October 15, 2019

1897 words 9 mins read

Paper Group NANR 168

Paper Group NANR 168

Automatic Curation and Visualization of Crime Related Information from Incrementally Crawled Multi-source News Reports. Do Character-Level Neural Network Language Models Capture Knowledge of Multiword Expression Compositionality?. A Language Model based Evaluator for Sentence Compression. Learning to Understand Image Blur. A Lexicon of Discourse Ma …

Title Automatic Curation and Visualization of Crime Related Information from Incrementally Crawled Multi-source News Reports
Authors Tirthankar Dasgupta, Lipika Dey, Rupsa Saha, Abir Naskar
Abstract In this paper, we demonstrate a system for the automatic extraction and curation of crime-related information from multi-source digitally published News articles collected over a period of five years. We have leveraged the use of deep convolution recurrent neural network model to analyze crime articles to extract different crime related entities and events. The proposed methods are not restricted to detecting known crimes only but contribute actively towards maintaining an updated crime ontology. We have done experiments with a collection of 5000 crime-reporting News articles span over time, and multiple sources. The end-product of our experiments is a crime-register that contains details of crime committed across geographies and time. This register can be further utilized for analytical and reporting purposes.
Tasks Entity Resolution
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-2023/
PDF https://www.aclweb.org/anthology/C18-2023
PWC https://paperswithcode.com/paper/automatic-curation-and-visualization-of-crime
Repo
Framework

Do Character-Level Neural Network Language Models Capture Knowledge of Multiword Expression Compositionality?

Title Do Character-Level Neural Network Language Models Capture Knowledge of Multiword Expression Compositionality?
Authors Ali Hakimi Parizi, Paul Cook
Abstract In this paper, we propose the first model for multiword expression (MWE) compositionality prediction based on character-level neural network language models. Experimental results on two kinds of MWEs (noun compounds and verb-particle constructions) and two languages (English and German) suggest that character-level neural network language models capture knowledge of multiword expression compositionality, in particular for English noun compounds and the particle component of English verb-particle constructions. In contrast to many other approaches to MWE compositionality prediction, this character-level approach does not require token-level identification of MWEs in a training corpus, and can potentially predict the compositionality of out-of-vocabulary MWEs.
Tasks Machine Translation
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-4920/
PDF https://www.aclweb.org/anthology/W18-4920
PWC https://paperswithcode.com/paper/do-character-level-neural-network-language
Repo
Framework

A Language Model based Evaluator for Sentence Compression

Title A Language Model based Evaluator for Sentence Compression
Authors Yang Zhao, Zhiyuan Luo, Akiko Aizawa
Abstract We herein present a language-model-based evaluator for deletion-based sentence compression and view this task as a series of deletion-and-evaluation operations using the evaluator. More specifically, the evaluator is a syntactic neural language model that is first built by learning the syntactic and structural collocation among words. Subsequently, a series of trial-and-error deletion operations are conducted on the source sentences via a reinforcement learning framework to obtain the best target compression. An empirical study shows that the proposed model can effectively generate more readable compression, comparable or superior to several strong baselines. Furthermore, we introduce a 200-sentence test set for a large-scale dataset, setting a new baseline for the future research.
Tasks Language Modelling, Sentence Compression
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-2028/
PDF https://www.aclweb.org/anthology/P18-2028
PWC https://paperswithcode.com/paper/a-language-model-based-evaluator-for-sentence
Repo
Framework

Learning to Understand Image Blur

Title Learning to Understand Image Blur
Authors Shanghang Zhang, Xiaohui Shen, Zhe Lin, Radomír Měch, João P. Costeira, José M. F. Moura
Abstract While many approaches have been proposed to estimate and remove blur in a photo, few efforts were made to have an algorithm automatically understand the blur desirability: whether the blur is desired or not, and how it affects the quality of the photo. Such a task not only relies on low-level visual features to identify blurry regions, but also requires high-level understanding of the image content as well as user intent during photo capture. In this paper, we propose a unified framework to estimate a spatially-varying blur map and understand its desirability in terms of image quality at the same time. In particular, we use a dilated fully convolutional neural network with pyramid pooling and boundary refinement layers to generate high-quality blur response maps. If blur exists, we classify its desirability to three levels ranging from good to bad, by distilling high-level semantics and learning an attention map to adaptively localize the important content in the image. The whole framework is end-to-end jointly trained with both supervisions of pixel-wise blur responses and image-wise blur desirability levels. Considering the limitations of existing image blur datasets, we collected a new large-scale dataset with both annotations to facilitate training. The proposed methods are extensively evaluated on two datasets and demonstrate state-of-the-art performance on both tasks.
Tasks
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Zhang_Learning_to_Understand_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Learning_to_Understand_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/learning-to-understand-image-blur
Repo
Framework

