Paper Group NAWR 20
Encoder-Decoder Methods for Text Normalization. Greedy Hash: Towards Fast Optimization for Accurate Hash Coding in CNN. Data-driven computing in elasticity via kernel regression. Cross-lingual Knowledge Graph Alignment via Graph Convolutional Networks. Multi-value Rule Sets for Interpretable Classification with Feature-Efficient Representations. St …
Encoder-Decoder Methods for Text Normalization
| Title | Encoder-Decoder Methods for Text Normalization |
| Authors | Massimo Lusetti, Tatyana Ruzsics, Anne G{"o}hring, Tanja Samard{\v{z}}i{'c}, Elisabeth Stark |
| Abstract | Text normalization is the task of mapping non-canonical language, typical of speech transcription and computer-mediated communication, to a standardized writing. It is an up-stream task necessary to enable the subsequent direct employment of standard natural language processing tools and indispensable for languages such as Swiss German, with strong regional variation and no written standard. Text normalization has been addressed with a variety of methods, most successfully with character-level statistical machine translation (CSMT). In the meantime, machine translation has changed and the new methods, known as neural encoder-decoder (ED) models, resulted in remarkable improvements. Text normalization, however, has not yet followed. A number of neural methods have been tried, but CSMT remains the state-of-the-art. In this work, we normalize Swiss German WhatsApp messages using the ED framework. We exploit the flexibility of this framework, which allows us to learn from the same training data in different ways. In particular, we modify the decoding stage of a plain ED model to include target-side language models operating at different levels of granularity: characters and words. Our systematic comparison shows that our approach results in an improvement over the CSMT state-of-the-art. |
| Tasks | Machine Translation |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-3902/ |
| https://www.aclweb.org/anthology/W18-3902 | |
| PWC | https://paperswithcode.com/paper/encoder-decoder-methods-for-text |
| Repo | https://github.com/tatyana-ruzsics/uzh-corpuslab-normalization |
| Framework | none |
Greedy Hash: Towards Fast Optimization for Accurate Hash Coding in CNN
| Title | Greedy Hash: Towards Fast Optimization for Accurate Hash Coding in CNN |
| Authors | Shupeng Su, Chao Zhang, Kai Han, Yonghong Tian |
| Abstract | To convert the input into binary code, hashing algorithm has been widely used for approximate nearest neighbor search on large-scale image sets due to its computation and storage efficiency. Deep hashing further improves the retrieval quality by combining the hash coding with deep neural network. However, a major difficulty in deep hashing lies in the discrete constraints imposed on the network output, which generally makes the optimization NP hard. In this work, we adopt the greedy principle to tackle this NP hard problem by iteratively updating the network toward the probable optimal discrete solution in each iteration. A hash coding layer is designed to implement our approach which strictly uses the sign function in forward propagation to maintain the discrete constraints, while in back propagation the gradients are transmitted intactly to the front layer to avoid the vanishing gradients. In addition to the theoretical derivation, we provide a new perspective to visualize and understand the effectiveness and efficiency of our algorithm. Experiments on benchmark datasets show that our scheme outperforms state-of-the-art hashing methods in both supervised and unsupervised tasks. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7360-greedy-hash-towards-fast-optimization-for-accurate-hash-coding-in-cnn |
| http://papers.nips.cc/paper/7360-greedy-hash-towards-fast-optimization-for-accurate-hash-coding-in-cnn.pdf | |
| PWC | https://paperswithcode.com/paper/greedy-hash-towards-fast-optimization-for |
| Repo | https://github.com/ssppp/GreedyHash |
| Framework | pytorch |
Data-driven computing in elasticity via kernel regression
| Title | Data-driven computing in elasticity via kernel regression |
| Authors | Yoshihiro Kanno |
| Abstract | This paper presents a simple nonparametric regression approach to data-driven computing in elasticity. We apply the kernel regression to the material data set, and formulate a system of nonlinear equations solved to obtain a static equilibrium state of an elastic structure. Preliminary numerical experiments illustrate that, compared with existing methods, the proposed method finds a reasonable solution even if data points distribute coarsely in a given material data set. |
| Tasks | Stress-Strain Relation |
| Published | 2018-12-12 |
| URL | https://www.sciencedirect.com/science/article/pii/S2095034918302071 |
| https://www.sciencedirect.com/science/article/pii/S2095034918302071 | |
| PWC | https://paperswithcode.com/paper/data-driven-computing-in-elasticity-via-1 |
| Repo | https://github.com/ykanno22/data_driven_kernel_regression |
