Publications

@conference{CSUR,

title = {Survey on Aspect Category Detection},

author = {Siva Uday Sampreeth Chebolu, Paolo Rosso, Sudipta Kar, Thamar Solorio},

url = {https://dl.acm.org/doi/abs/10.1145/3544557},

year  = {2022},

date = {2022-01-01},

booktitle = {ACM Computing Surveys (CSUR)},

publisher = {ACM},

abstract = {In recent years, aspect category detection has become popular due to the rapid growth in customer reviews data on e-commerce and other online platforms. Aspect Category Detection, a sub-task of Aspect-Based Sentiment Analysis, categorizes the reviews based on the features of a product such as a laptop’s display, or an aspect of an entity such as the restaurant’s ambiance. Various methods have been proposed to deal with such a problem. In this paper, we first introduce several datasets in the community that deal with this task and take a closer look at them by providing some exploratory analysis. Then, we review a number of representative methods for aspect category detection and classify them into two main groups: 1) supervised learning, and 2) unsupervised learning. Next, we discuss the strengths and weaknesses of different kinds of methods, which are expected to benefit both practical applications and …},

keywords = {explanatory analysis},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {Identifying Keyword Predictors in Lecture Video Screen Text},

author = {Farah Naz Chowdhury, Raga Shalini Koka, Mohammad Rajiur Rahman, Thamar Solorio, Jaspal Subhlok},

url = {http://www.videopoints.org/public/paper/Identifying_Keyword_Predictors_in_Lecture_Video_Screen_Text.pdf},

year  = {2021},

date = {2021-11-01},

booktitle = {2021 IEEE International Symposium on Multimedia (ISM)

},

pages = {281-286},

publisher = {IEEE},

abstract = {Automatic discovery of keywords for lecture video segments is an important component of advanced navigation systems for lecture videos. The suitability of a word or a short phrase to be a keyword depends on various factors, including the frequency in a segment, relative frequency in reference to the full video, font size, time on screen, and the existence in domain and language dictionaries. The research presented in this paper provides a refined understanding of how various factors contribute to predicting keywords based on logistic regression analysis. The analysis employs a real-world dataset consisting of lecture videos from Biology, Computer Science, and Chemistry, hosted on Videopoints, a lecture video management portal. Term frequency, maximum font size, and presence in a domain dictionary were identified as the most important predictors of keywords. The results provide a scientific foundation and …},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{nokey,

title = {A Human-Centered Systematic Literature Review of the Computational Approaches for Online Sexual Risk Detection},

author = {Afsaneh Razi, Seunghyun Kim, Ashwaq Alsoubai, Gianluca Stringhini, Thamar Solorio, Munmun De Choudhury, Pamela J Wisniewsk},

url = {https://stirlab.org/wp-content/uploads/Review-of-the-Computational-Approaches-for-Online-Sexual-Risk-Detection.pdf},

year  = {2021},

date = {2021-10-18},

booktitle = {Proceedings of the ACM on Human-Computer Interaction

},

journal = {Proceedings of the ACM on Human-Computer Interaction},

pages = {1-38},

publisher = {ACM},

abstract = {In the era of big data and artificial intelligence, online risk detection has become a popular research topic. From detecting online harassment to the sexual predation of youth, the state-of-the-art in computational risk detection has the potential to protect particularly vulnerable populations from online victimization. Yet, this is a high-risk, high-reward endeavor that requires a systematic and human-centered approach to synthesize disparate bodies of research across different application domains, so that we can identify best practices, potential gaps, and set a strategic research agenda for leveraging these approaches in a way that betters society. Therefore, we conducted a comprehensive literature review to analyze 73 peer-reviewed articles on computational approaches utilizing text or meta-data/multimedia for online sexual risk detection. We identified sexual grooming (75%), sex trafficking (12%), and sexual …},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{,

title = {End-to-end fine-grained neural entity recognition of patients, interventions, outcomes},

