Paper Group NANR 236
Metaphor: A Computational Perspective by Tony Veale, Ekaterina Shutova and Beata Beigman Klebanov. COAST - Customizable Online Syllable Enhancement in Texts. A flexible framework for automatically enhancing reading materials. Discovering Point Lights With Intensity Distance Fields. Neural Interaction Transparency (NIT): Disentangling Learned Intera …
Metaphor: A Computational Perspective by Tony Veale, Ekaterina Shutova and Beata Beigman Klebanov
| Title | Metaphor: A Computational Perspective by Tony Veale, Ekaterina Shutova and Beata Beigman Klebanov |
| Authors | Carlo Strapparava |
| Abstract | |
| Tasks | Paraphrase Generation |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/J18-1007/ |
| https://www.aclweb.org/anthology/J18-1007 | |
| PWC | https://paperswithcode.com/paper/metaphor-a-computational-perspective-by-tony |
| Repo | |
| Framework | |
COAST - Customizable Online Syllable Enhancement in Texts. A flexible framework for automatically enhancing reading materials
| Title | COAST - Customizable Online Syllable Enhancement in Texts. A flexible framework for automatically enhancing reading materials |
| Authors | Heiko Holz, Zarah Weiss, Oliver Brehm, Detmar Meurers |
| Abstract | This paper presents COAST, a web-based application to easily and automatically enhance syllable structure, word stress, and spacing in texts, that was designed in close collaboration with learning therapists to ensure its practical relevance. Such syllable-enhanced texts are commonly used in learning therapy or private tuition to promote the recognition of syllables in order to improve reading and writing skills. In a state of the art solutions for automatic syllable enhancement, we put special emphasis on syllable stress and support specific marking of the primary syllable stress in words. Core features of our tool are i) a highly customizable text enhancement and template functionality, and ii) a novel crowd-sourcing mechanism that we employ to address the issue of data sparsity in language resources. We successfully tested COAST with real-life practitioners in a series of user tests validating the concept of our framework. |
| Tasks | Language Acquisition |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0509/ |
| https://www.aclweb.org/anthology/W18-0509 | |
| PWC | https://paperswithcode.com/paper/coast-customizable-online-syllable |
| Repo | |
| Framework | |
Discovering Point Lights With Intensity Distance Fields
| Title | Discovering Point Lights With Intensity Distance Fields |
| Authors | Edward Zhang, Michael F. Cohen, Brian Curless |
| Abstract | We introduce the light localization problem. A scene is illuminated by a set of unobserved isotropic point lights. Given the geometry, materials, and illuminated appearance of the scene, the light localization problem is to completely recover the number, positions, and intensities of the lights. We first present a scene transform that identifies likely light positions. Based on this transform, we develop an iterative algorithm to locate remaining lights and determine all light intensities. We demonstrate the success of this method in a large set of 2D synthetic scenes, and show that it extends to 3D, in both synthetic scenes and real-world scenes. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Zhang_Discovering_Point_Lights_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Discovering_Point_Lights_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/discovering-point-lights-with-intensity |
| Repo | |
| Framework | |
Neural Interaction Transparency (NIT): Disentangling Learned Interactions for Improved Interpretability
| Title | Neural Interaction Transparency (NIT): Disentangling Learned Interactions for Improved Interpretability |
| Authors | Michael Tsang, Hanpeng Liu, Sanjay Purushotham, Pavankumar Murali, Yan Liu |
| Abstract | Neural networks are known to model statistical interactions, but they entangle the interactions at intermediate hidden layers for shared representation learning. We propose a framework, Neural Interaction Transparency (NIT), that disentangles the shared learning across different interactions to obtain their intrinsic lower-order and interpretable structure. This is done through a novel regularizer that directly penalizes interaction order. We show that disentangling interactions reduces a feedforward neural network to a generalized additive model with interactions, which can lead to transparent models that perform comparably to the state-of-the-art models. NIT is also flexible and efficient; it can learn generalized additive models with maximum $K$-order interactions by training only $O(1)$ models. |
