Paper Group NANR 46
Automatic Gender Identification and Reinflection in Arabic. Partners in Crime: Multi-view Sequential Inference for Movie Understanding. Dick-Preston and Morbo at SemEval-2019 Task 4: Transfer Learning for Hyperpartisan News Detection. Localized random projections challenge benchmarks for bio-plausible deep learning. DAGMapper: Learning to Map by Di …
Automatic Gender Identification and Reinflection in Arabic
| Title | Automatic Gender Identification and Reinflection in Arabic |
| Authors | Nizar Habash, Houda Bouamor, Christine Chung |
| Abstract | The impressive progress in many Natural Language Processing (NLP) applications has increased the awareness of some of the biases these NLP systems have with regards to gender identities. In this paper, we propose an approach to extend biased single-output gender-blind NLP systems with gender-specific alternative reinflections. We focus on Arabic, a gender-marking morphologically rich language, in the context of machine translation (MT) from English, and for first-person-singular constructions only. Our contributions are the development of a system-independent gender-awareness wrapper, and the building of a corpus for training and evaluating first-person-singular gender identification and reinflection in Arabic. Our results successfully demonstrate the viability of this approach with 8{%} relative increase in Bleu score for first-person-singular feminine, and 5.3{%} comparable increase for first-person-singular masculine on top of a state-of-the-art gender-blind MT system on a held-out test set. |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3822/ |
| https://www.aclweb.org/anthology/W19-3822 | |
| PWC | https://paperswithcode.com/paper/automatic-gender-identification-and |
| Repo | |
| Framework | |
Partners in Crime: Multi-view Sequential Inference for Movie Understanding
| Title | Partners in Crime: Multi-view Sequential Inference for Movie Understanding |
| Authors | Nikos Papasarantopoulos, Lea Frermann, Mirella Lapata, Shay B. Cohen |
| Abstract | Multi-view learning algorithms are powerful representation learning tools, often exploited in the context of multimodal problems. However, for problems requiring inference at the token-level of a sequence (that is, a separate prediction must be made for every time step), it is often the case that single-view systems are used, or that more than one views are fused in a simple manner. We describe an incremental neural architecture paired with a novel training objective for incremental inference. The network operates on multi-view data. We demonstrate the effectiveness of our approach on the problem of predicting perpetrators in crime drama series, for which our model significantly outperforms previous work and strong baselines. Moreover, we introduce two tasks, crime case and speaker type tagging, that contribute to movie understanding and demonstrate the effectiveness of our model on them. |
| Tasks | MULTI-VIEW LEARNING, Representation Learning |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1212/ |
| https://www.aclweb.org/anthology/D19-1212 | |
| PWC | https://paperswithcode.com/paper/partners-in-crime-multi-view-sequential |
| Repo | |
| Framework | |
Dick-Preston and Morbo at SemEval-2019 Task 4: Transfer Learning for Hyperpartisan News Detection
| Title | Dick-Preston and Morbo at SemEval-2019 Task 4: Transfer Learning for Hyperpartisan News Detection |
| Authors | Tim Isbister, Fredrik Johansson |
| Abstract | In a world of information operations, influence campaigns, and fake news, classification of news articles as following hyperpartisan argumentation or not is becoming increasingly important. We present a deep learning-based approach in which a pre-trained language model has been fine-tuned on domain-specific data and used for classification of news articles, as part of the SemEval-2019 task on hyperpartisan news detection. The suggested approach yields accuracy and F1-scores around 0.8 which places the best performing classifier among the top-5 systems in the competition. |
| Tasks | Language Modelling, Transfer Learning |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2160/ |
| https://www.aclweb.org/anthology/S19-2160 | |
| PWC | https://paperswithcode.com/paper/dick-preston-and-morbo-at-semeval-2019-task-4 |
| Repo | |
| Framework | |
Localized random projections challenge benchmarks for bio-plausible deep learning