author = {Anjani Dhrangadhariya, Gustavo Aguilar, Thamar Solorio, Roger Hilfiker, Henning Müller},

url = {https://arodes.hes-so.ch/record/8949/files/Author%20postprint.pdf},

year  = {2021},

date = {2021-09-21},

urldate = {2021-09-21},

booktitle = {International Conference of the Cross-Language Evaluation Forum for European Languages},

pages = {65-77},

publisher = {Springer, Cham},

abstract = {PICO recognition is an information extraction task for detecting parts of text describing Participant (P), Intervention (I), Comparator (C), and Outcome (O) (PICO elements) in clinical trial literature. Each PICO description is further decomposed into finer semantic units. For example, in the sentence ‘The study involved 242 adult men with back pain.’, the phrase ‘242 adult men with back pain’ describes the participant, but this coarse-grained description is further divided into finer semantic units. The term ‘242’ shows “sample size” of the participants, ‘adult’ shows “age”, ‘men’ shows “sex”, and ‘back pain’ show the participant “condition”. Recognizing these fine-grained PICO entities in health literature is a challenging named-entity recognition (NER) task but it can help to fully automate systematic reviews (SR). Previous approaches concentrated on coarse-grained PICO recognition but focus on the fine-grained },

keywords = {NER},

pubstate = {published},

tppubtype = {conference}

}

@conference{(RANLP2021),

title = {A Case Study of Deep Learning-Based Multi-Modal Methods for Labeling the Presence of Questionable Content in Movie Trailers},

author = {Mahsa Shafaei, Christos Smailis, Ioannis Kakadiaris, Thamar Solorio},

url = {https://aclanthology.org/2021.ranlp-1.146.pdf},

year  = {2021},

date = {2021-09-01},

urldate = {2021-09-01},

booktitle = {Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)},

pages = {1297-1307},

abstract = {In this work, we explore different approaches to combine modalities for the problem of automated age-suitability rating of movie trailers. First, we introduce a new dataset containing videos of movie trailers in English downloaded from IMDB and YouTube, along with their corresponding age-suitability rating labels. Secondly, we propose a multi-modal deep learning pipeline addressing the movie trailer age suitability rating problem. This is the first attempt to combine video, audio, and speech information for this problem, and our experimental results show that multi-modal approaches significantly outperform the best mono and bimodal models in this task.},

keywords = {Deeplearning},

pubstate = {published},

tppubtype = {conference}

}

@conference{,

title = {PSED: A Dataset for Selecting Emphasis in Presentation Slides},

author = {Amirreza Shirani, Giai Tran, Hieu Trinh, Franck Dernoncourt, Nedim Lipka, Jose Echevarria, Thamar Solorio, Paul Asente},

url = {https://aclanthology.org/2021.findings-acl.377.pdf},

year  = {2021},

date = {2021-08-01},

urldate = {2021-08-01},

booktitle = {Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

},

pages = {4314-4320},

publisher = {ACL},

abstract = {Emphasizing words in presentation slides allows viewers to direct their gaze to focal points without reading the entire slide, retaining their attention on the speaker. Despite many studies on automatic slide generation, few have addressed helping authors choose which words to emphasize. Motivated by this, we study the problem of choosing candidates for emphasis by introducing a new dataset containing presentation slides with a wide variety of topics. We evaluated a range of state-of-the-art models on this novel dataset by organizing a shared task and inviting multiple researchers to model emphasis in slides.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@conference{-Switching,

title = {Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching},

author = {Thamar Solorio, Shuguang Chen, Alan W Black, Mona Diab, Sunayana Sitaram, Victor Soto, Emre Yilmaz, Anirudh Srinivasan},

url = {https://aclanthology.org/2021.calcs-1.0.pdf},

year  = {2021},

date = {2021-06-01},

urldate = {2021-06-01},

booktitle = {Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching},

abstract = {Bienvenidos to the proceedings of the fifth edition of the workshop on computational approaches for linguistic code-switching (CALCS-2021)! Code-switching is this very interesting phenomenon where multilingual speakers communicate by moving back and forth between the languages they speak when communicating with other multilingual speakers. Code-switching (CSW) is predominantly used in speech but since it also tends to be more prevalent in casual settings, we can observe CSW in genres like social media platforms where interactions tend to be more casual.

