2021
Mahsa Shafaei Yigeng Zhang, Fabio Gonzalez
From None to Severe: Predicting Severity in Movie Scripts Journal Article
In: 2021.
Abstract | Links | BibTeX | Tags: Multitask
@article{arXivpreprintarXiv:2109.09276,
title = {From None to Severe: Predicting Severity in Movie Scripts},
author = {Yigeng Zhang, Mahsa Shafaei, Fabio Gonzalez, Thamar Solorio
},
url = {https://arxiv.org/pdf/2109.09276.pdf},
year = {2021},
date = {2021-09-20},
abstract = {In this paper, we introduce the task of predicting severity of age-restricted aspects of movie content based solely on the dialogue script. We first investigate categorizing the ordinal severity of movies on 5 aspects: Sex, Violence, Profanity, Substance consumption, and Frightening scenes. The problem is handled using a siamese network-based multitask framework which concurrently improves the interpretability of the predictions. The experimental results show that our method outperforms the previous state-of-the-art model and provides useful information to interpret model predictions. The proposed dataset and source code are publicly available at our GitHub repository.},
keywords = {Multitask},
pubstate = {published},
tppubtype = {article}
}
In this paper, we introduce the task of predicting severity of age-restricted aspects of movie content based solely on the dialogue script. We first investigate categorizing the ordinal severity of movies on 5 aspects: Sex, Violence, Profanity, Substance consumption, and Frightening scenes. The problem is handled using a siamese network-based multitask framework which concurrently improves the interpretability of the predictions. The experimental results show that our method outperforms the previous state-of-the-art model and provides useful information to interpret model predictions. The proposed dataset and source code are publicly available at our GitHub repository.
2019
Maharjan, Suraj; Mave, Deepthi; Shrestha, Prasha; Montes, Manuel; Gonzalez, Fabio A; Solorio, Thamar
Jointly Learning Author and Annotated Character N-gram Embeddings: A Case Study in Literary Text Conference
In Proceedings of the 2019 Conference on Recent Advances in Natural Language Processing (RANLP), ACL, Varna, Bulgaria, 2019.
Abstract | Links | BibTeX | Tags: Authorship Attribution, Book Likability Prediction, Multitask, Neural Language Model, Transfer learning
@conference{Maharjan2019,
title = {Jointly Learning Author and Annotated Character N-gram Embeddings: A Case Study in Literary Text},
author = {Suraj Maharjan and Deepthi Mave and Prasha Shrestha and Manuel Montes and Fabio A Gonzalez and Thamar Solorio},
url = {https://www.aclweb.org/anthology/R19-1080/},
year = {2019},
date = {2019-09-02},
booktitle = {In Proceedings of the 2019 Conference on Recent Advances in Natural Language Processing (RANLP)},
pages = {684-692},
publisher = {ACL},
address = {Varna, Bulgaria},
abstract = {An author's way of presenting a story through his/her writing style has a great impact on whether the story will be liked by readers or not. In this paper, we learn representations for authors of literary texts together with representations for character n-grams annotated with their functional roles. We train a neural character n-gram based language model using an external corpus of literary texts and transfer learned representations for use in downstream tasks. We show that augmenting the knowledge from external works of authors produces results competitive with other style-based methods for book likability prediction, genre classification, and authorship attribution.},
keywords = {Authorship Attribution, Book Likability Prediction, Multitask, Neural Language Model, Transfer learning},
pubstate = {published},
tppubtype = {conference}
}
An author’s way of presenting a story through his/her writing style has a great impact on whether the story will be liked by readers or not. In this paper, we learn representations for authors of literary texts together with representations for character n-grams annotated with their functional roles. We train a neural character n-gram based language model using an external corpus of literary texts and transfer learned representations for use in downstream tasks. We show that augmenting the knowledge from external works of authors produces results competitive with other style-based methods for book likability prediction, genre classification, and authorship attribution.
2018
Maharjan, Suraj; Montes, Manuel; Gonzalez, Fabio A.; Solorio, Thamar
A Genre-Aware Attention Model to Improve the Likability Prediction of Books Proceeding
In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2018.
Abstract | Links | BibTeX | Tags: Genre-Aware Attention Model, Multitask
@proceedings{Maharjan2018b,
title = {A Genre-Aware Attention Model to Improve the Likability Prediction of Books},
author = {Suraj Maharjan and Manuel Montes and Fabio A. Gonzalez and Thamar Solorio},
url = {http://aclweb.org/anthology/D18-1375},
year = {2018},
date = {2018-11-02},
publisher = {In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
abstract = {Likability prediction of books has many uses. Readers, writers, as well as the publishing industry, can all benefit from automatic book likability prediction systems. In order to make reliable decisions, these systems need to assimilate information from different aspects of a book in a sensible way. We propose a novel multimodal neural architecture that incorporates genre supervision to assign weights to individual feature types. Our proposed method is capable of dynamically tailoring weights given to feature types based on the characteristics of each book. Our architecture achieves competitive results and even outperforms state-of-the-art for this task.},
keywords = {Genre-Aware Attention Model, Multitask},
pubstate = {published},
tppubtype = {proceedings}
}
Likability prediction of books has many uses. Readers, writers, as well as the publishing industry, can all benefit from automatic book likability prediction systems. In order to make reliable decisions, these systems need to assimilate information from different aspects of a book in a sensible way. We propose a novel multimodal neural architecture that incorporates genre supervision to assign weights to individual feature types. Our proposed method is capable of dynamically tailoring weights given to feature types based on the characteristics of each book. Our architecture achieves competitive results and even outperforms state-of-the-art for this task.
