October 15, 2019

2014 words 10 mins read

Paper Group NANR 167

Paper Group NANR 167

CoLoSS: Cognitive Load Corpus with Speech and Performance Data from a Symbol-Digit Dual-Task. Corpora of Typical Sentences. Regularization Neural Networks via Constrained Virtual Movement Field. The RST Spanish-Chinese Treebank. Directional Skip-Gram: Explicitly Distinguishing Left and Right Context for Word Embeddings. Semi-Supervised Generative A …

CoLoSS: Cognitive Load Corpus with Speech and Performance Data from a Symbol-Digit Dual-Task

Title CoLoSS: Cognitive Load Corpus with Speech and Performance Data from a Symbol-Digit Dual-Task
Authors Robert Herms, Maria Wirzberger, Maximilian Eibl, G{"u}nter Daniel Rey
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1681/
PDF https://www.aclweb.org/anthology/L18-1681
PWC https://paperswithcode.com/paper/coloss-cognitive-load-corpus-with-speech-and
Repo
Framework

Corpora of Typical Sentences

Title Corpora of Typical Sentences
Authors Lydia M{"u}ller, Uwe Quasthoff, Maciej Sumalvico
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1688/
PDF https://www.aclweb.org/anthology/L18-1688
PWC https://paperswithcode.com/paper/corpora-of-typical-sentences
Repo
Framework

Regularization Neural Networks via Constrained Virtual Movement Field

Title Regularization Neural Networks via Constrained Virtual Movement Field
Authors Zhendong Zhang, Cheolkon Jung
Abstract We provide a novel thinking of regularization neural networks. We smooth the objective of neural networks w.r.t small adversarial perturbations of the inputs. Different from previous works, we assume the adversarial perturbations are caused by the movement field. When the magnitude of movement field approaches 0, we call it virtual movement field. By introducing the movement field, we cast the problem of finding adversarial perturbations into the problem of finding adversarial movement field. By adding proper geometrical constraints to the movement field, such smoothness can be approximated in closed-form by solving a min-max problem and its geometric meaning is clear. We define the approximated smoothness as the regularization term. We derive three regularization terms as running examples which measure the smoothness w.r.t shift, rotation and scale respectively by adding different constraints. We evaluate our methods on synthetic data, MNIST and CIFAR-10. Experimental results show that our proposed method can significantly improve the baseline neural networks. Compared with the state of the art regularization methods, proposed method achieves a tradeoff between accuracy and geometrical interpretability as well as computational cost.
Tasks
Published 2018-01-01
URL https://openreview.net/forum?id=SkHl6MWC-
PDF https://openreview.net/pdf?id=SkHl6MWC-
PWC https://paperswithcode.com/paper/regularization-neural-networks-via
Repo
Framework

The RST Spanish-Chinese Treebank

Title The RST Spanish-Chinese Treebank
Authors Shuyuan Cao, Iria da Cunha, Mikel Iruskieta
Abstract Discourse analysis is necessary for different tasks of Natural Language Processing (NLP). As two of the most spoken languages in the world, discourse analysis between Spanish and Chinese is important for NLP research. This paper aims to present the first open Spanish-Chinese parallel corpus annotated with discourse information, whose theoretical framework is based on the Rhetorical Structure Theory (RST). We have evaluated and harmonized each annotation part to obtain a high annotated-quality corpus. The corpus is already available to the public.
Tasks
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-4917/
PDF https://www.aclweb.org/anthology/W18-4917
PWC https://paperswithcode.com/paper/the-rst-spanish-chinese-treebank
Repo
Framework

Directional Skip-Gram: Explicitly Distinguishing Left and Right Context for Word Embeddings

Title Directional Skip-Gram: Explicitly Distinguishing Left and Right Context for Word Embeddings
Authors Yan Song, Shuming Shi, Jing Li, Haisong Zhang
Abstract In this paper, we present directional skip-gram (DSG), a simple but effective enhancement of the skip-gram model by explicitly distinguishing left and right context in word prediction. In doing so, a direction vector is introduced for each word, whose embedding is thus learned by not only word co-occurrence patterns in its context, but also the directions of its contextual words. Theoretical and empirical studies on complexity illustrate that our model can be trained as efficient as the original skip-gram model, when compared to other extensions of the skip-gram model. Experimental results show that our model outperforms others on different datasets in semantic (word similarity measurement) and syntactic (part-of-speech tagging) evaluations, respectively.
Tasks Learning Word Embeddings, Part-Of-Speech Tagging, Word Embeddings
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-2028/
PDF https://www.aclweb.org/anthology/N18-2028
PWC https://paperswithcode.com/paper/directional-skip-gram-explicitly
Repo
Framework