However interesting, our current NLP technology is lagging behind in the development of resources and methodologies that can effectively process code-switched language. This is true for even the large multilingual pretrained models such as mBERT and BART. At the same time, the growing adoption of smart devices and automated assistants that rely on speech interfaces, makes it even more pressing that our field addresses CSW language data},

keywords = {Code-Switching},

pubstate = {published},

tppubtype = {conference}

}

@conference{Chen2021,

title = {Mitigating Temporal-Drift: A Simple Approach to Keep NER Models Crisp},

author = {Shuguang Chen and Leonardo Neves and Thamar Solorio},

url = {https://arxiv.org/abs/2104.09742

https://github.com/RiTUAL-UH/trending_NER},

year  = {2021},

date = {2021-04-19},

publisher = {Ninth International Workshop on Natural Language Processing for Social Media (SocialNLP @ NAACL 2021)},

abstract = {Performance of neural models for named entity recognition degrades over time, becoming stale. This degradation is due to temporal drift, the change in our target variables' statistical properties over time. This issue is especially problematic for social media data, where topics change rapidly. In order to mitigate the problem, data annotation and retraining of models is common. Despite its usefulness, this process is expensive and time-consuming, which motivates new research on efficient model updating. In this paper, we propose an intuitive approach to measure the potential trendiness of tweets and use this metric to select the most informative instances to use for training. We conduct experiments on three state-of-the-art models on the Temporal Twitter Dataset. Our approach shows larger increases in prediction accuracy with less training data than the alternatives, making it an attractive, practical solution.},

keywords = {NER, Social Media},

pubstate = {published},

tppubtype = {conference}

}

@conference{shirani-etal-2020-semeval,

title = {SemEval-2020 Task 10: Emphasis Selection for Written Text in Visual Media},

author = {Amirreza Shirani and Franck Dernoncourt and Nedim Lipka and Paul Asente and Jose Echevarria and Thamar Solorio},

url = {https://www.aclweb.org/anthology/2020.semeval-1.184},

year  = {2020},

date = {2020-12-03},

booktitle = {Proceedings of the Fourteenth Workshop on Semantic Evaluation},

publisher = {International Committee for Computational Linguistics},

address = {Barcelona (online)},

abstract = {In this paper, we present the main findings and compare the results of SemEval-2020 Task 10, Emphasis Selection for Written Text in Visual Media. The goal of this shared task is to design automatic methods for emphasis selection, i.e. choosing candidates for emphasis in textual content to enable automated design assistance in authoring. The main focus is on short text instances for social media, with a variety of examples, from social media posts to inspirational quotes. Participants were asked to model emphasis using plain text with no additional context from the user or other design considerations. SemEval-2020 Emphasis Selection shared task attracted 197 participants in the early phase and a total of 31 teams made submissions to this task. The highest-ranked submission achieved 0.823 Matchm score. The analysis of systems submitted to the task indicates that BERT and RoBERTa were the most common choice of pre-trained models used, and part of speech tag (POS) was the most useful feature. Full results can be found on the task's website.},

keywords = {Emphasis Selection, SemEval},

pubstate = {published},

tppubtype = {conference}

}

@conference{Kar2020,

title = {Multi-view Story Characterization from Movie Plot Synopses and Reviews},

author = {Sudipta Kar and Gustavo Aguilar and Mirella Lapata and Thamar Solorio},

url = {https://www.aclweb.org/anthology/2020.emnlp-main.454.pdf},

year  = {2020},

date = {2020-11-16},

booktitle = {EMNLP 2020},

pages = {5629-5646},

organization = {ACL},

keywords = {Narrative Analysis, Text Classification},

pubstate = {published},

tppubtype = {conference}

}

@conference{shirani-etal-2020-choose,

title = {Let Me Choose: From Verbal Context to Font Selection},

author = {Amirreza Shirani and Franck Dernoncourt and Jose Echevarria and Paul Asente and Nedim Lipka and Thamar Solorio},