| Framework | none |
Cross-lingual Knowledge Graph Alignment via Graph Convolutional Networks
| Title | Cross-lingual Knowledge Graph Alignment via Graph Convolutional Networks |
| Authors | Zhichun Wang, Qingsong Lv, Xiaohan Lan, Yu Zhang |
| Abstract | Multilingual knowledge graphs (KGs) such as DBpedia and YAGO contain structured knowledge of entities in several distinct languages, and they are useful resources for cross-lingual AI and NLP applications. Cross-lingual KG alignment is the task of matching entities with their counterparts in different languages, which is an important way to enrich the cross-lingual links in multilingual KGs. In this paper, we propose a novel approach for cross-lingual KG alignment via graph convolutional networks (GCNs). Given a set of pre-aligned entities, our approach trains GCNs to embed entities of each language into a unified vector space. Entity alignments are discovered based on the distances between entities in the embedding space. Embeddings can be learned from both the structural and attribute information of entities, and the results of structure embedding and attribute embedding are combined to get accurate alignments. In the experiments on aligning real multilingual KGs, our approach gets the best performance compared with other embedding-based KG alignment approaches. |
| Tasks | Feature Engineering, Knowledge Graphs, Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1032/ |
| https://www.aclweb.org/anthology/D18-1032 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-knowledge-graph-alignment-via |
| Repo | https://github.com/1049451037/GCN-Align |
| Framework | tf |
Multi-value Rule Sets for Interpretable Classification with Feature-Efficient Representations
| Title | Multi-value Rule Sets for Interpretable Classification with Feature-Efficient Representations |
| Authors | Tong Wang |
| Abstract | We present the Multi-value Rule Set (MRS) for interpretable classification with feature efficient presentations. Compared to rule sets built from single-value rules, MRS adopts a more generalized form of association rules that allows multiple values in a condition. Rules of this form are more concise than classical single-value rules in capturing and describing patterns in data. Our formulation also pursues a higher efficiency of feature utilization, which reduces possible cost in data collection and storage. We propose a Bayesian framework for formulating an MRS model and develop an efficient inference method for learning a maximum a posteriori, incorporating theoretically grounded bounds to iteratively reduce the search space and improve the search efficiency. Experiments on synthetic and real-world data demonstrate that MRS models have significantly smaller complexity and fewer features than baseline models while being competitive in predictive accuracy. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8281-multi-value-rule-sets-for-interpretable-classification-with-feature-efficient-representations |
| http://papers.nips.cc/paper/8281-multi-value-rule-sets-for-interpretable-classification-with-feature-efficient-representations.pdf | |
| PWC | https://paperswithcode.com/paper/multi-value-rule-sets-for-interpretable |
| Repo | https://github.com/wangtongada/MRS |
| Framework | none |
Stimulus domain transfer in recurrent models for large scale cortical population prediction on video
| Title | Stimulus domain transfer in recurrent models for large scale cortical population prediction on video |
| Authors | Fabian Sinz, Alexander S. Ecker, Paul Fahey, Edgar Walker, Erick Cobos, Emmanouil Froudarakis, Dimitri Yatsenko, Zachary Pitkow, Jacob Reimer, Andreas Tolias |
| Abstract | To better understand the representations in visual cortex, we need to generate better predictions of neural activity in awake animals presented with their ecological input: natural video. Despite recent advances in models for static images, models for predicting responses to natural video are scarce and standard linear-nonlinear models perform poorly. We developed a new deep recurrent network architecture that predicts inferred spiking activity of thousands of mouse V1 neurons simultaneously recorded with two-photon microscopy, while accounting for confounding factors such as the animal’s gaze position and brain state changes related to running state and pupil dilation. Powerful system identification models provide an opportunity to gain insight into cortical functions through in silico experiments that can subsequently be tested in the brain. However, in many cases this approach requires that the model is able to generalize to stimulus statistics that it was not trained on, such as band-limited noise and other parameterized stimuli. We investigated these domain transfer properties in our model and find that our model trained on natural images is able to correctly predict the orientation tuning of neurons in responses to artificial noise stimuli. Finally, we show that we can fully generalize from movies to noise and maintain high predictive performance on both stimulus domains by fine-tuning only the final layer’s weights on a network otherwise trained on natural movies. The converse, however, is not true. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7950-stimulus-domain-transfer-in-recurrent-models-for-large-scale-cortical-population-prediction-on-video |
