Paper Group NANR 220
Chemical Compounds Knowledge Visualization with Natural Language Processing and Linked Data. OpenSeq2Seq: Extensible Toolkit for Distributed and Mixed Precision Training of Sequence-to-Sequence Models. Voice Builder: A Tool for Building Text-To-Speech Voices. Show Me a Story: Towards Coherent Neural Story Illustration. Towards Effective GANs for Da …
Chemical Compounds Knowledge Visualization with Natural Language Processing and Linked Data
| Title | Chemical Compounds Knowledge Visualization with Natural Language Processing and Linked Data |
| Authors | Kazunari Tanaka, Tomoya Iwakura, Yusuke Koyanagi, Noriko Ikeda, Hiroyuki Shindo, Yuji Matsumoto |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1356/ |
| https://www.aclweb.org/anthology/L18-1356 | |
| PWC | https://paperswithcode.com/paper/chemical-compounds-knowledge-visualization |
| Repo | |
| Framework | |
OpenSeq2Seq: Extensible Toolkit for Distributed and Mixed Precision Training of Sequence-to-Sequence Models
| Title | OpenSeq2Seq: Extensible Toolkit for Distributed and Mixed Precision Training of Sequence-to-Sequence Models |
| Authors | Oleksii Kuchaiev, Boris Ginsburg, Igor Gitman, Vitaly Lavrukhin, Carl Case, Paulius Micikevicius |
| Abstract | We present OpenSeq2Seq {–} an open-source toolkit for training sequence-to-sequence models. The main goal of our toolkit is to allow researchers to most effectively explore different sequence-to-sequence architectures. The efficiency is achieved by fully supporting distributed and mixed-precision training. OpenSeq2Seq provides building blocks for training encoder-decoder models for neural machine translation and automatic speech recognition. We plan to extend it with other modalities in the future. |
| Tasks | Machine Translation, Speech Recognition |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2507/ |
| https://www.aclweb.org/anthology/W18-2507 | |
| PWC | https://paperswithcode.com/paper/openseq2seq-extensible-toolkit-for |
| Repo | |
| Framework | |
Voice Builder: A Tool for Building Text-To-Speech Voices
| Title | Voice Builder: A Tool for Building Text-To-Speech Voices |
| Authors | Pasindu De Silva, Theeraphol Wattanavekin, Tang Hao, Knot Pipatsrisawat |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1354/ |
| https://www.aclweb.org/anthology/L18-1354 | |
| PWC | https://paperswithcode.com/paper/voice-builder-a-tool-for-building-text-to |
| Repo | |
| Framework | |
Show Me a Story: Towards Coherent Neural Story Illustration
| Title | Show Me a Story: Towards Coherent Neural Story Illustration |
| Authors | Hareesh Ravi, Lezi Wang, Carlos Muniz, Leonid Sigal, Dimitris Metaxas, Mubbasir Kapadia |
| Abstract | We propose an end-to-end network for the visual illustration of a sequence of sentences forming a story. At the core of our model is the ability to model the inter-related nature of the sentences within a story, as well as the ability to learn coherence to support reference resolution. The framework takes the form of an encoder-decoder architecture, where sentences are encoded using a hierarchical two-level sentence-story GRU, combined with an encoding of coherence, and sequentially decoded using predicted feature representation into a consistent illustrative image sequence. We optimize all parameters of our network in an end-to-end fashion with respect to order embedding loss, encoding entailment between images and sentences. Experiments on the VIST storytelling dataset cite{vist} highlight the importance of our algorithmic choices and efficacy of our overall model. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Ravi_Show_Me_a_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Ravi_Show_Me_a_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/show-me-a-story-towards-coherent-neural-story |
| Repo | |
| Framework | |
Towards Effective GANs for Data Distributions with Diverse Modes
| Title | Towards Effective GANs for Data Distributions with Diverse Modes |
| Authors | Sanchit Agrawal, Gurneet Singh, Mitesh Khapra |
