October 16, 2019

1822 words 9 mins read

Paper Group NANR 16

Paper Group NANR 16

Language Identification and Named Entity Recognition in Hinglish Code Mixed Tweets. Automatic and Manual Web Annotations in an Infrastructure to handle Fake News and other Online Media Phenomena. Cross-Lingual Generation and Evaluation of a Wide-Coverage Lexical Semantic Resource. System Description of Supervised and Unsupervised Neural Machine Tra …

Language Identification and Named Entity Recognition in Hinglish Code Mixed Tweets

Title Language Identification and Named Entity Recognition in Hinglish Code Mixed Tweets
Authors Kushagra Singh, Indira Sen, Ponnurangam Kumaraguru
Abstract While growing code-mixed content on Online Social Networks(OSN) provides a fertile ground for studying various aspects of code-mixing, the lack of automated text analysis tools render such studies challenging. To meet this challenge, a family of tools for analyzing code-mixed data such as language identifiers, parts-of-speech (POS) taggers, chunkers have been developed. Named Entity Recognition (NER) is an important text analysis task which is not only informative by itself, but is also needed for downstream NLP tasks such as semantic role labeling. In this work, we present an exploration of automatic NER of code-mixed data. We compare our method with existing off-the-shelf NER tools for social media content,and find that our systems outperforms the best baseline by 33.18 {%} (F1 score).
Tasks Abuse Detection, Chunking, Language Identification, Named Entity Recognition, Semantic Role Labeling
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-3008/
PDF https://www.aclweb.org/anthology/P18-3008
PWC https://paperswithcode.com/paper/language-identification-and-named-entity
Repo
Framework

Automatic and Manual Web Annotations in an Infrastructure to handle Fake News and other Online Media Phenomena

Title Automatic and Manual Web Annotations in an Infrastructure to handle Fake News and other Online Media Phenomena
Authors Georg Rehm, Julian Moreno-Schneider, Peter Bourgonje
Abstract
Tasks News Annotation, Rumour Detection
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1384/
PDF https://www.aclweb.org/anthology/L18-1384
PWC https://paperswithcode.com/paper/automatic-and-manual-web-annotations-in-an
Repo
Framework

Cross-Lingual Generation and Evaluation of a Wide-Coverage Lexical Semantic Resource

Title Cross-Lingual Generation and Evaluation of a Wide-Coverage Lexical Semantic Resource
Authors Attila Nov{'a}k, Borb{'a}la Nov{'a}k
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1007/
PDF https://www.aclweb.org/anthology/L18-1007
PWC https://paperswithcode.com/paper/cross-lingual-generation-and-evaluation-of-a
Repo
Framework

System Description of Supervised and Unsupervised Neural Machine Translation Approaches from ``NL Processing’’ Team at DeepHack.Babel Task

Title System Description of Supervised and Unsupervised Neural Machine Translation Approaches from ``NL Processing’’ Team at DeepHack.Babel Task |
Authors Ilya Gusev, Artem Oboturov
Abstract
Tasks Machine Translation
Published 2018-03-01
URL https://www.aclweb.org/anthology/W18-2206/
PDF https://www.aclweb.org/anthology/W18-2206
PWC https://paperswithcode.com/paper/system-description-of-supervised-and
Repo
Framework

BlogSet-BR: A Brazilian Portuguese Blog Corpus

Title BlogSet-BR: A Brazilian Portuguese Blog Corpus
Authors Henrique Santos, Vinicius Woloszyn, Renata Vieira
Abstract
Tasks Opinion Mining, Sentiment Analysis
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1105/
PDF https://www.aclweb.org/anthology/L18-1105
PWC https://paperswithcode.com/paper/blogset-br-a-brazilian-portuguese-blog-corpus
Repo
Framework

Fast Approximate Natural Gradient Descent in a Kronecker Factored Eigenbasis

Title Fast Approximate Natural Gradient Descent in a Kronecker Factored Eigenbasis
Authors Thomas George, César Laurent, Xavier Bouthillier, Nicolas Ballas, Pascal Vincent
Abstract Optimization algorithms that leverage gradient covariance information, such as variants of natural gradient descent (Amari, 1998), offer the prospect of yielding more effective descent directions. For models with many parameters, the covari- ance matrix they are based on becomes gigantic, making them inapplicable in their original form. This has motivated research into both simple diagonal approxima- tions and more sophisticated factored approximations such as KFAC (Heskes, 2000; Martens & Grosse, 2015; Grosse & Martens, 2016). In the present work we draw inspiration from both to propose a novel approximation that is provably better than KFAC and amendable to cheap partial updates. It consists in tracking a diagonal variance, not in parameter coordinates, but in a Kronecker-factored eigenbasis, in which the diagonal approximation is likely to be more effective. Experiments show improvements over KFAC in optimization speed for several deep network architectures.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/8164-fast-approximate-natural-gradient-descent-in-a-kronecker-factored-eigenbasis
PDF http://papers.nips.cc/paper/8164-fast-approximate-natural-gradient-descent-in-a-kronecker-factored-eigenbasis.pdf
PWC https://paperswithcode.com/paper/fast-approximate-natural-gradient-descent-in
Repo
Framework