Semi-Supervised Generative Adversarial Hashing for Image Retrieval

Title Semi-Supervised Generative Adversarial Hashing for Image Retrieval
Authors Guan’an Wang, Qinghao Hu, Jian Cheng, Zengguang Hou
Abstract With explosive growth of image and video data on the Internet, hashing technique has been extensively studied for large-scale visual search. Benefiting from the advance of deep learning, deep hashing methods have achieved promising performance. However, those deep hashing models are usually trained with supervised information, which is rare and expensive in practice, especially class labels. In this paper, inspired by the idea of generative models and the minimax two-player game, we propose a novel semi-supervised generative adversarial hashing (SSGAH) approach. Firstly, we unify a generative model, a discriminative model and a deep hashing model in a framework for making use of triplet-wise information and unlabeled data. Secondly, we design novel structure of the generative model and the discriminative model to learn the distribution of triplet-wise information in a semi-supervised way. In addition, we propose a semi-supervised ranking loss and an adversary ranking loss to learn binary codes which preserve semantic similarity for both labeled data and unlabeled data. Finally, by optimizing the whole model in an adversary training way, the learned binary codes can capture better semantic information of all data. Extensive empirical evaluations on two widely-used benchmark datasets show that our proposed approach significantly outperforms state-of-the-art hashing methods.
Tasks Image Retrieval, Semantic Similarity, Semantic Textual Similarity
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Guanan_Wang_Semi-Supervised_Generative_Adversarial_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Guanan_Wang_Semi-Supervised_Generative_Adversarial_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/semi-supervised-generative-adversarial
Repo
Framework

M-CNER: A Corpus for Chinese Named Entity Recognition in Multi-Domains

Title M-CNER: A Corpus for Chinese Named Entity Recognition in Multi-Domains
Authors Qi Lu, YaoSheng Yang, Zhenghua Li, Wenliang Chen, Min Zhang
Abstract
Tasks Chinese Named Entity Recognition, Named Entity Recognition, Question Answering, Relation Extraction
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1706/
PDF https://www.aclweb.org/anthology/L18-1706
PWC https://paperswithcode.com/paper/m-cner-a-corpus-for-chinese-named-entity
Repo
Framework

Learning Steady-States of Iterative Algorithms over Graphs

Title Learning Steady-States of Iterative Algorithms over Graphs
Authors Hanjun Dai, Zornitsa Kozareva, Bo Dai, Alex Smola, Le Song
Abstract Many graph analytics problems can be solved via iterative algorithms where the solutions are often characterized by a set of steady-state conditions. Different algorithms respect to different set of fixed point constraints, so instead of using these traditional algorithms, can we learn an algorithm which can obtain the same steady-state solutions automatically from examples, in an effective and scalable way? How to represent the meta learner for such algorithm and how to carry out the learning? In this paper, we propose an embedding representation for iterative algorithms over graphs, and design a learning method which alternates between updating the embeddings and projecting them onto the steady-state constraints. We demonstrate the effectiveness of our framework using a few commonly used graph algorithms, and show that in some cases, the learned algorithm can handle graphs with more than 100,000,000 nodes in a single machine.
Tasks
Published 2018-07-01
URL https://icml.cc/Conferences/2018/Schedule?showEvent=2424
PDF http://proceedings.mlr.press/v80/dai18a/dai18a.pdf
PWC https://paperswithcode.com/paper/learning-steady-states-of-iterative
Repo
Framework

Improving Online Algorithms via ML Predictions

Title Improving Online Algorithms via ML Predictions
Authors Manish Purohit, Zoya Svitkina, Ravi Kumar
Abstract In this work we study the problem of using machine-learned predictions to improve performance of online algorithms. We consider two classical problems, ski rental and non-clairvoyant job scheduling, and obtain new online algorithms that use predictions to make their decisions. These algorithms are oblivious to the performance of the predictor, improve with better predictions, but do not degrade much if the predictions are poor.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/8174-improving-online-algorithms-via-ml-predictions
PDF http://papers.nips.cc/paper/8174-improving-online-algorithms-via-ml-predictions.pdf
PWC https://paperswithcode.com/paper/improving-online-algorithms-via-ml
Repo
Framework

ForFun 1.0: Prague Database of Forms and Functions – An Invaluable Resource for Linguistic Research

Title ForFun 1.0: Prague Database of Forms and Functions – An Invaluable Resource for Linguistic Research
Authors Marie Mikulov{'a}, Eduard Bej{\v{c}}ek
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1709/
PDF https://www.aclweb.org/anthology/L18-1709
PWC https://paperswithcode.com/paper/forfun-10-prague-database-of-forms-and
Repo
Framework

T-Know: a Knowledge Graph-based Question Answering and Infor-mation Retrieval System for Traditional Chinese Medicine