A Lexicon of Discourse Markers for Portuguese – LDM-PT

Title A Lexicon of Discourse Markers for Portuguese – LDM-PT
Authors Am{'a}lia Mendes, Iria del Rio, Manfred Stede, Felix Dombek
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1693/
PDF https://www.aclweb.org/anthology/L18-1693
PWC https://paperswithcode.com/paper/a-lexicon-of-discourse-markers-for-portuguese
Repo
Framework

Data Management Plan (DMP) for Language Data under the New General Da-ta Protection Regulation (GDPR)

Title Data Management Plan (DMP) for Language Data under the New General Da-ta Protection Regulation (GDPR)
Authors Pawel Kamocki, Val{'e}rie Mapelli, Khalid Choukri
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1021/
PDF https://www.aclweb.org/anthology/L18-1021
PWC https://paperswithcode.com/paper/data-management-plan-dmp-for-language-data
Repo
Framework

A Flexible and Easy-to-use Semantic Role Labeling Framework for Different Languages

Title A Flexible and Easy-to-use Semantic Role Labeling Framework for Different Languages
Authors Quynh Ngoc Thi Do, Artuur Leeuwenberg, Geert Heyman, Marie-Francine Moens
Abstract This paper presents a flexible and open source framework for deep semantic role labeling. We aim at facilitating easy exploration of model structures for multiple languages with different characteristics. It provides flexibility in its model construction in terms of word representation, sequence representation, output modeling, and inference styles and comes with clear output visualization. The framework is available under the Apache 2.0 license.
Tasks Feature Engineering, Semantic Role Labeling
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-2035/
PDF https://www.aclweb.org/anthology/C18-2035
PWC https://paperswithcode.com/paper/a-flexible-and-easy-to-use-semantic-role
Repo
Framework

Frame Semantics across Languages: Towards a Multilingual FrameNet

Title Frame Semantics across Languages: Towards a Multilingual FrameNet
Authors Collin Baker, Michael Ellsworth, Miriam R. L. Petruck, Swabha Swayamdipta
Abstract
Tasks Question Answering, Semantic Parsing, Semantic Role Labeling, Structured Prediction
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-3003/
PDF https://www.aclweb.org/anthology/C18-3003
PWC https://paperswithcode.com/paper/frame-semantics-across-languages-towards-a
Repo
Framework

Topological map construction and scene recognition for vehicle localization

Title Topological map construction and scene recognition for vehicle localization
Authors Huei-Yung Lin
Abstract This paper presents a vehicle localization method to assist vehicle navigation based on topological map construction and scene recognition. A topological map is constructed using omni-directional image sequences, and the node information of the topological map is used for place recognition and derivation of vehicle location. In topological map construction and scene change detection, we utilize the Extended-HCT method for semantic description and feature extraction. Content-based and feature-based image retrieval approaches are adopted for place recognition and vehicle localization on the real scene image dataset. The proposed technique is able to construct a real-time image retrieval system for navigation assistance and validate the correctness of the route. Experiments are carried out in both the indoor and outdoor environments using real world images.
Tasks Image Retrieval, Scene Recognition
Published 2018-01-01
URL https://link.springer.com/article/10.1007%2Fs10514-017-9638-9#Sec2
PDF https://link.springer.com/article/10.1007%2Fs10514-017-9638-9#Sec2
PWC https://paperswithcode.com/paper/topological-map-construction-and-scene
Repo
Framework

A Multi- versus a Single-classifier Approach for the Identification of Modality in the Portuguese Language

Title A Multi- versus a Single-classifier Approach for the Identification of Modality in the Portuguese Language
Authors Jo{~a}o Sequeira, Teresa Gon{\c{c}}alves, Paulo Quaresma, Am{'a}lia Mendes, Iris Hendrickx
Abstract
Tasks Opinion Mining, Sentiment Analysis, Text Classification, Word Sense Disambiguation
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1161/
PDF https://www.aclweb.org/anthology/L18-1161
PWC https://paperswithcode.com/paper/a-multi-versus-a-single-classifier-approach
Repo
Framework

What do RNN Language Models Learn about Filler–Gap Dependencies?

