October 16, 2019

1571 words 8 mins read

Paper Group NANR 29

Paper Group NANR 29

SB-CH: A Swiss German Corpus with Sentiment Annotations. MetaReg: Towards Domain Generalization using Meta-Regularization. Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP. A Large Automatically-Acquired All-Words List of Multiword Expressions Scored for Compositionality. Sign Languages and the …

SB-CH: A Swiss German Corpus with Sentiment Annotations

Title SB-CH: A Swiss German Corpus with Sentiment Annotations
Authors Ralf Grubenmann, Don Tuggener, Pius von D{"a}niken, Jan Deriu, Mark Cieliebak
Abstract
Tasks Sentiment Analysis
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1372/
PDF https://www.aclweb.org/anthology/L18-1372
PWC https://paperswithcode.com/paper/sb-ch-a-swiss-german-corpus-with-sentiment
Repo
Framework

MetaReg: Towards Domain Generalization using Meta-Regularization

Title MetaReg: Towards Domain Generalization using Meta-Regularization
Authors Yogesh Balaji, Swami Sankaranarayanan, Rama Chellappa
Abstract Training models that generalize to new domains at test time is a problem of fundamental importance in machine learning. In this work, we encode this notion of domain generalization using a novel regularization function. We pose the problem of finding such a regularization function in a Learning to Learn (or) meta-learning framework. The objective of domain generalization is explicitly modeled by learning a regularizer that makes the model trained on one domain to perform well on another domain. Experimental validations on computer vision and natural language datasets indicate that our method can learn regularizers that achieve good cross-domain generalization.
Tasks Domain Generalization, Meta-Learning
Published 2018-12-01
URL http://papers.nips.cc/paper/7378-metareg-towards-domain-generalization-using-meta-regularization
PDF http://papers.nips.cc/paper/7378-metareg-towards-domain-generalization-using-meta-regularization.pdf
PWC https://paperswithcode.com/paper/metareg-towards-domain-generalization-using
Repo
Framework

Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP

Title Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
Authors
Abstract
Tasks
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-5400/
PDF https://www.aclweb.org/anthology/W18-5400
PWC https://paperswithcode.com/paper/proceedings-of-the-2018-emnlp-workshop
Repo
Framework

A Large Automatically-Acquired All-Words List of Multiword Expressions Scored for Compositionality

Title A Large Automatically-Acquired All-Words List of Multiword Expressions Scored for Compositionality
Authors Will Roberts, Markus Egg
Abstract
Tasks Information Retrieval, Machine Translation, Question Answering, Text Generation, Word Sense Disambiguation
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1046/
PDF https://www.aclweb.org/anthology/L18-1046
PWC https://paperswithcode.com/paper/a-large-automatically-acquired-all-words-list
Repo
Framework

Sign Languages and the Online World Online Dictionaries & Lexicostatistics

Title Sign Languages and the Online World Online Dictionaries & Lexicostatistics
Authors Shi Yu, Carlo Geraci, Natasha Abner
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1668/
PDF https://www.aclweb.org/anthology/L18-1668
PWC https://paperswithcode.com/paper/sign-languages-and-the-online-world-online
Repo
Framework

A Multilingual Wikified Data Set of Educational Material

Title A Multilingual Wikified Data Set of Educational Material
Authors Iris Hendrickx, Eirini Takoulidou, Thanasis Naskos, Katia Lida Kermanidis, Vilelmini Sosoni, Hugo de Vos, Maria Stasimioti, Menno van Zaanen, Panayota Georgakopoulou, Valia Kordoni, Maja Popovic, Markus Egg, Antal van den Bosch
Abstract
Tasks Cross-Lingual Semantic Textual Similarity, Machine Translation, Semantic Textual Similarity, Word Sense Disambiguation
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1073/
PDF https://www.aclweb.org/anthology/L18-1073
PWC https://paperswithcode.com/paper/a-multilingual-wikified-data-set-of
Repo
Framework