| Tasks | Representation Learning |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7822-neural-interaction-transparency-nit-disentangling-learned-interactions-for-improved-interpretability |
| http://papers.nips.cc/paper/7822-neural-interaction-transparency-nit-disentangling-learned-interactions-for-improved-interpretability.pdf | |
| PWC | https://paperswithcode.com/paper/neural-interaction-transparency-nit |
| Repo | |
| Framework | |
Evaluation of Feature-Space Speaker Adaptation for End-to-End Acoustic Models
| Title | Evaluation of Feature-Space Speaker Adaptation for End-to-End Acoustic Models |
| Authors | Natalia Tomashenko, Yannick Est{`e}ve |
| Abstract | |
| Tasks | Data Augmentation, End-To-End Speech Recognition, Multi-Task Learning, Speech Recognition |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1500/ |
| https://www.aclweb.org/anthology/L18-1500 | |
| PWC | https://paperswithcode.com/paper/evaluation-of-feature-space-speaker |
| Repo | |
| Framework | |
End-to-End Deep Structured Models for Drawing Crosswalks
| Title | End-to-End Deep Structured Models for Drawing Crosswalks |
| Authors | Justin Liang, Raquel Urtasun |
| Abstract | In this paper we address the problem of detecting crosswalks from LiDAR and camera imagery. Towards this goal, given multiple LiDAR sweeps and the corresponding imagery, we project both inputs onto the ground surface to produce a top down view of the scene. We then leverage convolutional neural networks to extract semantic cues about the location of the crosswalks. These are then used in combination with road centerlines from freely available maps (e.g., OpenStreetMaps) to solve a structured optimization problem which draws the final crosswalk boundaries. Our experiments over crosswalks in a large city area show that 96.6% automation can be achieved. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Justin_Liang_End-to-End_Deep_Structured_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Justin_Liang_End-to-End_Deep_Structured_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-deep-structured-models-for-drawing |
| Repo | |
| Framework | |
A Gold Standard to Measure Relative Linguistic Complexity with a Grounded Language Learning Model
| Title | A Gold Standard to Measure Relative Linguistic Complexity with a Grounded Language Learning Model |
| Authors | Leonor Becerra-Bonache, Henning Christiansen, M. Dolores Jim{'e}nez-L{'o}pez |
| Abstract | This paper focuses on linguistic complexity from a relative perspective. It presents a grounded language learning system that can be used to study linguistic complexity from a developmental point of view and introduces a tool for generating a gold standard in order to evaluate the performance of the learning system. In general, researchers agree that it is more feasible to approach complexity from an objective or theory-oriented viewpoint than from a subjective or user-related point of view. Studies that have adopted a relative complexity approach have showed some preferences for L2 learners. In this paper, we try to show that computational models of the process of language acquisition may be an important tool to consider children and the process of first language acquisition as suitable candidates for evaluating the complexity of languages. |
| Tasks | Language Acquisition |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4601/ |
| https://www.aclweb.org/anthology/W18-4601 | |
| PWC | https://paperswithcode.com/paper/a-gold-standard-to-measure-relative |
| Repo | |
| Framework | |
Associating Inter-Image Salient Instances for Weakly Supervised Semantic Segmentation
| Title | Associating Inter-Image Salient Instances for Weakly Supervised Semantic Segmentation |
| Authors | Ruochen Fan, Qibin Hou, Ming-Ming Cheng, Gang Yu, Ralph R. Martin, Shi-Min Hu |