editor = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020)},

url = {https://www.aclweb.org/anthology/2020.acl-main.762.pdf},

doi = {10.18653/v1/2020.acl-main.762},

year  = {2020},

date = {2020-07-19},

booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL 2020)},

publisher = {Association for Computational Linguistics},

abstract = {In this paper, we aim to learn associations between visual attributes of fonts and the verbal context of the texts they are typically applied to. Compared to related work leveraging the surrounding visual context, we choose to focus only on the input text as this can enable new applications for which the text is the only visual element in the document. We introduce a new dataset, containing examples of different topics in social media posts and ads, labeled through crowd-sourcing. Due to the subjective nature of the task, multiple fonts might be perceived as acceptable for an input text, which makes this problem challenging. To this end, we investigate different end-to-end models to learn label distributions on crowd-sourced data and capture inter-subjectivity across all annotations.},

keywords = {Font, font selection, From Verbal Context to Font Selection},

pubstate = {published},

tppubtype = {conference}

}

@conference{aguilar20_cs-elmo,

title = {From English to Code-Switching: Transfer Learning with Strong Morphological Clues},

author = {Gustavo Aguilar and Thamar Solorio},

editor = {ACL},

url = {https://www.aclweb.org/anthology/2020.acl-main.716.pdf},

year  = {2020},

date = {2020-06-19},

booktitle = {The 58th Annual Meeting of the Association for Computational Linguistics},

publisher = {ACL},

abstract = {Linguistic Code-switching (CS) is still an understudied phenomenon in natural language processing. The NLP community has mostly focused on monolingual and multi-lingual scenarios, but little attention has been given to CS in particular. This is partly because of the lack of resources and annotated data, despite its increasing occurrence in social media platforms. In this paper, we aim at adapting monolingual models to code-switched text in various tasks. Specifically, we transfer English knowledge from a pre-trained ELMo model to different code-switched language pairs (i.e., Nepali-English, Spanish-English, and Hindi-English) using the task of language identification. Our method, CS-ELMo, is an extension of ELMo with a simple yet effective position-aware attention mechanism inside its character convolutions. We show the effectiveness of this transfer learning step by outperforming multilingual BERT and homologous CS-unaware ELMo models and establishing a new state of the art in CS tasks, such as NER and POS tagging. Our technique can be expanded to more English-paired code-switched languages, providing more resources to the CS community.},

keywords = {Code-Switching, Transfer learning},

pubstate = {published},

tppubtype = {conference}

}

@conference{aguilar20_lince,

title = {LinCE: A Centralized Linguistic Code-Switching Evaluation Benchmark},

author = {Gustavo Aguilar and Sudipta Kar and Thamar Solorio},

editor = {LREC},

url = {https://www.aclweb.org/anthology/2020.lrec-1.223.pdf},

year  = {2020},

date = {2020-05-11},

booktitle = {Proceedings of the Twelfth International Conference on Language Resources and Evaluation},

publisher = {LREC},

abstract = {Recent trends in NLP research have raised an interest in linguistic code-switching (CS); modern approaches have been proposed to solve a wide range of NLP tasks on multiple language pairs. Unfortunately, these proposed methods are hardly generalizable to different code-switched languages. In addition, it is unclear whether a model architecture is applicable for a different task while still being compatible with the code-switching setting. This is mainly because of the lack of a centralized benchmark and the sparse corpora that researchers employ based on their specific needs and interests. To facilitate research in this direction, we propose a centralized benchmark for textbf{Lin}guistic textbf{C}ode-switching textbf{E}valuation (textbf{LinCE}) that combines ten corpora covering four different code-switched language pairs (i.e., Spanish-English, Nepali-English, Hindi-English, and Modern Standard Arabic-Egyptian Arabic) and four tasks (i.e., language identification, named entity recognition, part-of-speech tagging, and sentiment analysis). As part of the benchmark centralization effort, we provide an online platform at texttt{ritual.uh.edu/lince}, where researchers can submit their results while comparing with others in real-time. In addition, we provide the scores of different popular models, including LSTM, ELMo, and multilingual BERT so that the NLP community can compare against state-of-the-art systems. LinCE is a continuous effort, and we will expand it with more low-resource languages and tasks.},

