2017
|
Gustavo Aguilar Suraj Maharjan, Pastor López Monroy Thamar Solorio A A Multi-task Approach for Named Entity Recognition on Social Media Data Inproceedings Proceedings of 3rd Workshop on Noisy User-generated Text, WNUT 2017., 2017, (Ranked 1st place in the two evaluation metrics). Abstract | Links | BibTeX | Tags: CRF, Deeplearning, Multitask, NER @inproceedings{aguilar-EtAl:2017:WNUT,
title = {A Multi-task Approach for Named Entity Recognition on Social Media Data},
author = {Gustavo Aguilar, Suraj Maharjan, A. Pastor López Monroy, Thamar Solorio},
url = {http://www.aclweb.org/anthology/W17-4419},
year = {2017},
date = {2017-09-07},
publisher = {Proceedings of 3rd Workshop on Noisy User-generated Text, WNUT 2017.},
abstract = {Named Entity Recognition for social media data is challenging because of its inherent noisiness. In addition to improper grammatical structures, it contains spelling inconsistencies and numerous informal abbreviations. We propose a novel multi-task approach by employing a more general secondary task of Named Entity (NE) segmentation together with the primary task of fine-grained NE categorization. The multi-task neural network architecture learns higher order feature representations from word and character sequences along with basic Part-of-Speech tags and gazetteer information. This neural network acts as a feature extractor to feed a Conditional Random Fields classifier. We were able to obtain the first position in the 3rd Workshop on Noisy User-generated Text (WNUT-2017) with a 41.86% entity F1-score and a 40.24% surface F1-score.},
note = {Ranked 1st place in the two evaluation metrics},
keywords = {CRF, Deeplearning, Multitask, NER},
pubstate = {published},
tppubtype = {inproceedings}
}
Named Entity Recognition for social media data is challenging because of its inherent noisiness. In addition to improper grammatical structures, it contains spelling inconsistencies and numerous informal abbreviations. We propose a novel multi-task approach by employing a more general secondary task of Named Entity (NE) segmentation together with the primary task of fine-grained NE categorization. The multi-task neural network architecture learns higher order feature representations from word and character sequences along with basic Part-of-Speech tags and gazetteer information. This neural network acts as a feature extractor to feed a Conditional Random Fields classifier. We were able to obtain the first position in the 3rd Workshop on Noisy User-generated Text (WNUT-2017) with a 41.86% entity F1-score and a 40.24% surface F1-score. |
2016
|
Samih, Younes; Maharjan, Suraj; Attia, Mohammed; Kallmeyer, Laura; Solorio, Thamar Multilingual Code-switching Identification via LSTM Recurrent Neural Networks Proceeding Proceedings of the Second Workshop on Computational Approaches to Code Switching; EMNLP, 2016. Links | BibTeX | Tags: Code-Switching, CRF, Deeplearning, Neural Networks @proceedings{Samih2016,
title = {Multilingual Code-switching Identification via LSTM Recurrent Neural Networks},
author = {Younes Samih and Suraj Maharjan and Mohammed Attia and Laura Kallmeyer and Thamar Solorio},
url = {http://www.aclweb.org/anthology/W/W16/W16-5806.pdf},
year = {2016},
date = {2016-10-31},
publisher = {Proceedings of the Second Workshop on Computational Approaches to Code Switching; EMNLP},
keywords = {Code-Switching, CRF, Deeplearning, Neural Networks},
pubstate = {published},
tppubtype = {proceedings}
}
|