Geometry Based Data Generation

Title Geometry Based Data Generation
Authors Ofir Lindenbaum, Jay Stanley, Guy Wolf, Smita Krishnaswamy
Abstract We propose a new type of generative model for high-dimensional data that learns a manifold geometry of the data, rather than density, and can generate points evenly along this manifold. This is in contrast to existing generative models that represent data density, and are strongly affected by noise and other artifacts of data collection. We demonstrate how this approach corrects sampling biases and artifacts, thus improves several downstream data analysis tasks, such as clustering and classification. Finally, we demonstrate that this approach is especially useful in biology where, despite the advent of single-cell technologies, rare subpopulations and gene-interaction relationships are affected by biased sampling. We show that SUGAR can generate hypothetical populations, and it is able to reveal intrinsic patterns and mutual-information relationships between genes on a single-cell RNA sequencing dataset of hematopoiesis.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/7414-geometry-based-data-generation
PDF http://papers.nips.cc/paper/7414-geometry-based-data-generation.pdf
PWC https://paperswithcode.com/paper/geometry-based-data-generation-1
Repo
Framework

BabyCloud, a Technological Platform for Parents and Researchers

Title BabyCloud, a Technological Platform for Parents and Researchers
Authors Xu{^a}n-Nga Cao, Cyrille Dakhlia, Patricia Del Carmen, Mohamed-Amine Jaouani, Malik Ould-Arbi, Emmanuel Dupoux
Abstract
Tasks Language Acquisition
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1361/
PDF https://www.aclweb.org/anthology/L18-1361
PWC https://paperswithcode.com/paper/babycloud-a-technological-platform-for
Repo
Framework

Neural Maximum Subgraph Parsing for Cross-Domain Semantic Dependency Analysis

Title Neural Maximum Subgraph Parsing for Cross-Domain Semantic Dependency Analysis
Authors Yufei Chen, Sheng Huang, Fang Wang, Junjie Cao, Weiwei Sun, Xiaojun Wan
Abstract We present experiments for cross-domain semantic dependency analysis with a neural Maximum Subgraph parser. Our parser targets 1-endpoint-crossing, pagenumber-2 graphs which are a good fit to semantic dependency graphs, and utilizes an efficient dynamic programming algorithm for decoding. For disambiguation, the parser associates words with BiLSTM vectors and utilizes these vectors to assign scores to candidate dependencies. We conduct experiments on the data sets from SemEval 2015 as well as Chinese CCGBank. Our parser achieves very competitive results for both English and Chinese. To improve the parsing performance on cross-domain texts, we propose a data-oriented method to explore the linguistic generality encoded in English Resource Grammar, which is a precisionoriented, hand-crafted HPSG grammar, in an implicit way. Experiments demonstrate the effectiveness of our data-oriented method across a wide range of conditions.
Tasks Dependency Parsing, Semantic Parsing
Published 2018-10-01
URL https://www.aclweb.org/anthology/K18-1054/
PDF https://www.aclweb.org/anthology/K18-1054
PWC https://paperswithcode.com/paper/neural-maximum-subgraph-parsing-for-cross
Repo
Framework

A Multimodal Translation-Based Approach for Knowledge Graph Representation Learning

Title A Multimodal Translation-Based Approach for Knowledge Graph Representation Learning
Authors Hatem Mousselly-Sergieh, Teresa Botschen, Iryna Gurevych, Stefan Roth
Abstract Current methods for knowledge graph (KG) representation learning focus solely on the structure of the KG and do not exploit any kind of external information, such as visual and linguistic information corresponding to the KG entities. In this paper, we propose a multimodal translation-based approach that defines the energy of a KG triple as the sum of sub-energy functions that leverage both multimodal (visual and linguistic) and structural KG representations. Next, a ranking-based loss is minimized using a simple neural network architecture. Moreover, we introduce a new large-scale dataset for multimodal KG representation learning. We compared the performance of our approach to other baselines on two standard tasks, namely knowledge graph completion and triple classification, using our as well as the WN9-IMG dataset. The results demonstrate that our approach outperforms all baselines on both tasks and datasets.
Tasks Graph Representation Learning, Information Retrieval, Knowledge Graph Completion, Knowledge Graphs, Question Answering, Representation Learning
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-2027/
PDF https://www.aclweb.org/anthology/S18-2027
PWC https://paperswithcode.com/paper/a-multimodal-translation-based-approach-for
Repo
Framework

Edit me: A Corpus and a Framework for Understanding Natural Language Image Editing

