Publications

@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}

}

@inproceedings{safisamghabadi-EtAl:2017:ALW1,

title = {Detecting Nastiness in Social Media},

author = {Niloofar S. Samghabadi, Suraj Maharjan, Alan Sprague, Raquel D. Sprague, Thamar Solorio},

url = {http://aclweb.org/anthology/W17-3010},

year  = {2017},

date = {2017-08-04},

booktitle = {ALW1@ACL2017},

keywords = {Abusive Language detection},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Kar2017,

title = {RiTUAL-UH at SemEval-2017 Task 5: Sentiment Analysis on Financial Data Using Neural Networks},

author = {Sudipta Kar and Suraj Maharjan and Thamar Solorio},

url = {http://www.aclweb.org/anthology/S17-2150},

year  = {2017},

date = {2017-08-03},

publisher = {Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)},

abstract = {In this paper, we present our systems for the “SemEval-2017 Task-5 on FineGrained Sentiment Analysis on Financial Microblogs and News”. In our system, we combined hand-engineered lexical, sentiment and metadata features, the representations learned from Convolutional Neural Networks (CNN) and Bidirectional Gated Recurrent Unit (Bi-GRU) with Attention model applied on top. With this architecture, we obtained weighted cosine similarity scores of 72.34% and 74.37% for subtask-1 and subtask-2, respectively. Using the official scoring system, our system ranked the second place for subtask-2 and eighth place for the subtask-1. It ranked first for both of the subtasks by the scores achieved by an alternate scoring system.

.},

note = {Ranked 2nd for Subtask 2. With alternate scoring, ranked 1st in both subtask.},

keywords = {CNN, Neural Networks, Sentiment analysis},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Maharjan2017,

title = {A Multi-task Approach to Predict Likability of Books},

author = {Suraj Maharjan and John Arevalo and Manuel Montes and Fabio A. Gonzalez and Thamar Solorio},

url = {https://www.aclweb.org/anthology/E/E17/E17-1114.pdf},

year  = {2017},

date = {2017-04-03},

booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers},

pages = {1217--1227},

publisher = {Association for Computational Linguistics},

address = {Valencia, Spain},

keywords = {Multitask, Neural Networks},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Shrestha2017,

title = {Convolutional Neural Networks for Authorship Attribution of Short Texts},

author = { Prasha Shrestha and Sebastian Sierra and Fabio Gonzalez and Manuel Montes and Paolo Rosso and Thamar Solorio},

url = {https://www.aclweb.org/anthology/E/E17/E17-2106.pdf},

year  = {2017},

date = {2017-04-03},

booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers},

pages = {669--674},

publisher = {Association for Computational Linguistics},

address = {Valencia, Spain},

keywords = {Authorship Attribution, CNN},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Franco-Salvador2016,

title = {UH-PRHLT at SemEval-2016 Task 3: Combining Lexical and Semantic-based Features for Community Question Answering},

author = {Marc Franco-Salvador and Sudipta Kar and Thamar Solorio and Paolo Rosso},

url = {https://aclweb.org/anthology/S/S16/S16-1126.pdf},

year  = {2016},

date = {2016-06-16},

booktitle = {Proceedings of SemEval-2016},

pages = {814-821},

publisher = {Association for Computational Linguistics},

address = {San Diego, California},

keywords = {Question Answering, Text Classification},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Sadeque-EtAl:2015:LOUHI,

title = {Predicting Continued Participation in Online Health Forums},

author = {Farig Sadeque and Thamar Solorio and Ted Pedersen and Prasha Shrestha and Steven Bethard},

url = {https://aclweb.org/anthology/W/W15/W15-2602.pdf},

year  = {2015},

date = {2015-09-23},

booktitle = {Proceedings of the 6th International Workshop on Health Text Mining and Information Analysis (Louhi)},

pages = {15-20},

publisher = {Association for Computational Linguistics},

address = {Lisboa, Portugal},

keywords = {health applications},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{maharjan-EtAl:2015:LAW,

title = {Developing Language-tagged Corpora for Code-switching Tweets},

author = {Suraj Maharjan and Elizabeth Blair and Steven Bethard and Thamar Solorio},

url = {http://www.aclweb.org/anthology/W15-1608},

year  = {2015},

date = {2015-06-05},

booktitle = {Proceedings of The 9th Linguistic Annotation Workshop},

pages = {72--84},

publisher = {Association for Computational Linguistics},

address = {Denver, Colorado, USA},

keywords = {Code-Switching},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{SapkotaEtAl:14,

