Filters








51,521 Hits in 4.8 sec

Adapting Sequence to Sequence models for Text Normalization in Social Media [article]

Ismini Lourentzou, Kabir Manghnani, ChengXiang Zhai
2019 arXiv   pre-print
pre-processing step for NLP applications to adapt to noisy text in social media.  ...  We argue that processing contextual information is crucial for this task and introduce a social media text normalization hybrid word-character attention-based encoder-decoder model that can serve as a  ...  The authors would like to thank the anonymous reviewers for their helpful comments. This material is based upon work supported by the National Science Foundation under Grant No. 1801652.  ... 
arXiv:1904.06100v1 fatcat:t73oet2rrnb2tpor475ob4zuua

Sequence-to-Sequence Lexical Normalization with Multilingual Transformers [article]

Ana-Maria Bucur, Adrian Cosma, Liviu P. Dinu
2021 arXiv   pre-print
operating on raw, unprocessed, social media text.  ...  One way to resolve this issue is through lexical normalization, which is the process of transforming non-standard text, usually from social media, into a more standardized form.  ...  Acknowledgments We would like to thank the reviewers for the insightful feedback provided. This research was partially supported by Blog Alchemy Limited.  ... 
arXiv:2110.02869v3 fatcat:sgbfb6uns5fstp475iak2n37vm

Parser Adaptation for Social Media by Integrating Normalization

Rob van der Goot, Gertjan van Noord
2017 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)  
This work explores normalization for parser adaptation. Traditionally, normalization is used as separate pre-processing step.  ...  This way, multiple normalization candidates can be leveraged, which improves parsing performance on social media.  ...  Furthermore we would like to thank Jennifer Foster for sharing the Twitter treebank. This work is part of the Parsing Algorithms for Uncertain Input project, funded by the Nuance Foundation.  ... 
doi:10.18653/v1/p17-2078 dblp:conf/acl/GootN17 fatcat:baeegqnebbb25hevyggydlar54

A POS Tagger for Social Media Texts Trained on Web Comments

Melanie Neunerdt, Michael Reyer, Rudolf Mathar
2013 POLIBITS Research Journal on Computer Science and Computer Engineering With Applications  
Hence, applying common taggers to such texts results in performance degradation. In this paper, we present extensions to a basic Markov model tagger for the annotation of social media texts.  ...  Applying our approach improves the tagging accuracy for social media texts considerably, when we train our model on a combination of annotated texts from newspapers and Web comments.  ...  We would like to thank Phillip Vaßen for his contribution.  ... 
doi:10.17562/pb-48-8 fatcat:6qiprirowncxfkmyb2rjc7ea3e

Neural Text Normalization for Turkish Social Media

Sinan Goker, Burcu Can
2018 2018 3rd International Conference on Computer Science and Engineering (UBMK)  
In this study, two neural approaches are applied for Turkish text normalization task: Contextual Normalization approach using distributed representations of words and Sequence-to-Sequence Normalization  ...  Social media has become a rich data source for natural language processing tasks with its worldwide use; however, it is hard to process social media data directly in language studies due to its unformatted  ...  for text normalization of Turkish social media.  ... 
doi:10.1109/ubmk.2018.8566406 fatcat:p6uyax4tvnhwhbvjclssxwhj34

Adapting Deep Learning Methods for Mental Health Prediction on Social Media

Ivan Sekulic, Michael Strube
2019 Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)  
Text analysis of rich resources, like social media, can contribute to deeper understanding of illnesses and provide means for their early detection.  ...  We tackle a challenge of detecting social media users' mental status through deep learning-based models, moving away from traditional approaches to the task.  ...  A social media user can be modeled as collection of their posts, so we look at neural models for large-scale text classification.  ... 
doi:10.18653/v1/d19-5542 dblp:conf/aclnut/SekulicS19 fatcat:ot4h5m536jgwrkhk5ejqw6fdkq

Unsupervised Domain Adaptation of Contextualized Embeddings for Sequence Labeling

Xiaochuang Han, Jacob Eisenstein
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
To address this scenario, we propose domain-adaptive finetuning, in which the contextualized embeddings are adapted by masked language modeling on text from the target domain.  ...  We conclude that domainadaptive fine-tuning offers a simple and effective approach for the unsupervised adaptation of sequence labeling to difficult new domains. 1  ...  Thanks to the anonymous reviewers and to Ross Girshick, Omer Levy, Michael Lewis, Yuval Pinter, Luke Zettlemoyer, and the Georgia Tech Computational Linguistics Lab for helpful discussions of this work  ... 
doi:10.18653/v1/d19-1433 dblp:conf/emnlp/HanE19 fatcat:ph6bwyoz3zab7bawpnfexhvob4

Unsupervised Domain Adaptation of Contextualized Embeddings for Sequence Labeling [article]