| Abstract | Effectively bridging between image level keyword annotations and corresponding image pixels is one of the main challenges in weakly supervised semantic segmentation. In this paper, we use an instance-level salient object detector to automatically generate salient instances (candidate objects) for training images. Using similarity features extracted from each salient instance in the whole training set, we build a similarity graph, then use a graph partitioning algorithm to separate it into multiple subgraphs, each of which is associated with a single keyword (tag). Our graph-partitioning-based clustering algorithm allows us to consider the relationships between all salient instances in the training set as well as the information within them. We further show that with the help of attention information, our clustering algorithm is able to correct certain wrong assignments, leading to more accurate results. The proposed framework is general, and any state-of-the-art fully-supervised network structure can be incorporated to learn the segmentation network. When working with DeepLab for semantic segmentation, our method outperforms state-of-the-art weakly supervised alternatives by a large margin, achieving 65.6% mIoU on the PASCAL VOC 2012 dataset. We also combine our method with Mask R-CNN for instance segmentation, and demonstrated for the first time the ability of weakly supervised instance segmentation using only keyword annotations. |
| Tasks | graph partitioning, Instance Segmentation, Semantic Segmentation, Weakly-supervised instance segmentation, Weakly-Supervised Semantic Segmentation |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Ruochen_Fan_Associating_Inter-Image_Salient_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Ruochen_Fan_Associating_Inter-Image_Salient_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/associating-inter-image-salient-instances-for |
| Repo | |
| Framework | |
Disentangling Structure and Aesthetics for Style-Aware Image Completion
| Title | Disentangling Structure and Aesthetics for Style-Aware Image Completion |
| Authors | Andrew Gilbert, John Collomosse, Hailin Jin, Brian Price |
| Abstract | Content-aware image completion or in-painting is a fundamental tool for the correction of defects or removal of objects in images. We propose a non-parametric in-painting algorithm that enforces both structural and aesthetic (style) consistency within the resulting image. Our contributions are two-fold: 1) we explicitly disentangle image structure and style during patch search and selection to ensure a visually consistent look and feel within the target image; 2) we perform adaptive stylization of patches to conform the aesthetics of selected patches to the target image, so harmonising the integration of selected patches into the final composition. We show that explicit consideration of visual style during in-painting delivers excellent qualitative and quantitative results across the varied image styles and content, over the Places2 photographic dataset and a challenging new in-painting dataset of artwork derived from BAM! |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Gilbert_Disentangling_Structure_and_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Gilbert_Disentangling_Structure_and_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/disentangling-structure-and-aesthetics-for |
| Repo | |
| Framework | |
Register-sensitive Translation: a Case Study of Mandarin and Cantonese (Non-archival Extended Abstract)
| Title | Register-sensitive Translation: a Case Study of Mandarin and Cantonese (Non-archival Extended Abstract) |
| Authors | Tak-sum Wong, John Lee |
| Abstract | |
| Tasks | |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-1809/ |
| https://www.aclweb.org/anthology/W18-1809 | |
| PWC | https://paperswithcode.com/paper/register-sensitive-translation-a-case-study |
| Repo | |
| Framework | |
A Bayes-Sard Cubature Method
| Title | A Bayes-Sard Cubature Method |
| Authors | Toni Karvonen, Chris J. Oates, Simo Sarkka |
| Abstract | This paper focusses on the formulation of numerical integration as an inferential task. To date, research effort has largely focussed on the development of Bayesian cubature, whose distributional output provides uncertainty quantification for the integral. However, the point estimators associated to Bayesian cubature can be inaccurate and acutely sensitive to the prior when the domain is high-dimensional. To address these drawbacks we introduce Bayes-Sard cubature, a probabilistic framework that combines the flexibility of Bayesian cubature with the robustness of classical cubatures which are well-established. This is achieved by considering a Gaussian process model for the integrand whose mean is a parametric regression model, with an improper prior on each regression coefficient. The features in the regression model consist of test functions which are guaranteed to be exactly integrated, with remaining degrees of freedom afforded to the non-parametric part. The asymptotic convergence of the Bayes-Sard cubature method is established and the theoretical results are numerically verified. In particular, we report two orders of magnitude reduction in error compared to Bayesian cubature in the context of a high-dimensional financial integral. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7829-a-bayes-sard-cubature-method |