title = {Cross-Topic Authorship Attribution: Will Out-Of-Topic Data Help?},

author = { Upendra Sapkota and Thamar Solorio and Manuel Montes and Steven Bethard and Paolo Rosso},

url = {http://www.aclweb.org/anthology/C14-1116},

year  = {2014},

date = {2014-08-01},

booktitle = {Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers},

pages = {1228--1237},

publisher = {Dublin City University and Association for Computational Linguistics},

address = {Dublin, Ireland},

keywords = {Authorship Attribution},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{SolorioEtAl:14b,

title = {Sockpuppet Detection in Wikipedia: A Corpus of Real-World Deceptive Writing for Linking Identities},

author = { Thamar Solorio and Ragib Hasan and Mainul Mizan},

url = {http://www.lrec-conf.org/proceedings/lrec2014/pdf/1007_Paper.pdf},

year  = {2014},

date = {2014-05-01},

booktitle = {The 9th edition of the Language Resources and Evaluation Conference (LREC 2014)},

pages = {26--31},

publisher = {European Language Resources Association (ELRA)},

address = {Reykjavik, Iceland},

keywords = {Authorship Attribution},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{RamirezEtAl:13,

title = {Exploring word class n-grams to measure language development in children},

author = { Gabriela Ramírez-de-la-Rosa and Thamar Solorio and Manuel Montes-y-Gómez and Yang Liu and Aquiles Iglesias and Lisa Bedore and Elizabeth Peña},

url = {http://www.aclweb.org/anthology/W13-1911},

year  = {2013},

date = {2013-08-01},

booktitle = {Proceedings of the 2013 Workshop on Biomedical Natural Language Processing},

pages = {89--97},

publisher = {ACL},

address = {Sofia, Bulgaria},

keywords = {Clinical Applications},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{HassanaliEtAl:13b,

title = {Using Latent Dirichlet Allocation for Child Narrative Analysis},

author = { Khairun-nisa Hassanali and Yang Liu and Thamar Solorio},

url = {http://www.aclweb.org/anthology/W13-1914},

year  = {2013},

date = {2013-08-01},

booktitle = {Proceedings of the 2013 Workshop on Biomedical Natural Language Processing},

pages = {111--115},

publisher = {ACL},

address = {Sofia, Bulgaria},

keywords = {Clinical Applications},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{GyawaliEtAl:13,

title = {Native Language Identification: a Simple n-gram Based Approach},

author = { Binod Gyawali and Gabriela Ramirez-de-la-Rosa and Thamar Solorio},

url = {http://www.aclweb.org/anthology/W13-1729},

year  = {2013},

date = {2013-06-01},

booktitle = {Proceedings of the Eighth Workshop on Innovative Use of NLP for Building Educational Applications},

pages = {224--231},

publisher = {ACL},

address = {Atlanta, Georgia},

keywords = {Information Extraction, Profiling},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{SolorioEtAl:13,

title = {A Case Study of Sockpuppet Detection in Wikipedia},

author = { Thamar Solorio and Ragib Hasan and Mainul Mizan},

year  = {2013},

date = {2013-06-01},

booktitle = {Workshop on Language Analysis in Social Media (LASM) at NAACL-HLT 2013},

pages = {59--68},

publisher = {ACL},

address = {Atlanta, Georgia},

keywords = {Authorship Attribution, Security},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{SapkotaEtAl:13,

title = {The use of Orthogonal Similarity Relations in the Prediction of Authorship},

author = { Upendra Sapkota and Thamar Solorio and Manuel Montes-y-Gómez and Paolo Rosso},

year  = {2013},

date = {2013-03-01},

booktitle = {Proceedings of the 14th International Conference on Intelligent Text Processing and Computational Linguistics, CICLing-2013},

pages = {463--475},

publisher = {, % note = (acceptance rate 24.6,%)},

address = {Samos, Greece},

keywords = {Authorship Attribution},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{OsborneEtAl:13,

title = {Evaluation of freely available open source software for clinical concept recognition},

author = { John David Osborne and Binod Gyawali and Thamar Solorio},

year  = {2013},

date = {2013-01-01},

booktitle = {Notebook for ShARe/CLEF eHealth Evaluation Lab at CLEF 2013},

keywords = {Clinical Applications, Information Extraction},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ShresthaAndSolorio:13,