| Title | Localized random projections challenge benchmarks for bio-plausible deep learning |
| Authors | Bernd Illing, Wulfram Gerstner, Johanni Brea |
| Abstract | Similar to models of brain-like computation, artificial deep neural networks rely on distributed coding, parallel processing and plastic synaptic weights. Training deep neural networks with the error-backpropagation algorithm, however, is considered bio-implausible. An appealing alternative to training deep neural networks is to use one or a few hidden layers with fixed random weights or trained with an unsupervised, local learning rule and train a single readout layer with a supervised, local learning rule. We find that a network of leaky-integrate-andfire neurons with fixed random, localized receptive fields in the hidden layer and spike timing dependent plasticity to train the readout layer achieves 98.1% test accuracy on MNIST, which is close to the optimal result achievable with error-backpropagation in non-convolutional networks of rate neurons with one hidden layer. To support the design choices of the spiking network, we systematically compare the classification performance of rate networks with a single hidden layer, where the weights of this layer are either random and fixed, trained with unsupervised Principal Component Analysis or Sparse Coding, or trained with the backpropagation algorithm. This comparison revealed, first, that unsupervised learning does not lead to better performance than fixed random projections for large hidden layers on digit classification (MNIST) and object recognition (CIFAR10); second, networks with random projections and localized receptive fields perform significantly better than networks with all-to-all connectivity and almost reach the performance of networks trained with the backpropagation algorithm. The performance of these simple random projection networks is comparable to most current models of bio-plausible deep learning and thus provides an interesting benchmark for future approaches. |
| Tasks | Object Recognition |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SJeT_oRcY7 |
| https://openreview.net/pdf?id=SJeT_oRcY7 | |
| PWC | https://paperswithcode.com/paper/localized-random-projections-challenge |
| Repo | |
| Framework | |
DAGMapper: Learning to Map by Discovering Lane Topology
| Title | DAGMapper: Learning to Map by Discovering Lane Topology |
| Authors | Namdar Homayounfar, Wei-Chiu Ma, Justin Liang, Xinyu Wu, Jack Fan, Raquel Urtasun |
| Abstract | One of the fundamental challenges to scale self-driving is being able to create accurate high definition maps (HD maps) with low cost. Current attempts to automate this pro- cess typically focus on simple scenarios, estimate independent maps per frame or do not have the level of precision required by modern self driving vehicles. In contrast, in this paper we focus on drawing the lane boundaries of complex highways with many lanes that contain topology changes due to forks and merges. Towards this goal, we formulate the problem as inference in a directed acyclic graphical model (DAG), where the nodes of the graph encode geo- metric and topological properties of the local regions of the lane boundaries. Since we do not know a priori the topology of the lanes, we also infer the DAG topology (i.e., nodes and edges) for each region. We demonstrate the effectiveness of our approach on two major North American Highways in two different states and show high precision and recall as well as 89% correct topology. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Homayounfar_DAGMapper_Learning_to_Map_by_Discovering_Lane_Topology_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Homayounfar_DAGMapper_Learning_to_Map_by_Discovering_Lane_Topology_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/dagmapper-learning-to-map-by-discovering-lane |
| Repo | |
| Framework | |
Studying Semantic Chain Shifts with Word2Vec: FOOD\textgreaterMEAT\textgreaterFLESH
| Title | Studying Semantic Chain Shifts with Word2Vec: FOOD\textgreaterMEAT\textgreaterFLESH |
| Authors | Richard Zimmermann |
| Abstract | Word2Vec models are used to study the semantic chain shift FOOD{\textgreater}MEAT{\textgreater}FLESH in the history of English, c. 1425-1925. The development stretches out over a long time, starting before 1500, and may possibly be continuing to this day. The semantic changes likely proceeded as a push chain. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4703/ |