Improving String Processing for Temporal Relations

Title Improving String Processing for Temporal Relations
Authors David Woods, Fern, Tim o
Abstract
Tasks
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-4709/
PDF https://www.aclweb.org/anthology/W18-4709
PWC https://paperswithcode.com/paper/improving-string-processing-for-temporal
Repo
Framework

Identifying Transferable Information Across Domains for Cross-domain Sentiment Classification

Title Identifying Transferable Information Across Domains for Cross-domain Sentiment Classification
Authors Raksha Sharma, Pushpak Bhattacharyya, D, S apat, ipan, Himanshu Sharad Bhatt
Abstract Getting manually labeled data in each domain is always an expensive and a time consuming task. Cross-domain sentiment analysis has emerged as a demanding concept where a labeled source domain facilitates a sentiment classifier for an unlabeled target domain. However, polarity orientation (positive or negative) and the significance of a word to express an opinion often differ from one domain to another domain. Owing to these differences, cross-domain sentiment classification is still a challenging task. In this paper, we propose that words that do not change their polarity and significance represent the transferable (usable) information across domains for cross-domain sentiment classification. We present a novel approach based on χ2 test and cosine-similarity between context vector of words to identify polarity preserving significant words across domains. Furthermore, we show that a weighted ensemble of the classifiers enhances the cross-domain classification performance.
Tasks Domain Adaptation, Sentiment Analysis, Transfer Learning
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-1089/
PDF https://www.aclweb.org/anthology/P18-1089
PWC https://paperswithcode.com/paper/identifying-transferable-information-across
Repo
Framework

Quantifying Context Overlap for Training Word Embeddings

Title Quantifying Context Overlap for Training Word Embeddings
Authors Yimeng Zhuang, Jinghui Xie, Yinhe Zheng, Xuan Zhu
Abstract Most models for learning word embeddings are trained based on the context information of words, more precisely first order co-occurrence relations. In this paper, a metric is designed to estimate second order co-occurrence relations based on context overlap. The estimated values are further used as the augmented data to enhance the learning of word embeddings by joint training with existing neural word embedding models. Experimental results show that better word vectors can be obtained for word similarity tasks and some downstream NLP tasks by the enhanced approach.
Tasks Dimensionality Reduction, Language Modelling, Learning Word Embeddings, Representation Learning, Semantic Composition, Word Embeddings
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1057/
PDF https://www.aclweb.org/anthology/D18-1057
PWC https://paperswithcode.com/paper/quantifying-context-overlap-for-training-word
Repo
Framework

Transc&Anno: A Graphical Tool for the Transcription and On-the-Fly Annotation of Handwritten Documents

Title Transc&Anno: A Graphical Tool for the Transcription and On-the-Fly Annotation of Handwritten Documents
Authors Nadezda Okinina, Lionel Nicolas, Verena Lyding
Abstract
Tasks Language Acquisition
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1112/
PDF https://www.aclweb.org/anthology/L18-1112
PWC https://paperswithcode.com/paper/transcanno-a-graphical-tool-for-the
Repo
Framework

Implicit Discourse Relation Recognition using Neural Tensor Network with Interactive Attention and Sparse Learning

Title Implicit Discourse Relation Recognition using Neural Tensor Network with Interactive Attention and Sparse Learning
Authors Fengyu Guo, Ruifang He, Di Jin, Jianwu Dang, Longbiao Wang, Xiangang Li
Abstract Implicit discourse relation recognition aims to understand and annotate the latent relations between two discourse arguments, such as temporal, comparison, etc. Most previous methods encode two discourse arguments separately, the ones considering pair specific clues ignore the bidirectional interactions between two arguments and the sparsity of pair patterns. In this paper, we propose a novel neural Tensor network framework with Interactive Attention and Sparse Learning (TIASL) for implicit discourse relation recognition. (1) We mine the most correlated word pairs from two discourse arguments to model pair specific clues, and integrate them as interactive attention into argument representations produced by the bidirectional long short-term memory network. Meanwhile, (2) the neural tensor network with sparse constraint is proposed to explore the deeper and the more important pair patterns so as to fully recognize discourse relations. The experimental results on PDTB show that our proposed TIASL framework is effective.
Tasks Sparse Learning, Text Summarization
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1046/
PDF https://www.aclweb.org/anthology/C18-1046
PWC https://paperswithcode.com/paper/implicit-discourse-relation-recognition-using
Repo
Framework