keywords = {benchmark, Code-Switching},

pubstate = {published},

tppubtype = {conference}

}

@conference{aguilar20_kd,

title = {Knowledge Distillation from Internal Representations},

author = {Gustavo Aguilar and Yuan Ling and Yu Zhang and Benjamin Yao and Xing Fan and Chenlei Guo},

editor = {AAAI},

url = {https://arxiv.org/pdf/1910.03723.pdf},

year  = {2020},

date = {2020-02-07},

booktitle = {The Thirty-Fourth AAAI Conference on Artificial Intelligence},

publisher = {AAAI},

abstract = {Knowledge distillation is typically conducted by training a small model (the student) to mimic a large and cumbersome model (the teacher). The idea is to compress the knowledge from the teacher by using its output probabilities as soft-labels to optimize the student. However, when the teacher is considerably large, there is no guarantee that the internal knowledge of the teacher will be transferred into the student; even if the student closely matches the soft-labels, its internal representations may be considerably different. This internal mismatch can undermine the generalization capabilities originally intended to be transferred from the teacher to the student. In this paper, we propose to distill the internal representations of a large model such as BERT into a simplified version of it. We formulate two ways to distill such representations and various algorithms to conduct the distillation. We experiment with datasets from the GLUE benchmark and consistently show that adding knowledge distillation from internal representations is a more powerful method than only using soft-label distillation.},

keywords = {},

pubstate = {published},

tppubtype = {conference}

}

@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}

}

@conference{aguilar19_er,

title = {Multimodal and Multi-view Models for Emotion Recognition},

author = {Gustavo Aguilar and Viktor Rozgić and Weiran Wang and Chao Wang},

editor = {Association for Computational Linguistics },

url = {https://arxiv.org/abs/1906.10198},

year  = {2019},

date = {2019-07-28},

booktitle = {The 57th Annual Meeting of the Association for Computational Linguistics},

journal = {Association for Computational Linguistics},

publisher = {ACL},

abstract = {Studies on emotion recognition (ER) show that combining lexical and acoustic information results in more robust and accurate models. The majority of the studies focus on settings where both modalities are available in training and evaluation. However, in practice, this is not always the case; getting ASR output may represent a bottleneck in a deployment pipeline due to computational complexity or privacy-related constraints. To address this challenge, we study the problem of efficiently combining acoustic and lexical modalities during training while still providing a deployable acoustic model that does not require lexical inputs. We first experiment with multimodal models and two attention mechanisms to assess the extent of the benefits that lexical information can provide. Then, we frame the task as a multi-view learning problem to induce semantic information from a multimodal model into our acoustic-only network using a contrastive loss function. Our multimodal model outperforms the previous state of the art on the USC-IEMOCAP dataset reported on lexical and acoustic information. Additionally, our multi-view-trained acoustic network significantly surpasses models that have been exclusively trained with acoustic features.},

keywords = {acoustics, emotion recognition, language, Multimodal, multiview},

pubstate = {published},

tppubtype = {conference}

}

@conference{Shirani2019,

title = {Learning Emphasis Selection for Written Text in Visual Media from Crowd-Sourced Label Distributions},

author = {Amirreza Shirani and Franck Dernoncourt and Paul Asente and Nedim Lipka and Seokhwan Kim and Jose Echevarria and Thamar Solorio},