| https://www.aclweb.org/anthology/W19-4703 | |
| PWC | https://paperswithcode.com/paper/studying-semantic-chain-shifts-with-word2vec |
| Repo | |
| Framework | |
Q-Theory Representations are Logically Equivalent to Autosegmental Representations
| Title | Q-Theory Representations are Logically Equivalent to Autosegmental Representations |
| Authors | Nick Danis, Adam Jardine |
| Abstract | |
| Tasks | |
| Published | 2019-01-01 |
| URL | https://www.aclweb.org/anthology/W19-0104/ |
| https://www.aclweb.org/anthology/W19-0104 | |
| PWC | https://paperswithcode.com/paper/q-theory-representations-are-logically |
| Repo | |
| Framework | |
Segmentation and UR Acquisition with UR Constraints
| Title | Segmentation and UR Acquisition with UR Constraints |
| Authors | Max Nelson |
| Abstract | |
| Tasks | |
| Published | 2019-01-01 |
| URL | https://www.aclweb.org/anthology/W19-0107/ |
| https://www.aclweb.org/anthology/W19-0107 | |
| PWC | https://paperswithcode.com/paper/segmentation-and-ur-acquisition-with-ur |
| Repo | |
| Framework | |
Number detectors spontaneously emerge in a deep neural network designed for visual object recognition
| Title | Number detectors spontaneously emerge in a deep neural network designed for visual object recognition |
| Authors | Khaled Nasr, Pooja Viswanathan, Andreas Nieder |
| Abstract | Humans and animals have a “number sense,” an innate capability to intuitively assess the number of visual items in a set, its numerosity. This capability implies that mechanisms to extract numerosity indwell the brain’s visual system, which is primarily concerned with visual object recognition. Here, we show that network units tuned to abstract numerosity, and therefore reminiscent of real number neurons, spontaneously emerge in a biologically inspired deep neural network that was merely trained on visual object recognition. These numerosity-tuned units underlay the network’s number discrimination performance that showed all the characteristics of human and animal number discriminations as predicted by the WeberFechner law. These findings explain the spontaneous emergence of the number sense based on mechanisms inherent to the visual system. |
| Tasks | Object Recognition |
| Published | 2019-05-08 |
| URL | https://advances.sciencemag.org/content/5/5/eaav7903.full |
| https://advances.sciencemag.org/content/advances/5/5/eaav7903.full.pdf%20 | |
| PWC | https://paperswithcode.com/paper/number-detectors-spontaneously-emerge-in-a |
| Repo | |
| Framework | |
Proceedings of the Second Workshop on Computational Models of Reference, Anaphora and Coreference
| Title | Proceedings of the Second Workshop on Computational Models of Reference, Anaphora and Coreference |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2800/ |
| https://www.aclweb.org/anthology/W19-2800 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-second-workshop-on-15 |
| Repo | |
| Framework | |
Identifying Participation of Individual Verbs or VerbNet Classes in the Causative Alternation
| Title | Identifying Participation of Individual Verbs or VerbNet Classes in the Causative Alternation |
| Authors | Esther Seyffarth |
| Abstract | |
| Tasks | Question Answering |
| Published | 2019-01-01 |
| URL | https://www.aclweb.org/anthology/W19-0115/ |
| https://www.aclweb.org/anthology/W19-0115 | |
| PWC | https://paperswithcode.com/paper/identifying-participation-of-individual-verbs |
| Repo | |
| Framework | |
Jabberwocky Parsing: Dependency Parsing with Lexical Noise
| Title | Jabberwocky Parsing: Dependency Parsing with Lexical Noise |
| Authors | Jungo Kasai, Robert Frank |
| Abstract | |
| Tasks | Dependency Parsing, Word Embeddings |
| Published | 2019-01-01 |
| URL | https://www.aclweb.org/anthology/W19-0112/ |
| https://www.aclweb.org/anthology/W19-0112 | |
| PWC | https://paperswithcode.com/paper/jabberwocky-parsing-dependency-parsing-with |
| Repo | |
| Framework | |
Versatile Multiple Choice Learning and Its Application to Vision Computing
| Title | Versatile Multiple Choice Learning and Its Application to Vision Computing |
| Authors | Kai Tian, Yi Xu, Shuigeng Zhou, Jihong Guan |