Xiaochuang Han, Jacob Eisenstein
2019 arXiv   pre-print
To address this scenario, we propose domain-adaptive fine-tuning, in which the contextualized embeddings are adapted by masked language modeling on text from the target domain.  ...  We conclude that domain-adaptive fine-tuning offers a simple and effective approach for the unsupervised adaptation of sequence labeling to difficult new domains.  ...  Thanks to the anonymous reviewers and to Ross Girshick, Omer Levy, Michael Lewis, Yuval Pinter, Luke Zettlemoyer, and the Georgia Tech Computational Linguistics Lab for helpful discussions of this work  ... 
arXiv:1904.02817v2 fatcat:p7uxula2lnhdteztqfzzw4dysy

Noisy Uyghur Text Normalization

Osman Tursun, Ruket Cakici
2017 Proceedings of the 3rd Workshop on Noisy User-generated Text  
However, a non-negligible part of Uyghur text appearing in social media is unsystematically written with the Latin alphabet, and it continues to increase in size.  ...  To this purpose, in this work we propose and compare the noisy channel model and the neural encoderdecoder model as normalizing methods.  ...  Acknowledgement We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Tesla K40 GPU used for this research.  ... 
doi:10.18653/v1/w17-4412 dblp:conf/aclnut/TursunC17 fatcat:4an7o3c4endlxmaizr3pccxdqy

A CRF Based POS Tagger for Code-mixed Indian Social Media Text [article]

Kamal Sarkar
2016 arXiv   pre-print
tagging for codemixed Indian social media text, held in conjunction with the 2016 International Conference on Natural Language Processing, IIT(BHU), India.  ...  In this work, we describe a conditional random fields (CRF) based system for Part-Of- Speech (POS) tagging of code-mixed Indian social media text as part of our participation in the tool contest on POS  ...  Automatic analysis of non-standard texts like social media texts which differ from standard texts in the word usage and their grammatical structure creates the need for the adaption of POS tagging methods  ... 
arXiv:1612.07956v1 fatcat:wncje6jitzcebeu4axn56qadfq

Fake News Detection using Bi-directional LSTM-Recurrent Neural Network

Pritika Bahad, Preeti Saxena, Raj Kamal
2019 Procedia Computer Science  
Media plays a vital role in the public dissemination of information about events. The rapid development of the Internet allows a quick spread of information through social networks or websites.  ...  Abstract Media plays a vital role in the public dissemination of information about events.  ...  There are several approaches to handle the problem of misinformation on social media.  ... 
doi:10.1016/j.procs.2020.01.072 fatcat:f5ybuielpvf2xjmuhlldv5edma

Steganographic visual story with mutual-perceived joint attention

Yanyang Guo, Hanzhou Wu, Xinpeng Zhang
2021 EURASIP Journal on Image and Video Processing  
AbstractSocial media plays an increasingly important role in providing information and social support to users.  ...  In this paper, we design a steganographic visual stories generation model that enables users to automatically post stego status on social media without any direct user intervention and use the mutual-perceived  ...  for modeling image features vector sequences.  ... 
doi:10.1186/s13640-020-00543-1 fatcat:q736logtyrg2lajsec5tp6gslm

Part-of-Speech Tagging for Code-mixed Indian Social Media Text at ICON 2015 [article]

Kamal Sarkar
2016 arXiv   pre-print
This paper discusses the experiments carried out by us at Jadavpur University as part of the participation in ICON 2015 task: POS Tagging for Code-mixed Indian Social Media Text.  ...  Our system has been trained and tested on the datasets released for ICON 2015 shared task: POS Tagging For Code-mixed Indian Social Media Text.  ...  This creates the need for adapting NLP methods to analyzing social media text and in particular, for the adaption of POS tagging methods to such text types.  ... 
arXiv:1601.01195v1 fatcat:cc5vi3o5x5byvjyuebu656ollu

Medical Social Media Text Classification Integrating Consumer Health Terminology

Kan Liu, Lu Chen
2019 IEEE Access  
However, current methods are underutilized for features including consumer health terminology in social media texts.  ...  In this paper, we proposed a medical social media text classification (MSMTC) algorithm that integrates consumer health terminology.  ...  Subsequently, researchers directly normalized the lexicon of social media texts. For example, Han et al.  ... 
doi:10.1109/access.2019.2921938 fatcat:qp6aozucnbce7ld7t2peazz2ea

Bi-Directional Recurrent Neural Ordinary Differential Equations for Social Media Text Classification [article]

Maunika Tamire, Srinivas Anumasa, P.K. Srijith
2021 arXiv   pre-print
Classification of posts in social media such as Twitter is difficult due to the noisy and short nature of texts.  ...  Sequence classification models based on recurrent neural networks (RNN) are popular for classifying posts that are sequential in nature.  ...  posts in social media.  ... 
arXiv:2112.12809v1 fatcat:aqcho23wgndprfmxanb66z5wqa
« Previous Showing results 1 — 15 out of 51,521 results