| Abstract | Generative Adversarial Networks (GANs), when trained on large datasets with diverse modes, are known to produce conflated images which do not distinctly belong to any of the modes. We hypothesize that this problem occurs due to the interaction between two facts: (1) For datasets with large variety, it is likely that the modes lie on separate manifolds. (2) The generator (G) is formulated as a continuous function, and the input noise is derived from a connected set, due to which G’s output is a connected set. If G covers all modes, then there must be some portion of G’s output which connects them. This corresponds to undesirable, conflated images. We develop theoretical arguments to support these intuitions. We propose a novel method to break the second assumption via learnable discontinuities in the latent noise space. Equivalently, it can be viewed as training several generators, thus creating discontinuities in the G function. We also augment the GAN formulation with a classifier C that predicts which noise partition/generator produced the output images, encouraging diversity between each partition/generator. We experiment on MNIST, celebA, STL-10, and a difficult dataset with clearly distinct modes, and show that the noise partitions correspond to different modes of the data distribution, and produce images of superior quality. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=HyDMX0l0Z |
| https://openreview.net/pdf?id=HyDMX0l0Z | |
| PWC | https://paperswithcode.com/paper/towards-effective-gans-for-data-distributions |
| Repo | |
| Framework | |
Learning Deep Models: Critical Points and Local Openness
| Title | Learning Deep Models: Critical Points and Local Openness |
| Authors | Maher Nouiehed, Meisam Razaviyayn |
| Abstract | With the increasing interest in deeper understanding of the loss surface of many non-convex deep models, this paper presents a unifying framework to study the local/global optima equivalence of the optimization problems arising from training of such non-convex models. Using the “local openness” property of the underlying training models, we provide simple sufficient conditions under which any local optimum of the resulting optimization problem is globally optimal. We first completely characterize the local openness of matrix multiplication mapping in its range. Then we use our characterization to: 1) show that every local optimum of two layer linear networks is globally optimal. Unlike many existing results in the literature, our result requires no assumption on the target data matrix Y, and input data matrix X. 2) develop almost complete characterization of the local/global optima equivalence of multi-layer linear neural networks. We provide various counterexamples to show the necessity of each of our assumptions. 3) show global/local optima equivalence of non-linear deep models having certain pyramidal structure. Unlike some existing works, our result requires no assumption on the differentiability of the activation functions and can go beyond “full-rank” cases. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=ByxLBMZCb |
| https://openreview.net/pdf?id=ByxLBMZCb | |
| PWC | https://paperswithcode.com/paper/learning-deep-models-critical-points-and |
| Repo | |
| Framework | |
360\mbox$^\circ$ Stance Detection
| Title | 360\mbox$^\circ$ Stance Detection |
| Authors | Sebastian Ruder, John Glover, Afshin Mehrabani, Parsa Ghaffari |
| Abstract | The proliferation of fake news and filter bubbles makes it increasingly difficult to form an unbiased, balanced opinion towards a topic. To ameliorate this, we propose 360{\mbox{$^\circ$}} Stance Detection, a tool that aggregates news with multiple perspectives on a topic. It presents them on a spectrum ranging from support to opposition, enabling the user to base their opinion on multiple pieces of diverse evidence. |
| Tasks | Stance Detection |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-5007/ |
| https://www.aclweb.org/anthology/N18-5007 | |
| PWC | https://paperswithcode.com/paper/360a-stance-detection |
| Repo | |
| Framework | |
Syntax for Semantic Role Labeling, To Be, Or Not To Be
| Title | Syntax for Semantic Role Labeling, To Be, Or Not To Be |
| Authors | Shexia He, Zuchao Li, Hai Zhao, Hongxiao Bai |
| Abstract | Semantic role labeling (SRL) is dedicated to recognizing the predicate-argument structure of a sentence. Previous studies have shown syntactic information has a remarkable contribution to SRL performance. However, such perception was challenged by a few recent neural SRL models which give impressive performance without a syntactic backbone. This paper intends to quantify the importance of syntactic information to dependency SRL in deep learning framework. We propose an enhanced argument labeling model companying with an extended korder argument pruning algorithm for effectively exploiting syntactic information. Our model achieves state-of-the-art results on the CoNLL-2008, 2009 benchmarks for both English and Chinese, showing the quantitative significance of syntax to neural SRL together with a thorough empirical survey over existing models. |
| Tasks | Dependency Parsing, Feature Engineering, Machine Translation, Question Answering, Semantic Parsing, Semantic Role Labeling |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1192/ |