| Abstract | Most existing ensemble methods aim to train the underlying embedded models independently and simply aggregate their final outputs via averaging or weighted voting. As many prediction tasks contain uncertainty, most of these ensemble methods just reduce variance of the predictions without considering the collaborations among the ensembles. Different from these ensemble methods, multiple choice learning (MCL) methods exploit the cooperation among all the embedded models to generate multiple diverse hypotheses. In this paper, a new MCL method, called vMCL (the abbreviation of versatile Multiple Choice Learning), is developed to extend the application scenarios of MCL methods by ensembling deep neural networks. Our vMCL method keeps the advantage of existing MCL methods while overcoming their major drawback, thus achieves better performance. The novelty of our vMCL lies in three aspects: (1) a choice network is designed to learn the confidence level of each specialist which can provide the best prediction base on multiple hypotheses; (2) a hinge loss is introduced to alleviate the overconfidence issue in MCL settings; (3) Easy to be implemented and can be trained in an end-to-end manner, which is a very attractive feature for many real-world applications. Experiments on image classification and image segmentation task show that vMCL outperforms the existing state-of-the-art MCL methods. |
| Tasks | Image Classification, Semantic Segmentation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Tian_Versatile_Multiple_Choice_Learning_and_Its_Application_to_Vision_Computing_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Tian_Versatile_Multiple_Choice_Learning_and_Its_Application_to_Vision_Computing_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/versatile-multiple-choice-learning-and-its |
| Repo | |
| Framework | |
Oracle-Efficient Algorithms for Online Linear Optimization with Bandit Feedback
| Title | Oracle-Efficient Algorithms for Online Linear Optimization with Bandit Feedback |
| Authors | Shinji Ito, Daisuke Hatano, Hanna Sumita, Kei Takemura, Takuro Fukunaga, Naonori Kakimura, Ken-Ichi Kawarabayashi |
| Abstract | We propose computationally efficient algorithms for \textit{online linear optimization with bandit feedback}, in which a player chooses an \textit{action vector} from a given (possibly infinite) set $\mathcal{A} \subseteq \mathbb{R}^d$, and then suffers a loss that can be expressed as a linear function in action vectors. Although existing algorithms achieve an optimal regret bound of $\tilde{O}(\sqrt{T})$ for $T$ rounds (ignoring factors of $\mathrm{poly} (d, \log T)$), computationally efficient ways of implementing them have not yet been specified, in particular when $\mathcal{A}$ is not bounded by a polynomial size in $d$. A standard way to pursue computational efficiency is to assume that we have an efficient algorithm referred to as \textit{oracle} that solves (offline) linear optimization problems over $\mathcal{A}$. Under this assumption, the computational efficiency of a bandit algorithm can then be measured in terms of \textit{oracle complexity}, i.e., the number of oracle calls. Our contribution is to propose algorithms that offer optimal regret bounds of $\tilde{O}(\sqrt{T})$ as well as low oracle complexity for both \textit{non-stochastic settings} and \textit{stochastic settings}. Our algorithm for non-stochastic settings has an oracle complexity of $\tilde{O}( T )$ and is the first algorithm that achieves both a regret bound of $\tilde{O}( \sqrt{T} )$ and an oracle complexity of $\tilde{O} ( \mathrm{poly} ( T ) )$, given only linear optimization oracles. Our algorithm for stochastic settings calls the oracle only $O( \mathrm{poly} (d, \log T))$ times, which is smaller than the current best oracle complexity of $O( T )$ if $T$ is sufficiently large. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9244-oracle-efficient-algorithms-for-online-linear-optimization-with-bandit-feedback |
| http://papers.nips.cc/paper/9244-oracle-efficient-algorithms-for-online-linear-optimization-with-bandit-feedback.pdf | |
| PWC | https://paperswithcode.com/paper/oracle-efficient-algorithms-for-online-linear |
| Repo | |
| Framework | |
Experiments on Non-native Speech Assessment and its Consistency
| Title | Experiments on Non-native Speech Assessment and its Consistency |
| Authors | Ziwei Zhou, Sowmya Vajjala, Seyed Vahid Mirnezami |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-6309/ |
| https://www.aclweb.org/anthology/W19-6309 | |
| PWC | https://paperswithcode.com/paper/experiments-on-non-native-speech-assessment |
| Repo | |
| Framework | |