Title What do RNN Language Models Learn about Filler–Gap Dependencies?
Authors Ethan Wilcox, Roger Levy, Takashi Morita, Richard Futrell
Abstract RNN language models have achieved state-of-the-art perplexity results and have proven useful in a suite of NLP tasks, but it is as yet unclear what syntactic generalizations they learn. Here we investigate whether state-of-the-art RNN language models represent long-distance \textbf{filler{–}gap dependencies} and constraints on them. Examining RNN behavior on experimentally controlled sentences designed to expose filler{–}gap dependencies, we show that RNNs can represent the relationship in multiple syntactic positions and over large spans of text. Furthermore, we show that RNNs learn a subset of the known restrictions on filler{–}gap dependencies, known as \textbf{island constraints}: RNNs show evidence for wh-islands, adjunct islands, and complex NP islands. These studies demonstrates that state-of-the-art RNN models are able to learn and generalize about empty syntactic positions.
Tasks Language Modelling, Machine Translation
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-5423/
PDF https://www.aclweb.org/anthology/W18-5423
PWC https://paperswithcode.com/paper/what-do-rnn-language-models-learn-about
Repo
Framework

Temporally Grounding Natural Sentence in Video

Title Temporally Grounding Natural Sentence in Video
Authors Jingyuan Chen, Xinpeng Chen, Lin Ma, Zequn Jie, Tat-Seng Chua
Abstract We introduce an effective and efficient method that grounds (i.e., localizes) natural sentences in long, untrimmed video sequences. Specifically, a novel Temporal GroundNet (TGN) is proposed to temporally capture the evolving fine-grained frame-by-word interactions between video and sentence. TGN sequentially scores a set of temporal candidates ended at each frame based on the exploited frame-by-word interactions, and finally grounds the segment corresponding to the sentence. Unlike traditional methods treating the overlapping segments separately in a sliding window fashion, TGN aggregates the historical information and generates the final grounding result in one single pass. We extensively evaluate our proposed TGN on three public datasets with significant improvements over the state-of-the-arts. We further show the consistent effectiveness and efficiency of TGN through an ablation study and a runtime test.
Tasks Video Captioning
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1015/
PDF https://www.aclweb.org/anthology/D18-1015
PWC https://paperswithcode.com/paper/temporally-grounding-natural-sentence-in
Repo
Framework

Construction of the Corpus of Everyday Japanese Conversation: An Interim Report

Title Construction of the Corpus of Everyday Japanese Conversation: An Interim Report
Authors Hanae Koiso, Yasuharu Den, Yuriko Iseki, Wakako Kashino, Yoshiko Kawabata, Ken{'}ya Nishikawa, Yayoi Tanaka, Yasuyuki Usuda
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1672/
PDF https://www.aclweb.org/anthology/L18-1672
PWC https://paperswithcode.com/paper/construction-of-the-corpus-of-everyday
Repo
Framework

Toward Bayesian Synchronous Tree Substitution Grammars for Sentence Planning

Title Toward Bayesian Synchronous Tree Substitution Grammars for Sentence Planning
Authors David M. Howcroft, Dietrich Klakow, Vera Demberg
Abstract Developing conventional natural language generation systems requires extensive attention from human experts in order to craft complex sets of sentence planning rules. We propose a Bayesian nonparametric approach to learn sentence planning rules by inducing synchronous tree substitution grammars for pairs of text plans and morphosyntactically-specified dependency trees. Our system is able to learn rules which can be used to generate novel texts after training on small datasets.
Tasks Text Generation
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-6546/
PDF https://www.aclweb.org/anthology/W18-6546
PWC https://paperswithcode.com/paper/toward-bayesian-synchronous-tree-substitution
Repo
Framework

Generating E-Commerce Product Titles and Predicting their Quality

Title Generating E-Commerce Product Titles and Predicting their Quality
Authors Jos{'e} G. Camargo de Souza, Michael Kozielski, Prashant Mathur, Ernie Chang, Marco Guerini, Matteo Negri, Marco Turchi, Evgeny Matusov
Abstract E-commerce platforms present products using titles that summarize product information. These titles cannot be created by hand, therefore an algorithmic solution is required. The task of automatically generating these titles given noisy user provided titles is one way to achieve the goal. The setting requires the generation process to be fast and the generated title to be both human-readable and concise. Furthermore, we need to understand if such generated titles are usable. As such, we propose approaches that (i) automatically generate product titles, (ii) predict their quality. Our approach scales to millions of products and both automatic and human evaluations performed on real-world data indicate our approaches are effective and applicable to existing e-commerce scenarios.
Tasks Text Generation
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-6530/
PDF https://www.aclweb.org/anthology/W18-6530
PWC https://paperswithcode.com/paper/generating-e-commerce-product-titles-and
Repo
Framework
comments powered by Disqus