title = {Using a Variety of n-Grams for the Detection of Different Kinds of Plagiarism},

author = { Prasha Shrestha and Thamar Solorio},

url = {http://ceur-ws.org/Vol-1179/CLEF2013wn-PAN-ShresthaEt2013.pdf},

year  = {2013},

date = {2013-01-01},

booktitle = {Notebook for PAN at CLEF 2013},

keywords = {plagiarism, shared task},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{SapkotaEtAl:13b,

title = {Automatic Author Profiling for English and Spanish Text},

author = { Upendra Sapkota and Thamar Solorio and Manuel Montes-y-Gómez and Gabriela Ramírez-de-la-Rosa},

year  = {2013},

date = {2013-01-01},

booktitle = {Notebook for PAN at CLEF 2013},

keywords = {Profiling, Security},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{SapkotaAndSolorio:12,

title = {Sub-profiling by linguistic dimensions to solve the authorship attribution task},

author = { Upendra Sapkota and Thamar Solorio},

year  = {2012},

date = {2012-09-01},

booktitle = {Notebook for PAN at CLEF 2012},

address = {Rome, Italy},

keywords = {Authorship Attribution},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{BogdanovaEtAl:12b,

title = {On the Impact of Sentiment and Emotion Based Features in Detecting Online Sexual Predators},

author = { Daria Bogdanova and Paolo Rosso and Thamar Solorio},

year  = {2012},

date = {2012-07-01},

booktitle = {Proceedings of the ACL 2012 3rd Workshop on Computational Approaches to Subjectivity and Sentiment Analysis (WASSA)},

pages = {110--118},

address = {Jeju, Republic of Korea},

organization = {ACL},

keywords = {Cyberpedophilia, Security},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{GyawaliEtAl:12a,

title = {Grading the Quality of Medical Evidence},

author = { Binod Gyawali and Thamar Solorio and Yassine Benajiba},

url = {http://www.aclweb.org/anthology/W12-2422},

year  = {2012},

date = {2012-06-01},

booktitle = {2012 Workshop on Biomedical Natural Language Processing (BIONLP 2012)},

pages = {176--184},

address = {Montréal, Canada},

organization = {ACL},

keywords = {health applications},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{GyawaliEtAl:12b,

title = {UABCoRAL: A Preliminary study for Resolving the Scope of Negation},

author = { Binod Gyawali and Thamar Solorio},

year  = {2012},

date = {2012-06-01},

booktitle = {*SEM: 1st Joint Conference on Lexical and Computational Semantics},

pages = {275--281},

address = {Montréal, Canada},

organization = {ACL},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{BogdanovaEtAl:12,

title = {Modelling Fixated Discourse in Chats with Cyberpedophiles},

author = { Daria Bogdanova and Paolo Rosso and Thamar Solorio},

year  = {2012},

date = {2012-04-01},

booktitle = {EACL 2012 Workshop on Computational Approaches to Deception Detection},

pages = {86--90},

address = {Avignon, France},

organization = {ACL},

keywords = {Cyberpedophilia, Security},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{HassanaliEtAl:12,

title = {Coherence in Child Language Narratives: A Case Study of Annotation and Automatic Prediction of Coherence},

author = { Khairun-nisa Hassanali and Yang Liu and Thamar Solorio},

year  = {2012},

date = {2012-01-01},

booktitle = {Proceedings of 3rd Workshop on Child, Computer and Interaction (WOCCI 2012)},

keywords = {Clinical Applications},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{HassanaliEtAl:12b,

title = {Evaluating NLP Features for Automatic Prediction of Language Impairment Using Child Speech Transcripts},

author = { Khairun-nisa Hassanali and Yang Liu and Thamar Solorio},

year  = {2012},

date = {2012-01-01},

booktitle = {Proceedings of INTERSPEECH 2012},

keywords = {Clinical Applications},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{EscalanteEtAl:11b,

title = {Weighted Profile Intersection Measure for Profile-based Authorship Attribution},

author = { Hugo Jair Escalante and Manuel Montes-y-Gómez and Thamar Solorio},

year  = {2011},

date = {2011-11-01},

booktitle = {10th Mexican International Conference on Artificial Intelligence},

pages = {232--243},

publisher = {, %note = (acceptance rate 27.5,%)},

address = {Puebla, Mexico},

keywords = {Authorship Attribution, Security},

pubstate = {published},

tppubtype = {inproceedings}

}