Title T-Know: a Knowledge Graph-based Question Answering and Infor-mation Retrieval System for Traditional Chinese Medicine
Authors Ziqing Liu, Enwei Peng, Shixing Yan, Guozheng Li, Tianyong Hao
Abstract T-Know is a knowledge service system based on the constructed knowledge graph of Traditional Chinese Medicine (TCM). Using authorized and anonymized clinical records, medicine clinical guidelines, teaching materials, classic medical books, academic publications, etc., as data resources, the system extracts triples from free texts to build a TCM knowledge graph by our developed natural language processing methods. On the basis of the knowledge graph, a deep learning algorithm is implemented for single-round question understanding and multiple-round dialogue. In addition, the TCM knowledge graph also is used to support human-computer interactive knowledge retrieval by normalizing search keywords to medical terminology.
Tasks Information Retrieval, Question Answering
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-2004/
PDF https://www.aclweb.org/anthology/C18-2004
PWC https://paperswithcode.com/paper/t-know-a-knowledge-graph-based-question
Repo
Framework

The Other Side of the Coin: Unsupervised Disambiguation of Potentially Idiomatic Expressions by Contrasting Senses

Title The Other Side of the Coin: Unsupervised Disambiguation of Potentially Idiomatic Expressions by Contrasting Senses
Authors Hessel Haagsma, Malvina Nissim, Johan Bos
Abstract Disambiguation of potentially idiomatic expressions involves determining the sense of a potentially idiomatic expression in a given context, e.g. determining that make hay in {`}Investment banks made hay while takeovers shone.{'} is used in a figurative sense. This enables automatic interpretation of idiomatic expressions, which is important for applications like machine translation and sentiment analysis. In this work, we present an unsupervised approach for English that makes use of literalisations of idiom senses to improve disambiguation, which is based on the lexical cohesion graph-based method by Sporleder and Li (2009). Experimental results show that, while literalisation carries novel information, its performance falls short of that of state-of-the-art unsupervised methods. |
Tasks Machine Translation, Sentiment Analysis
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-4919/
PDF https://www.aclweb.org/anthology/W18-4919
PWC https://paperswithcode.com/paper/the-other-side-of-the-coin-unsupervised
Repo
Framework

Latent forward model for Real-time Strategy game planning with incomplete information

Title Latent forward model for Real-time Strategy game planning with incomplete information
Authors Yuandong Tian, Qucheng Gong
Abstract Model-free deep reinforcement learning approaches have shown superhuman performance in simulated environments (e.g., Atari games, Go, etc). During training, these approaches often implicitly construct a latent space that contains key information for decision making. In this paper, we learn a forward model on this latent space and apply it to model-based planning in miniature Real-time Strategy game with incomplete information (MiniRTS). We first show that the latent space constructed from existing actor-critic models contains relevant information of the game, and design training procedure to learn forward models. We also show that our learned forward model can predict meaningful future state and is usable for latent space Monte-Carlo Tree Search (MCTS), in terms of win rates against rule-based agents.
Tasks Atari Games, Decision Making
Published 2018-01-01
URL https://openreview.net/forum?id=H1LAqMbRW
PDF https://openreview.net/pdf?id=H1LAqMbRW
PWC https://paperswithcode.com/paper/latent-forward-model-for-real-time-strategy
Repo
Framework

On the Construction and Evaluation of Color Invariant Networks

Title On the Construction and Evaluation of Color Invariant Networks
Authors Konrad Groh
Abstract This is an empirical paper which constructs color invariant networks and evaluates their performances on a realistic data set. The paper studies the simplest possible case of color invariance: invariance under pixel-wise permutation of the color channels. Thus the network is aware not of the specific color object, but its colorfulness. The data set introduced in the paper consists of images showing crashed cars from which ten classes were extracted. An additional annotation was done which labeled whether the car shown was red or non-red. The networks were evaluated by their performance on the classification task. With the color annotation we altered the color ratios in the training data and analyzed the generalization capabilities of the networks on the unaltered test data. We further split the test data in red and non-red cars and did a similar evaluation. It is shown in the paper that an pixel-wise ordering of the rgb-values of the images performs better or at least similarly for small deviations from the true color ratios. The limits of these networks are also discussed.
Tasks
Published 2018-01-01
URL https://openreview.net/forum?id=BkoCeqgR-
PDF https://openreview.net/pdf?id=BkoCeqgR-
PWC https://paperswithcode.com/paper/on-the-construction-and-evaluation-of-color
Repo
Framework

Poem Machine - a Co-creative NLG Web Application for Poem Writing

Title Poem Machine - a Co-creative NLG Web Application for Poem Writing
Authors Mika H{"a}m{"a}l{"a}inen
Abstract We present Poem Machine, an interactive online tool for co-authoring Finnish poetry with a computationally creative agent. Poem Machine can produce poetry of its own and assist the user in authoring poems. The main target group for the system is primary school children, and its use as a part of teaching is currently under study.
Tasks Text Generation
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-6525/
PDF https://www.aclweb.org/anthology/W18-6525
PWC https://paperswithcode.com/paper/poem-machine-a-co-creative-nlg-web
Repo
Framework
comments powered by Disqus