Paper Group NANR 213
CUNI System for the WMT18 Multimodal Translation Task. Findings of the WMT 2018 Shared Task on Quality Estimation. Modifying memories in a Recurrent Neural Network Unit. Challenge or Empower: Revisiting Argumentation Quality in a News Editorial Corpus. Unbiased Objective Estimation in Predictive Optimization. Learning Parsimonious Deep Feed-forward …
CUNI System for the WMT18 Multimodal Translation Task
| Title | CUNI System for the WMT18 Multimodal Translation Task |
| Authors | Jind{\v{r}}ich Helcl, Jind{\v{r}}ich Libovick{'y}, Du{\v{s}}an Vari{\v{s}} |
| Abstract | We present our submission to the WMT18 Multimodal Translation Task. The main feature of our submission is applying a self-attentive network instead of a recurrent neural network. We evaluate two methods of incorporating the visual features in the model: first, we include the image representation as another input to the network; second, we train the model to predict the visual features and use it as an auxiliary objective. For our submission, we acquired both textual and multimodal additional data. Both of the proposed methods yield significant improvements over recurrent networks and self-attentive textual baselines. |
| Tasks | Image Classification, Machine Translation, Multimodal Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6441/ |
| https://www.aclweb.org/anthology/W18-6441 | |
| PWC | https://paperswithcode.com/paper/cuni-system-for-the-wmt18-multimodal-1 |
| Repo | |
| Framework | |
Findings of the WMT 2018 Shared Task on Quality Estimation
| Title | Findings of the WMT 2018 Shared Task on Quality Estimation |
| Authors | Lucia Specia, Fr{'e}d{'e}ric Blain, Varvara Logacheva, Ram{'o}n Astudillo, Andr{'e} F. T. Martins |
| Abstract | We report the results of the WMT18 shared task on Quality Estimation, i.e. the task of predicting the quality of the output of machine translation systems at various granularity levels: word, phrase, sentence and document. This year we include four language pairs, three text domains, and translations produced by both statistical and neural machine translation systems. Participating teams from ten institutions submitted a variety of systems to different task variants and language pairs. |
| Tasks | Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6451/ |
| https://www.aclweb.org/anthology/W18-6451 | |
| PWC | https://paperswithcode.com/paper/findings-of-the-wmt-2018-shared-task-on-1 |
| Repo | |
| Framework | |
Modifying memories in a Recurrent Neural Network Unit
| Title | Modifying memories in a Recurrent Neural Network Unit |
| Authors | Vlad Velici, Adam Prügel-Bennett |
| Abstract | Long Short-Term Memory (LSTM) units have the ability to memorise and use long-term dependencies between inputs to generate predictions on time series data. We introduce the concept of modifying the cell state (memory) of LSTMs using rotation matrices parametrised by a new set of trainable weights. This addition shows significant increases of performance on some of the tasks from the bAbI dataset. |
| Tasks | Time Series |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=ByUEelW0- |
| https://openreview.net/pdf?id=ByUEelW0- | |
| PWC | https://paperswithcode.com/paper/modifying-memories-in-a-recurrent-neural |
| Repo | |
| Framework | |
Challenge or Empower: Revisiting Argumentation Quality in a News Editorial Corpus
| Title | Challenge or Empower: Revisiting Argumentation Quality in a News Editorial Corpus |
| Authors | Roxanne El Baff, Henning Wachsmuth, Khalid Al-Khatib, Benno Stein |
| Abstract | News editorials are said to shape public opinion, which makes them a powerful tool and an important source of political argumentation. However, rarely do editorials change anyone{'}s stance on an issue completely, nor do they tend to argue explicitly (but rather follow a subtle rhetorical strategy). So, what does argumentation quality mean for editorials then? We develop the notion that an effective editorial challenges readers with opposing stance, and at the same time empowers the arguing skills of readers that share the editorial{'}s stance {—} or even challenges both sides. To study argumentation quality based on this notion, we introduce a new corpus with 1000 editorials from the New York Times, annotated for their perceived effect along with the annotators{'} political orientations. Analyzing the corpus, we find that annotators with different orientation disagree on the effect significantly. While only 1{%} of all editorials changed anyone{'}s stance, more than 5{%} meet our notion. We conclude that our corpus serves as a suitable resource for studying the argumentation quality of news editorials. |