| https://www.aclweb.org/anthology/P18-1192 | |
| PWC | https://paperswithcode.com/paper/syntax-for-semantic-role-labeling-to-be-or |
| Repo | |
| Framework | |
Collecting Language Resources from Public Administrations in the Nordic and Baltic Countries
| Title | Collecting Language Resources from Public Administrations in the Nordic and Baltic Countries |
| Authors | Andrejs Vasi{\c{l}}jevs, Rihards Kalni{\c{n}}{\v{s}}, Roberts Rozis, Aivars B{=e}rzi{\c{n}}{\v{s}} |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1391/ |
| https://www.aclweb.org/anthology/L18-1391 | |
| PWC | https://paperswithcode.com/paper/collecting-language-resources-from-public |
| Repo | |
| Framework | |
Using Neural Transfer Learning for Morpho-syntactic Tagging of South-Slavic Languages Tweets
| Title | Using Neural Transfer Learning for Morpho-syntactic Tagging of South-Slavic Languages Tweets |
| Authors | Sara Meftah, Nasredine Semmar, Fatiha Sadat, Stephan Raaijmakers |
| Abstract | In this paper, we describe a morpho-syntactic tagger of tweets, an important component of the CEA List DeepLIMA tool which is a multilingual text analysis platform based on deep learning. This tagger is built for the Morpho-syntactic Tagging of Tweets (MTT) Shared task of the 2018 VarDial Evaluation Campaign. The MTT task focuses on morpho-syntactic annotation of non-canonical Twitter varieties of three South-Slavic languages: Slovene, Croatian and Serbian. We propose to use a neural network model trained in an end-to-end manner for the three languages without any need for task or domain specific features engineering. The proposed approach combines both character and word level representations. Considering the lack of annotated data in the social media domain for South-Slavic languages, we have also implemented a cross-domain Transfer Learning (TL) approach to exploit any available related out-of-domain annotated data. |
| Tasks | Part-Of-Speech Tagging, Transfer Learning |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-3927/ |
| https://www.aclweb.org/anthology/W18-3927 | |
| PWC | https://paperswithcode.com/paper/using-neural-transfer-learning-for-morpho |
| Repo | |
| Framework | |
Modulated Convolutional Networks
| Title | Modulated Convolutional Networks |
| Authors | Xiaodi Wang, Baochang Zhang, Ce Li, Rongrong Ji, Jungong Han, Xianbin Cao, Jianzhuang Liu |
| Abstract | Despite great effectiveness of very deep and wide Convolutional Neural Networks (CNNs) in various computer vision tasks, the significant cost in terms of storage requirement of such networks impedes the deployment on computationally limited devices. In this paper, we propose new Modulated Convolutional Networks (MCNs) to improve the portability of CNNs via binarized filters. In MCNs, we propose a new loss function which considers the filter loss, center loss and softmax loss in an end-to-end framework. We first introduce modulation filters (M-Filters) to recover the unbinarized filters, which leads to a new architecture to calculate the network model. The convolution operation is further approximated by considering intra-class compactness in the loss function. As a result, our MCNs can reduce the size of required storage space of convolutional filters by a factor of 32, in contrast to the full-precision model, while achieving much better performances than state-of-the-art binarized models. Most importantly, MCNs achieve a comparable performance to the full-precision ResNets and Wide-ResNets. The code will be available publicly soon. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Wang_Modulated_Convolutional_Networks_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Modulated_Convolutional_Networks_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/modulated-convolutional-networks |
| Repo | |
| Framework | |
Introspection for convolutional automatic speech recognition
| Title | Introspection for convolutional automatic speech recognition |
| Authors | Andreas Krug, Sebastian Stober |
| Abstract | Artificial Neural Networks (ANNs) have experienced great success in the past few years. The increasing complexity of these models leads to less understanding about their decision processes. Therefore, introspection techniques have been proposed, mostly for images as input data. Patterns or relevant regions in images can be intuitively interpreted by a human observer. This is not the case for more complex data like speech recordings. In this work, we investigate the application of common introspection techniques from computer vision to an Automatic Speech Recognition (ASR) task. To this end, we use a model similar to image classification, which predicts letters from spectrograms. We show difficulties in applying image introspection to ASR. To tackle these problems, we propose normalized averaging of aligned inputs (NAvAI): a data-driven method to reveal learned patterns for prediction of specific classes. Our method integrates information from many data examples through local introspection techniques for Convolutional Neural Networks (CNNs). We demonstrate that our method provides better interpretability of letter-specific patterns than existing methods. |