Title Edit me: A Corpus and a Framework for Understanding Natural Language Image Editing
Authors Ramesh Manuvinakurike, Jacqueline Brixey, Trung Bui, Walter Chang, Doo Soon Kim, Ron Artstein, Kallirroi Georgila
Abstract
Tasks Image Captioning, Question Answering, Visual Question Answering
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1683/
PDF https://www.aclweb.org/anthology/L18-1683
PWC https://paperswithcode.com/paper/edit-me-a-corpus-and-a-framework-for
Repo
Framework

Deep Reinforcement Learning of Region Proposal Networks for Object Detection

Title Deep Reinforcement Learning of Region Proposal Networks for Object Detection
Authors Aleksis Pirinen, Cristian Sminchisescu
Abstract We propose drl-RPN, a deep reinforcement learning-based visual recognition model consisting of a sequential region proposal network (RPN) and an object detector. In contrast to typical RPNs, where candidate object regions (RoIs) are selected greedily via class-agnostic NMS, drl-RPN optimizes an objective closer to the final detection task. This is achieved by replacing the greedy RoI selection process with a sequential attention mechanism which is trained via deep reinforcement learning (RL). Our model is capable of accumulating class-specific evidence over time, potentially affecting subsequent proposals and classification scores, and we show that such context integration significantly boosts detection accuracy. Moreover, drl-RPN automatically decides when to stop the search process and has the benefit of being able to jointly learn the parameters of the policy and the detector, both represented as deep networks. Our model can further learn to search over a wide range of exploration-accuracy trade-offs making it possible to specify or adapt the exploration extent at test time. The resulting search trajectories are image- and category-dependent, yet rely only on a single policy over all object categories. Results on the MS COCO and PASCAL VOC challenges show that our approach outperforms established, typical state-of-the-art object detection pipelines.
Tasks Object Detection
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Pirinen_Deep_Reinforcement_Learning_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Pirinen_Deep_Reinforcement_Learning_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/deep-reinforcement-learning-of-region
Repo
Framework

Evaluating EcoLexiCAT: a Terminology-Enhanced CAT Tool

Title Evaluating EcoLexiCAT: a Terminology-Enhanced CAT Tool
Authors Pilar Le{'o}n-Ara{'u}z, Arianne Reimerink
Abstract
Tasks Machine Translation
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1377/
PDF https://www.aclweb.org/anthology/L18-1377
PWC https://paperswithcode.com/paper/evaluating-ecolexicat-a-terminology-enhanced
Repo
Framework

Solving the Perspective-2-Point Problem for Flying-Camera Photo Composition

Title Solving the Perspective-2-Point Problem for Flying-Camera Photo Composition
Authors Ziquan Lan, David Hsu, Gim Hee Lee
Abstract Drone-mounted flying cameras will revolutionize photo-taking. The user, instead of holding a camera in hand and manually searching for a viewpoint, will interact directly with image contents in the viewfinder through simple gestures, and the flying camera will achieve the desired viewpoint through the autonomous flying capability of the drone. This work studies the underlying viewpoint search problem for composing a photo with two objects of interest, a common situation in photo-taking. We model it as a Perspective-2-Point (P2P) problem, which is under-constrained to determine the six degrees-of-freedom camera pose uniquely. By incorporating the user’s composition requirements and minimizing the camera’s flying distance, we form a constrained nonlinear optimization problem and solve it in closed form. Experiments on synthetic data sets and on a real flying camera system indicate promising results.
Tasks
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Lan_Solving_the_Perspective-2-Point_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Lan_Solving_the_Perspective-2-Point_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/solving-the-perspective-2-point-problem-for
Repo
Framework

A German Corpus for Fine-Grained Named Entity Recognition and Relation Extraction of Traffic and Industry Events

Title A German Corpus for Fine-Grained Named Entity Recognition and Relation Extraction of Traffic and Industry Events
Authors Martin Schiersch, Veselina Mironova, Maximilian Schmitt, Philippe Thomas, Aleks Gabryszak, ra, Leonhard Hennig
Abstract
Tasks Decision Making, Named Entity Recognition, Relation Extraction
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1703/
PDF https://www.aclweb.org/anthology/L18-1703
PWC https://paperswithcode.com/paper/a-german-corpus-for-fine-grained-named-entity
Repo
Framework
comments powered by Disqus