| http://papers.nips.cc/paper/7829-a-bayes-sard-cubature-method.pdf | |
| PWC | https://paperswithcode.com/paper/a-bayes-sard-cubature-method |
| Repo | |
| Framework | |
The Influence of Context on the Learning of Metrical Stress Systems Using Finite-State Machines
| Title | The Influence of Context on the Learning of Metrical Stress Systems Using Finite-State Machines |
| Authors | Cesko Voeten, Menno van Zaanen |
| Abstract | Languages vary in the way stress is assigned to syllables within words. This article investigates the learnability of stress systems in a wide range of languages. The stress systems can be described using finite-state automata with symbols indicating levels of stress (primary, secondary, or no stress). Finite-state automata have been the focus of research in the area of grammatical inference for some time now. It has been shown that finite-state machines are learnable from examples using state-merging. One such approach, which aims to learn k-testable languages, has been applied to stress systems with some success. The family of k-testable languages has been shown to be efficiently learnable (in polynomial time). Here, we extend this approach to k, l-local languages by taking not only left context, but also right context, into account. We consider empirical results testing the performance of our learner using various amounts of context (corresponding to varying definitions of phonological locality). Our results show that our approach of learning stress patterns using state-merging is more reliant on left context than on right context. Additionally, some stress systems fail to be learned by our learner using either the left-context k-testable or the left-and-right-context k, l-local learning system. A more complex merging strategy, and hence grammar representation, is required for these stress systems. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/J18-2004/ |
| https://www.aclweb.org/anthology/J18-2004 | |
| PWC | https://paperswithcode.com/paper/the-influence-of-context-on-the-learning-of |
| Repo | |
| Framework | |
Corpus-Driven Thematic Hierarchy Induction
| Title | Corpus-Driven Thematic Hierarchy Induction |
| Authors | Ilia Kuznetsov, Iryna Gurevych |
| Abstract | Thematic role hierarchy is a widely used linguistic tool to describe interactions between semantic roles and their syntactic realizations. Despite decades of dedicated research and numerous thematic hierarchy suggestions in the literature, this concept has not been used in NLP so far due to incompatibility and limited scope of existing hierarchies. We introduce an empirical framework for thematic hierarchy induction and evaluate several role ranking strategies on English and German full-text corpus data. We hypothesize that global thematic hierarchy induction is feasible, that a hierarchy can be induced from just fractions of training data and that resulting hierarchies apply cross-lingually. We evaluate these assumptions empirically. |
| Tasks | Machine Translation, Question Answering, Semantic Role Labeling |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/K18-1006/ |
| https://www.aclweb.org/anthology/K18-1006 | |
| PWC | https://paperswithcode.com/paper/corpus-driven-thematic-hierarchy-induction |
| Repo | |
| Framework | |
EFLLex: A Graded Lexical Resource for Learners of English as a Foreign Language
| Title | EFLLex: A Graded Lexical Resource for Learners of English as a Foreign Language |
| Authors | Luise D{"u}rlich, Thomas Fran{\c{c}}ois |
| Abstract | |
| Tasks | Language Acquisition, Reading Comprehension |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1140/ |
| https://www.aclweb.org/anthology/L18-1140 | |
| PWC | https://paperswithcode.com/paper/efllex-a-graded-lexical-resource-for-learners |
| Repo | |
| Framework | |
Revita: a Language-learning Platform at the Intersection of ITS and CALL
| Title | Revita: a Language-learning Platform at the Intersection of ITS and CALL |
| Authors | Anisia Katinskaia, Javad Nouri, Roman Yangarber |
| Abstract | |
| Tasks | Language Acquisition |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1644/ |
| https://www.aclweb.org/anthology/L18-1644 | |
| PWC | https://paperswithcode.com/paper/revita-a-language-learning-platform-at-the |
| Repo | |
| Framework | |