| Tasks | Argument Mining |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/K18-1044/ |
| https://www.aclweb.org/anthology/K18-1044 | |
| PWC | https://paperswithcode.com/paper/challenge-or-empower-revisiting-argumentation |
| Repo | |
| Framework | |
Unbiased Objective Estimation in Predictive Optimization
| Title | Unbiased Objective Estimation in Predictive Optimization |
| Authors | Shinji Ito, Akihiro Yabe, Ryohei Fujimaki |
| Abstract | For data-driven decision-making, one promising approach, called predictive optimization, is to solve maximization problems i n which the objective function to be maximized is estimated from data. Predictive optimization, however, suffers from the problem of a calculated optimal solution’s being evaluated too optimistically, i.e., the value of the objective function is overestimated. This paper investigates such optimistic bias and presents two methods for correcting it. The first, which is analogous to cross-validation, successfully corrects the optimistic bias but results in underestimation of the true value. Our second method employs resampling techniques to avoid both overestimation and underestimation. We show that the second method, referred to as the parameter perturbation method, achieves asymptotically unbiased estimation. Empirical results for both artificial and real-world datasets demonstrate that our proposed approach successfully corrects the optimistic bias. |
| Tasks | Decision Making |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2001 |
| http://proceedings.mlr.press/v80/ito18a/ito18a.pdf | |
| PWC | https://paperswithcode.com/paper/unbiased-objective-estimation-in-predictive |
| Repo | |
| Framework | |
Learning Parsimonious Deep Feed-forward Networks
| Title | Learning Parsimonious Deep Feed-forward Networks |
| Authors | Zhourong Chen, Xiaopeng Li, Nevin L. Zhang |
| Abstract | Convolutional neural networks and recurrent neural networks are designed with network structures well suited to the nature of spacial and sequential data respectively. However, the structure of standard feed-forward neural networks (FNNs) is simply a stack of fully connected layers, regardless of the feature correlations in data. In addition, the number of layers and the number of neurons are manually tuned on validation data, which is time-consuming and may lead to suboptimal networks. In this paper, we propose an unsupervised structure learning method for learning parsimonious deep FNNs. Our method determines the number of layers, the number of neurons at each layer, and the sparse connectivity between adjacent layers automatically from data. The resulting models are called Backbone-Skippath Neural Networks (BSNNs). Experiments on 17 tasks show that, in comparison with FNNs, BSNNs can achieve better or comparable classification performance with much fewer parameters. The interpretability of BSNNs is also shown to be better than that of FNNs. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=HJMN-xWC- |
| https://openreview.net/pdf?id=HJMN-xWC- | |
| PWC | https://paperswithcode.com/paper/learning-parsimonious-deep-feed-forward |
| Repo | |
| Framework | |
Birzeit Arabic Dialect Identification System for the 2018 VarDial Challenge
| Title | Birzeit Arabic Dialect Identification System for the 2018 VarDial Challenge |
| Authors | Rabee Naser, Abualsoud Hanani |
| Abstract | This paper describes our Automatic Dialect Recognition (ADI) system for the VarDial 2018 challenge, with the goal of distinguishing four major Arabic dialects, as well as Modern Standard Arabic (MSA). The training and development ADI VarDial 2018 data consists of 16,157 utterances, their words transcription, their phonetic transcriptions obtained with four non-Arabic phoneme recognizers and acoustic embedding data. Our overall system is a combination of four different systems. One system uses the words transcriptions and tries to recognize the speaker dialect by modeling the sequence of words for each dialect. Another system tries to recognize the dialect by modeling the phones sequence produced by non-Arabic phone recognizers, whereas, the other two systems use GMM trained on the acoustic features for recognizing the dialect. The best performance was achieved by the fused system which combines four systems together, with F1 micro of 68.77{%}. |
| Tasks | Language Modelling, Large Vocabulary Continuous Speech Recognition, Speech Recognition |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-3924/ |