ARB-SEN at SemEval-2018 Task1: A New Set of Features for Enhancing the Sentiment Intensity Prediction in Arabic Tweets

Title ARB-SEN at SemEval-2018 Task1: A New Set of Features for Enhancing the Sentiment Intensity Prediction in Arabic Tweets
Authors El Moatez Billah Nagoudi
Abstract This article describes our proposed Arabic Sentiment Analysis system named ARB-SEN. This system is designed for the International Workshop on Semantic Evaluation 2018 (SemEval-2018), Task1: Affect in Tweets. ARB-SEN proposes two supervised models to estimate the sentiment intensity in Arabic tweets. Both models use a set of features including sentiment lexicon, negation, word embedding and emotion symbols features. Our system combines these features to assist the sentiment analysis task. ARB-SEN system achieves a correlation score of 0.720, ranking 6th among all participants in the valence intensity regression (V-reg) for the Arabic sub-task organized within the SemEval 2018 evaluation campaign.
Tasks Arabic Sentiment Analysis, Sentiment Analysis
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1055/
PDF https://www.aclweb.org/anthology/S18-1055
PWC https://paperswithcode.com/paper/arb-sen-at-semeval-2018-task1-a-new-set-of
Repo
Framework

Word Embedding Evaluation Datasets and Wikipedia Title Embedding for Chinese

Title Word Embedding Evaluation Datasets and Wikipedia Title Embedding for Chinese
Authors Chi-Yen Chen, Wei-Yun Ma
Abstract
Tasks Knowledge Graphs, Word Embeddings
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1132/
PDF https://www.aclweb.org/anthology/L18-1132
PWC https://paperswithcode.com/paper/word-embedding-evaluation-datasets-and
Repo
Framework

Webly Supervised Joint Embedding for Cross-Modal lmage-Text Retrieval

Title Webly Supervised Joint Embedding for Cross-Modal lmage-Text Retrieval
Authors Niluthpol Chowdhury Mithun, Rameswar Panda, Vagelis Papalexakis, Amit K.Roy-Chowdhury
Abstract Cross-modal retrieval between visual data and natural language description remains a long-standing challenge in multimedia. While recent image-text retrieval methods offer great promise by learning deep representations aligned across modalities, most of these meth-ods are plagued by the issue of training with small-scale datasets covering a limited number of images with ground-truth sentences. Moreover, it is extremely expensive to create a larger dataset by annotating millions of training images with ground-truth sentences and may lead to a biased model. Inspired by the recent success of web-supervised learning in deep neural networks, we capitalize on readily-available web images with noisy annotations to learn robust image-text joint representation. Specifically, our main idea is to leverage web images and corresponding tags, along with fully annotated datasets, in training for learning the visual-semantic joint embedding. We propose a two-stage approach for the task that can augment a typical supervised pair-wise ranking loss based formulation with weakly-annotated web images to learn a more robust visual-semantic embedding. Extensive experiments on two standard benchmark datasets demonstrate that our method achieves a significant performance gain in image-text retrieval compared to state-of-the-art approaches.
Tasks Cross-Modal Retrieval
Published 2018-10-01
URL https://dl.acm.org/doi/abs/10.1145/3240508.3240712
PDF https://par.nsf.gov/servlets/purl/10064325
PWC https://paperswithcode.com/paper/webly-supervised-joint-embedding-for-cross-1
Repo
Framework

Deep Progressive Reinforcement Learning for Skeleton-Based Action Recognition

Title Deep Progressive Reinforcement Learning for Skeleton-Based Action Recognition
Authors Yansong Tang, Yi Tian, Jiwen Lu, Peiyang Li, Jie Zhou
Abstract In this paper, we propose a deep progressive reinforcement learning (DPRL) method for action recognition in skeleton-based videos, which aims to distil the most informative frames and discard ambiguous frames in sequences for recognizing actions. Since the choices of selecting representative frames are multitudinous for each video, we model the frame selection as a progressive process through deep reinforcement learning, during which we progressively adjust the chosen frames by taking two important factors into account: (1) the quality of the selected frames and (2) the relationship between the selected frames to the whole video. Moreover, considering the topology of human body inherently lies in a graph-based structure, where the vertices and edges represent the hinged joints and rigid bones respectively, we employ the graph-based convolutional neural network to capture the dependency between the joints for action recognition. Our approach achieves very competitive performance on three widely used benchmarks.
Tasks Skeleton Based Action Recognition, Temporal Action Localization
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Tang_Deep_Progressive_Reinforcement_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Tang_Deep_Progressive_Reinforcement_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/deep-progressive-reinforcement-learning-for
Repo
Framework
comments powered by Disqus