| http://papers.nips.cc/paper/7950-stimulus-domain-transfer-in-recurrent-models-for-large-scale-cortical-population-prediction-on-video.pdf | |
| PWC | https://paperswithcode.com/paper/stimulus-domain-transfer-in-recurrent-models |
| Repo | https://github.com/sinzlab/Sinz2018_NIPS |
| Framework | pytorch |
Urdu Word Embeddings
| Title | Urdu Word Embeddings |
| Authors | Samar Haider |
| Abstract | |
| Tasks | Semantic Textual Similarity, Word Embeddings |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1155/ |
| https://www.aclweb.org/anthology/L18-1155 | |
| PWC | https://paperswithcode.com/paper/urdu-word-embeddings |
| Repo | https://github.com/samarh/urduvec |
| Framework | none |
ETPC - A Paraphrase Identification Corpus Annotated with Extended Paraphrase Typology and Negation
| Title | ETPC - A Paraphrase Identification Corpus Annotated with Extended Paraphrase Typology and Negation |
| Authors | Venelin Kovatchev, M. Ant{`o}nia Mart{'\i}, Maria Salam{'o} |
| Abstract | |
| Tasks | Natural Language Inference, Paraphrase Identification, Question Answering, Semantic Textual Similarity, Text Simplification, Text Summarization |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1221/ |
| https://www.aclweb.org/anthology/L18-1221 | |
| PWC | https://paperswithcode.com/paper/etpc-a-paraphrase-identification-corpus |
| Repo | https://github.com/venelink/ETPC |
| Framework | none |
Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks
| Title | Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks |
| Authors | Daniel Povey, Gaofeng Cheng, Yiming Wang, Ke Li, Hainan Xu, Mahsa Yarmohammadi, Sanjeev Khudanpur |
| Abstract | Time Delay Neural Networks (TDNNs), also known as onedimensional Convolutional Neural Networks (1-d CNNs), are an efficient and well-performing neural network architecture for speech recognition. We introduce a factored form of TDNNs (TDNN-F) which is structurally the same as a TDNN whose layers have been compressed via SVD, but is trained from a random start with one of the two factors of each matrix constrained to be semi-orthogonal. This gives substantial improvements over TDNNs and performs about as well as TDNN-LSTM hybrids. |
| Tasks | Speech Recognition |
| Published | 2018-09-02 |
| URL | https://www.isca-speech.org/archive/Interspeech_2018/abstracts/1417.html |
| https://www.danielpovey.com/files/2018_interspeech_tdnnf.pdf | |
| PWC | https://paperswithcode.com/paper/semi-orthogonal-low-rank-matrix-factorization |
| Repo | https://github.com/cvqluu/Factorized-TDNN |
| Framework | pytorch |
Bidirectional Feature Pyramid Network with Recurrent Attention Residual Modules for Shadow Detection
| Title | Bidirectional Feature Pyramid Network with Recurrent Attention Residual Modules for Shadow Detection |
| Authors | Lei Zhu, Zijun Deng, Xiaowei Hu, Chi-Wing Fu, Xuemiao Xu, Jing Qin, Pheng-Ann Heng |
| Abstract | This paper presents a network to detect shadows by exploring and combining global context in deep layers and local context in shallow layers of a deep convolutional neural network (CNN). There are two technical contributions in our network design. First, we formulate the recurrent attention residual (RAR) module to combine the contexts in two adjacent CNN layers and learn an attention map to select a residual and then refine the context features. Second, we develop a bidirectional feature pyramid network (BFPN) to aggregate shadow contexts spanned across different CNN layers by deploying two series of RAR modules in the network to iteratively combine and refine context features: one series to refine context features from deep to shallow layers, and another series from shallow to deep layers. Hence, we can better suppress false detections and enhance shadow details at the same time. We evaluate our network on two common shadow detection benchmark datasets: SBU and UCF. Experimental results show that our network outperforms the best existing method with 34.88% reduction on SBU and 34.57% reduction on UCF for the balance error rate. |
| Tasks | Shadow Detection |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Lei_Zhu_Bi-directional_Feature_Pyramid_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Lei_Zhu_Bi-directional_Feature_Pyramid_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/bidirectional-feature-pyramid-network-with |
| Repo | https://github.com/zijundeng/BDRAR |
| Framework | pytorch |
RNN Simulations of Grammaticality Judgments on Long-distance Dependencies
| Title | RNN Simulations of Grammaticality Judgments on Long-distance Dependencies |
| Authors | Shammur Absar Chowdhury, Roberto Zamparelli |