| https://www.aclweb.org/anthology/W18-3924 | |
| PWC | https://paperswithcode.com/paper/birzeit-arabic-dialect-identification-system |
| Repo | |
| Framework | |
Sub-GAN: An Unsupervised Generative Model via Subspaces
| Title | Sub-GAN: An Unsupervised Generative Model via Subspaces |
| Authors | Jie Liang, Jufeng Yang, Hsin-Ying Lee, Kai Wang, Ming-Hsuan Yang |
| Abstract | The recent years have witnessed significant growth in constructing robust generative models to capture informative distributions of natural data. However, it is difficult to fully exploit the distribution of complex data, like images and videos, due to the high dimensionality of ambient space. Sequentially, how to effectively guide the training of generative models is a crucial issue. In this paper, we present a subspace-based generative adversarial network (Sub-GAN) which simultaneously disentangles multiple latent subspaces and generates diverse samples correspondingly. Since the high-dimensional natural data usually lies on a union of low-dimensional subspaces which contain semantically extensive structure, Sub-GAN incorporates a novel clusterer that can interact with the generator and discriminator via subspace information. Unlike the traditional generative models, the proposed Sub-GAN can control the diversity of the generated samples via the multiplicity of the learned subspaces. Moreover, the Sub-GAN follows an unsupervised fashion to explore not only the visual classes but the latent continuous attributes. We demonstrate that our model can discover meaningful visual attributes which is hard to be annotated via strong supervision, e.g., the writing style of digits, thus avoid the mode collapse problem. Extensive experimental results show the competitive performance of the proposed method for both generating diverse images with satisfied quality and discovering discriminative latent subspaces. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Jie_Liang_Sub-GAN_An_Unsupervised_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Jie_Liang_Sub-GAN_An_Unsupervised_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/sub-gan-an-unsupervised-generative-model-via |
| Repo | |
| Framework | |
A Prior-Less Method for Multi-Face Tracking in Unconstrained Videos
| Title | A Prior-Less Method for Multi-Face Tracking in Unconstrained Videos |
| Authors | Chung-Ching Lin, Ying Hung |
| Abstract | This paper presents a prior-less method for tracking and clustering an unknown number of human faces and maintaining their individual identities in unconstrained videos. The key challenge is to accurately track faces with partial occlusion and drastic appearance changes in multiple shots resulting from significant variations of makeup, facial expression, head pose and illumination. To address this challenge, we propose a new multi-face tracking and re-identification algorithm, which provides high accuracy in face association in the entire video with automatic cluster number generation, and is robust to outliers. We develop a co-occurrence model of multiple body parts to seamlessly create face tracklets, and recursively link tracklets to construct a graph for extracting clusters. A Gaussian Process model is introduced to compensate the deep feature insufficiency, and is further used to refine the linking results. The advantages of the proposed algorithm are demonstrated using a variety of challenging music videos and newly introduced body-worn camera videos. The proposed method obtains significant improvements over the state of the art [51], while relying less on handling video-specific prior information to achieve high performance. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Lin_A_Prior-Less_Method_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Lin_A_Prior-Less_Method_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/a-prior-less-method-for-multi-face-tracking |
| Repo | |
| Framework | |
Tackling Adversarial Examples in QA via Answer Sentence Selection
| Title | Tackling Adversarial Examples in QA via Answer Sentence Selection |
| Authors | Yuanhang Ren, Ye Du, Di Wang |
| Abstract | Question answering systems deteriorate dramatically in the presence of adversarial sentences in articles. According to Jia and Liang (2017), the single BiDAF system (Seo et al., 2016) only achieves an F1 score of 4.8 on the ADDANY adversarial dataset. In this paper, we present a method to tackle this problem via answer sentence selection. Given a paragraph of an article and a corresponding query, instead of directly feeding the whole paragraph to the single BiDAF system, a sentence that most likely contains the answer to the query is first selected, which is done via a deep neural network based on TreeLSTM (Tai et al., 2015). Experiments on ADDANY adversarial dataset validate the effectiveness of our method. The F1 score has been improved to 52.3. |