url = {https://www.aclweb.org/anthology/papers/P/P19/P19-1112/},

year  = {2019},

date = {2019-06-10},

booktitle = {The 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019)},

abstract = {In visual communication, text emphasis is used to increase the comprehension of written text and to convey the author’s intent. We study the problem of emphasis selection, i.e. choosing candidates for emphasis in short written text, to enable automated design assistance in authoring. Without knowing the author’s intent and only considering the input text, multiple emphasis selections are valid. We propose a model that employs end-to-end label distribution learning (LDL) on crowd-sourced data and predicts a selection distribution, capturing the inter-subjectivity (common-sense) in the audience as well as the ambiguity of the input. We compare the model with several baselines in which the problem is transformed to single-label learning by mapping label distributions to absolute labels via majority voting.},

keywords = {Emphasis Selection},

pubstate = {published},

tppubtype = {conference}

}

@conference{Shafaei2019,

title = {Exploiting Textual, Visual and Product Features for Predicting the Likeability of Movies},

author = {Mahsa Shafaei and Adrian Pastor Lopez-Monroy and Thamar Solorio},

url = {https://www.aaai.org/ocs/index.php/FLAIRS/FLAIRS19/paper/view/18305},

year  = {2019},

date = {2019-05-01},

publisher = {The 32nd  International FLAIRS Conference},

abstract = {Watching movies is one of the most popular entertainments among people. Every year, a huge amount of money goes to the movie industry to release movies to the market. In this paper, we propose a multimodal model to predict the likability of movies using textual, visual and product features. With the help of these features, we capture different aspects of movies and feed them as inputs to binary and multi-class classification and regression models to predict IMDB rating of movies at early steps of production. We also propose our own dataset consisting of about 15000 movie subtitles along with their metadata and poster images. We achieve 76%  and 63% weighted F1-score for binary and multiclass classification respectively, and 0.7 mean square error for the regression model. Using prediction methods and data analysis, this research helps the movie business to be more productive. },

keywords = {Sentiment analysis, Text Classification},

pubstate = {published},

tppubtype = {conference}

}

@conference{shirani2019question,

title = {Question Relatedness on Stack Overflow: The Task, Dataset, and Corpus-inspired Models},

author = {Amirreza Shirani, Bowen Xu, David Lo, Thamar Solorio, Amin Alipour},

url = {https://arxiv.org/pdf/1905.01966.pdf},

year  = {2019},

date = {2019-01-03},

booktitle = {AAAI Reasoning for Complex Question Answering

Workshop (AAAI 2019)},

abstract = {Domain-specific community question answering is becoming an integral part of professions. Finding related questions

and answers in these communities can significantly improve

the effectiveness and efficiency of information seeking. Stack

Overflow is one of the most popular communities that is being

used by millions of programmers. In this paper, we analyze

the problem of predicting knowledge unit (question thread)

relatedness in Stack Overflow. In particular, we formulate the

question relatedness task as a multi-class classification problem with four degrees of relatedness.

We present a large-scale dataset with more than 300K pairs.

To the best of our knowledge, this dataset is the largest

domain-specific dataset for Question-Question relatedness.

We present the steps that we took to collect, clean, process,

and assure the quality of the dataset. The proposed dataset

on Stack Overflow is a useful resource to develop novel solutions, specifically data-hungry neural network models, for the

prediction of relatedness in technical community question-answering forums.

We adapt a neural network architecture and a traditional

model for this task that effectively utilize information from

different parts of knowledge units to compute the relatedness

between them. These models can be used to benchmark novel

models, as they perform well in our task and in a closely similar task.},

keywords = {Community question answering, cQA, Question relatedness, stack overflow},

pubstate = {published},

tppubtype = {conference}

}

@conference{Kar2018b,

title = {Folksonomication: Predicting Tags for Movies from Plot Synopses using Emotion Flow encoded Neural Network},