| Abstract | The paper explores the ability of LSTM networks trained on a language modeling task to detect linguistic structures which are ungrammatical due to extraction violations (extra arguments and subject-relative clause island violations), and considers its implications for the debate on language innatism. The results show that the current RNN model can correctly classify (un)grammatical sentences, in certain conditions, but it is sensitive to linguistic processing factors and probably ultimately unable to induce a more abstract notion of grammaticality, at least in the domain we tested. |
| Tasks | Language Modelling |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1012/ |
| https://www.aclweb.org/anthology/C18-1012 | |
| PWC | https://paperswithcode.com/paper/rnn-simulations-of-grammaticality-judgments |
| Repo | https://github.com/LiCo-TREiL/Computational-Ungrammaticality |
| Framework | none |
Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism
| Title | Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism |
| Authors | Xiangrong Zeng, Daojian Zeng, Shizhu He, Kang Liu, Jun Zhao |
| Abstract | The relational facts in sentences are often complicated. Different relational triplets may have overlaps in a sentence. We divided the sentences into three types according to triplet overlap degree, including Normal, EntityPairOverlap and SingleEntiyOverlap. Existing methods mainly focus on Normal class and fail to extract relational triplets precisely. In this paper, we propose an end-to-end model based on sequence-to-sequence learning with copy mechanism, which can jointly extract relational facts from sentences of any of these classes. We adopt two different strategies in decoding process: employing only one united decoder or applying multiple separated decoders. We test our models in two public datasets and our model outperform the baseline method significantly. |
| Tasks | Feature Engineering, Relation Extraction |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1047/ |
| https://www.aclweb.org/anthology/P18-1047 | |
| PWC | https://paperswithcode.com/paper/extracting-relational-facts-by-an-end-to-end |
| Repo | https://github.com/xiangrongzeng/copy_re |
| Framework | none |
Experiments with Convolutional Neural Networks for Multi-Label Authorship Attribution
| Title | Experiments with Convolutional Neural Networks for Multi-Label Authorship Attribution |
| Authors | Dainis Boumber, Yifan Zhang, Arjun Mukherjee |
| Abstract | |
| Tasks | Domain Adaptation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1409/ |
| https://www.aclweb.org/anthology/L18-1409 | |
| PWC | https://paperswithcode.com/paper/experiments-with-convolutional-neural |
| Repo | https://github.com/dainis-boumber/AA_CNN |
| Framework | tf |
Deep Learning for Hand Gesture Recognition on Skeletal Data
| Title | Deep Learning for Hand Gesture Recognition on Skeletal Data |
| Authors | Guillaume Devineau, Wang Xi, Jie Yang, Fabien Moutarde |
| Abstract | In this paper, we introduce a new 3D hand gesture recognition approach based on a deep learning model. We introduce a new Convolutional Neural Network (CNN) where sequences of hand-skeletal joints’ positions are processed by parallel convolutions; we then investigate the performance of this model on hand gesture sequence classification tasks. Our model only uses hand-skeletal data and no depth image. Experimental results show that our approach achieves a state-of-the-art performance on a challenging dataset (DHG dataset from the SHREC 2017 3D Shape Retrieval Contest), when compared to other published approaches. Our model achieves a 91.28% classification accuracy for the 14 gesture classes case and an 84.35% classification accuracy for the 28 gesture classes case. |
| Tasks | 3D Shape Retrieval, Gesture Recognition, Hand Gesture Recognition, Hand-Gesture Recognition, Skeleton Based Action Recognition, Temporal Information Extraction |
| Published | 2018-05-15 |
| URL | https://hal-mines-paristech.archives-ouvertes.fr/hal-01737771/file/DeepLearning-HandSkeletalGestureRecognition_MINES-ParisTech_FG2018.pdf |
| https://hal-mines-paristech.archives-ouvertes.fr/hal-01737771/file/DeepLearning-HandSkeletalGestureRecognition_MINES-ParisTech_FG2018.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-hand-gesture-recognition-on |
| Repo | https://github.com/guillaumephd/deep_learning_hand_gesture_recognition |
| Framework | pytorch |
Construction of Large-scale English Verbal Multiword Expression Annotated Corpus
| Title | Construction of Large-scale English Verbal Multiword Expression Annotated Corpus |
| Authors | Akihiko Kato, Hiroyuki Shindo, Yuji Matsumoto |
| Abstract | |
| Tasks | Dependency Parsing, Semantic Parsing |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1396/ |
| https://www.aclweb.org/anthology/L18-1396 | |
| PWC | https://paperswithcode.com/paper/construction-of-large-scale-english-verbal |
| Repo | https://github.com/naist-cl-parsing/Verbal-MWE-annotations |
| Framework | none |