Maharjan, Suraj; Kar, Sudipta; Montes, Manuel; Gonzalez, Fabio A.; Solorio, Thamar
Letting Emotions Flow: Success Prediction by Modeling the Flow of Emotions in Books Inproceedings
In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics, New Orleans, Louisiana, 2018.
Abstract | Links | BibTeX | Tags: Attention Model, Emotion Flow, Emotion Shapes, Likability Classification, Multitask
@inproceedings{Maharjan2018,
title = {Letting Emotions Flow: Success Prediction by Modeling the Flow of Emotions in Books},
author = {Suraj Maharjan and Sudipta Kar and Manuel Montes and Fabio A. Gonzalez and Thamar Solorio},
url = {http://www.aclweb.org/anthology/N18-2042},
year = {2018},
date = {2018-06-01},
booktitle = {Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
publisher = {Association for Computational Linguistics},
address = {New Orleans, Louisiana},
abstract = {Books have the power to make us feel happiness, sadness, pain, surprise, or sorrow. An author's dexterity in the use of these emotions captivates readers and makes it difficult for them to put the book down. In this paper, we model the flow of emotions over a book using recurrent neural networks and quantify its usefulness in predicting the book's success. We obtained the best weighted F1-score of 0.690 for predicting books' success in a multitask setting (simultaneously predicting success and genre of books)},
keywords = {Attention Model, Emotion Flow, Emotion Shapes, Likability Classification, Multitask},
pubstate = {published},
tppubtype = {inproceedings}
}
Books have the power to make us feel happiness, sadness, pain, surprise, or sorrow. An author’s dexterity in the use of these emotions captivates readers and makes it difficult for them to put the book down. In this paper, we model the flow of emotions over a book using recurrent neural networks and quantify its usefulness in predicting the book’s success. We obtained the best weighted F1-score of 0.690 for predicting books’ success in a multitask setting (simultaneously predicting success and genre of books)
Aguilar, Gustavo; Monroy, A. Pastor López; Gonzalez, Fabio A.; Solorio, Thamar
Modeling Noisiness to Recognize Named Entities using Multitask Neural Networks on Social Media Inproceedings
In: for Computational Linguistics, Association (Ed.): Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics, New Orleans, Louisiana, 2018.
Abstract | Links | BibTeX | Tags: CRF, Multitask, NER, Phonetics, Phonology, Social Media
@inproceedings{gaguilar2018,
title = {Modeling Noisiness to Recognize Named Entities using Multitask Neural Networks on Social Media},
author = {Gustavo Aguilar and A. Pastor López Monroy and Fabio A. Gonzalez and Thamar Solorio},
editor = {Association for Computational Linguistics },
url = {http://www.aclweb.org/anthology/N18-1127},
year = {2018},
date = {2018-06-01},
booktitle = {Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
publisher = {Association for Computational Linguistics},
address = {New Orleans, Louisiana},
abstract = {Recognizing named entities in a document is a key task in many NLP applications. Although current state-of-the-art approaches to this task reach a high performance on clean text (e.g. newswire genres), those algorithms dramatically degrade when they are moved to noisy environments such as social media domains. We present two systems that address the challenges of processing social media data using character-level phonetics and phonology, word embeddings, and Part-of-Speech tags as features. The first model is a multitask end-to-end Bidirectional Long Short-Term Memory (BLSTM)-Conditional Random Field (CRF) network whose output layer contains two CRF classifiers. The second model uses a multitask BLSTM network as feature extractor that transfers the learning to a CRF classifier for the final prediction. Our systems outperform the current F1 scores from state-of-the-art on the Workshop on Noisy User-generated Text 2017 dataset by 2.45% and 3.69%, establishing a more suitable approach for social media environments. },
keywords = {CRF, Multitask, NER, Phonetics, Phonology, Social Media},
pubstate = {published},
tppubtype = {inproceedings}
}
Recognizing named entities in a document is a key task in many NLP applications. Although current state-of-the-art approaches to this task reach a high performance on clean text (e.g. newswire genres), those algorithms dramatically degrade when they are moved to noisy environments such as social media domains. We present two systems that address the challenges of processing social media data using character-level phonetics and phonology, word embeddings, and Part-of-Speech tags as features. The first model is a multitask end-to-end Bidirectional Long Short-Term Memory (BLSTM)-Conditional Random Field (CRF) network whose output layer contains two CRF classifiers. The second model uses a multitask BLSTM network as feature extractor that transfers the learning to a CRF classifier for the final prediction. Our systems outperform the current F1 scores from state-of-the-art on the Workshop on Noisy User-generated Text 2017 dataset by 2.45% and 3.69%, establishing a more suitable approach for social media environments.
2017
Suraj Maharjan Gustavo Aguilar, A. Pastor López Monroy
A Multi-task Approach for Named Entity Recognition on Social Media Data Inproceedings
In: 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.
Maharjan, Suraj; Arevalo, John; Montes, Manuel; Gonzalez, Fabio A.; Solorio, Thamar
A Multi-task Approach to Predict Likability of Books Inproceedings
In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pp. 1217–1227, Association for Computational Linguistics, Valencia, Spain, 2017.
Links | BibTeX | Tags: Multitask, Neural Networks
@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}
}