| Tasks | Image Classification, Machine Translation, Speech Recognition |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-5421/ |
| https://www.aclweb.org/anthology/W18-5421 | |
| PWC | https://paperswithcode.com/paper/introspection-for-convolutional-automatic |
| Repo | |
| Framework | |
Cross-Domain Detection of Abusive Language Online
| Title | Cross-Domain Detection of Abusive Language Online |
| Authors | Mladen Karan, Jan {\v{S}}najder |
| Abstract | We investigate to what extent the models trained to detect general abusive language generalize between different datasets labeled with different abusive language types. To this end, we compare the cross-domain performance of simple classification models on nine different datasets, finding that the models fail to generalize to out-domain datasets and that having at least some in-domain data is important. We also show that using the frustratingly simple domain adaptation (Daume III, 2007) in most cases improves the results over in-domain training, especially when used to augment a smaller dataset with a larger one. |
| Tasks | Domain Adaptation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5117/ |
| https://www.aclweb.org/anthology/W18-5117 | |
| PWC | https://paperswithcode.com/paper/cross-domain-detection-of-abusive-language |
| Repo | |
| Framework | |
Deep Adversarial Subspace Clustering
| Title | Deep Adversarial Subspace Clustering |
| Authors | Pan Zhou, Yunqing Hou, Jiashi Feng |
| Abstract | Most existing subspace clustering methods hinge on self-expression of handcrafted representations and are unaware of potential clustering errors. Thus they perform unsatisfactorily on real data with complex underlying subspaces. To solve this issue, we propose a novel deep adversarial subspace clustering (DASC) model, which learns more favorable sample representations by deep learning for subspace clustering, and more importantly introduces adversarial learning to supervise sample representation learning and subspace clustering. Specifically, DASC consists of a subspace clustering generator and a quality-verifying discriminator, which learn against each other. The generator produces subspace estimation and sample clustering. The discriminator evaluates current clustering performance by inspecting whether the re-sampled data from estimated subspaces have consistent subspace properties, and supervises the generator to progressively improve subspace clustering. Experimental results on the handwritten recognition, face and object clustering tasks demonstrate the advantages of DASC over shallow and few deep subspace clustering models. Moreover, to our best knowledge, this is the first successful application of GAN-alike model for unsupervised subspace clustering, which also paves the way for deep learning to solve other unsupervised learning problems. |
| Tasks | Representation Learning |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Zhou_Deep_Adversarial_Subspace_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhou_Deep_Adversarial_Subspace_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-adversarial-subspace-clustering |
| Repo | |
| Framework | |
Multi-Language Surface Realisation as REST API based NLG Microservice
| Title | Multi-Language Surface Realisation as REST API based NLG Microservice |
| Authors | Andreas Madsack, Johanna Heininger, Nyamsuren Davaasambuu, Vitaliia Voronik, Michael K{"a}ufl, Robert Wei{\ss}graeber |
| Abstract | We present a readily available API that solves the morphology component for surface realizers in 10 languages (e.g., English, German and Finnish) for any topic and is available as REST API. This can be used to add morphology to any kind of NLG application (e.g., a multi-language chatbot), without requiring computational linguistic knowledge by the integrator. |
| Tasks | Chatbot, Text Generation |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6560/ |
| https://www.aclweb.org/anthology/W18-6560 | |
| PWC | https://paperswithcode.com/paper/multi-language-surface-realisation-as-rest |
| Repo | |
| Framework | |