| Tasks | Question Answering, Reading Comprehension |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2604/ |
| https://www.aclweb.org/anthology/W18-2604 | |
| PWC | https://paperswithcode.com/paper/tackling-adversarial-examples-in-qa-via |
| Repo | |
| Framework | |
Proceedings of the 13th Conference of the Association for Machine Translation in the Americas (Volume 2: User Papers)
| Title | Proceedings of the 13th Conference of the Association for Machine Translation in the Americas (Volume 2: User Papers) |
| Authors | |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-1900/ |
| https://www.aclweb.org/anthology/W18-1900 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-13th-conference-of-the |
| Repo | |
| Framework | |
Developing a Neural Machine Translation Service for the 2017-2018 European Union Presidency
| Title | Developing a Neural Machine Translation Service for the 2017-2018 European Union Presidency |
| Authors | M{=a}rcis Pinnis, Rihards Kalnins |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-1910/ |
| https://www.aclweb.org/anthology/W18-1910 | |
| PWC | https://paperswithcode.com/paper/developing-a-neural-machine-translation |
| Repo | |
| Framework | |
Global Attention for Name Tagging
| Title | Global Attention for Name Tagging |
| Authors | Boliang Zhang, Spencer Whitehead, Lifu Huang, Heng Ji |
| Abstract | Many name tagging approaches use local contextual information with much success, but can fail when the local context is ambiguous or limited. We present a new framework to improve name tagging by utilizing local, document-level, and corpus-level contextual information. For each word, we retrieve document-level context from other sentences within the same document and corpus-level context from sentences in other documents. We propose a model that learns to incorporate document-level and corpus-level contextual information alongside local contextual information via document-level and corpus-level attentions, which dynamically weight their respective contextual information and determines the influence of this information through gating mechanisms. Experiments on benchmark datasets show the effectiveness of our approach, which achieves state-of-the-art results for Dutch, German, and Spanish on the CoNLL-2002 and CoNLL-2003 datasets. We will make our code and pre-trained models publicly available for research purposes. |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/K18-1009/ |
| https://www.aclweb.org/anthology/K18-1009 | |
| PWC | https://paperswithcode.com/paper/global-attention-for-name-tagging |
| Repo | |
| Framework | |
Aspect-Based Sentiment Analysis Using Bitmask Bidirectional Long Short Term Memory Networks
| Title | Aspect-Based Sentiment Analysis Using Bitmask Bidirectional Long Short Term Memory Networks |
| Authors | Binh Thanh Do |
| Abstract | This paper introduces a new method to classify sentiment polarity for aspects in product reviews. We call it bitmask bidirectional long short term memory networks. It is based on long short term memory (LSTM) networks, which is a frequently mentioned model in natural language processing. Our proposed method uses a bitmask layer to keep attention on aspects. We evaluate it on reviews of restaurant and laptop domains from three popular contests: SemEval-2014 task 4, SemEval-2015 task 12, and SemEval-2016 task 5. It obtains competitive results with state-of-the-art methods based on LSTM networks. Furthermore, we demonstrate the benefit of using sentiment lexicons and word embeddings of a particular domain in aspect-based sentiment analysis. |
| Tasks | Aspect-Based Sentiment Analysis, Sentiment Analysis, Word Embeddings |
| Published | 2018-05-01 |
| URL | https://aaai.org/ocs/index.php/FLAIRS/FLAIRS18/paper/view/17646 |
| https://aaai.org/ocs/index.php/FLAIRS/FLAIRS18/paper/view/17646/16840 | |
| PWC | https://paperswithcode.com/paper/aspect-based-sentiment-analysis-using-bitmask |
| Repo | |
| Framework | |
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
| Title | Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/D18-2000/ |
| https://www.aclweb.org/anthology/D18-2000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2018-conference-on |
| Repo | |
| Framework | |
