdd.org/kdd2016/papers/files/rfp0191-wangAemb.pdf | |
| PWC | https://paperswithcode.com/paper/structural-deep-network-embedding |
| Repo | https://github.com/shenweichen/GraphEmbedding |
| Framework | tf |