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

url = {http://ritual.uh.edu/folksonomication-2018},

year  = {2018},

date = {2018-08-23},

booktitle = {Proceedings of the 27th International Conference on Computational Linguistics},

keywords = {CNN, Narrative Analysis, Sentiment analysis},

pubstate = {published},

tppubtype = {conference}

}

@conference{pastor18,

title = {Early Text Classification using Multi-Resolution Concept Representations},

author = {A. Pastor López-Monroy and Fabio A. González and Manuel Montes-y-Gómez and Hugo Jair Escalante and Thamar Solorio},

editor = {Association for Computational Linguistics },

url = {http://www.aclweb.org/anthology/N18-1110},

year  = {2018},

date = {2018-06-04},

booktitle = {The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},

publisher = {Association for Computational Linguistics },

abstract = {This paper proposes a novel document representation, called Multi-Resolution Representation (MulR), to improve the early detection of risks in social media sources. The goal is to effectively identify the potential risk using as little evidence as  possible and with as much anticipation as possible. MulR allows us to generate multiple ``views" of the text. These views capture different semantic meanings for words and documents at different levels of granularity, which is very useful in early scenarios to model the variable amounts of evidence. Our experimental evaluation shows that MuLR using low resolution is better suited for  modeling short documents (very early stages), whereas large documents (medium/late stages) are better modeled with higher resolutions.  We evaluate the proposed ideas in two different tasks where anticipation is critical: sexual predator detection and depression detection. The experimental evaluation for these early tasks revealed that the proposed approach outperforms previous methodologies by a considerable margin.},

keywords = {Text Classification},

pubstate = {published},

tppubtype = {conference}

}

@conference{Kar2018,

title = {MPST: A Corpus of Movie Plot Synopses with Tags},

author = {Sudipta Kar and Suraj Maharjan and A. Pastor López-Monroy and Thamar Solorio},

url = {http://sudiptakar.info/wp-content/uploads/2018/05/322_LREC_2018.pdf, Slide

http://sudiptakar.info/wp-content/uploads/2018/02/mpst-corpus-movie-2.pdf, Paper},

year  = {2018},

date = {2018-05-10},

booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)},

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

abstract = {Social tagging of movies reveals a wide range of heterogeneous information about movies, like the genre, plot structure, soundtracks, metadata, visual and emotional experiences. Such information can be valuable in building automatic systems to create tags for movies. Automatic tagging systems can help recommendation engines to improve the retrieval of similar movies as well as help viewers to know what to expect from a movie in advance. In this paper, we set out to the task of collecting a corpus of movie plot synopses and tags. We describe a methodology that enabled us to build a fine-grained set of around 70 tags exposing heterogeneous characteristics of movie plots and the multi-label associations of these tags with some 14K movie plot synopses. We investigate how these tags correlate with movies and the flow of emotions throughout different types of movies. Finally, we use this corpus to explore the feasibility of inferring tags from plot synopses. We expect the corpus will be useful in other tasks where analysis of narratives is relevant.},

keywords = {Information Extraction, Narrative Analysis, Sentiment analysis, Text Classification},

pubstate = {published},

tppubtype = {conference}

}

@conference{Shirani2018,

title = {Evaluation of Type Inference with Textual Cues},

author = {Amirreza Shirani, Pastor Lopez-Monroy, Fabio Gonzalez, Thamar Solorio, Mohammad Amin Alipour},

url = {https://www.researchgate.net/publication/323627639_Evaluation_of_Type_Inference_with_Textual_Cues},

year  = {2018},

date = {2018-02-07},

booktitle = {Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18)},

abstract = {Type information plays an important role in the success of information retrieval and recommendation systems in software engineering. Thus, the absence of types in dynamically-typed languages poses a challenge to adapt these systems to support dynamic languages. In this paper, we explore the viability of type inference using textual cues. That is, we formulate the type inference problem as a classification problem which uses the textual features in the source code to predict the type of variables. In this approach, a classifier learns a model to distinguish between types of variables in a program. The model is subsequently used to (approximately) infer the types of other variables. We evaluate the feasibility of this approach on four Java projects wherein type information is already available in the source code and can be used to train and test a classifier. Our experiments show this approach can predict the type of new variables with relatively high accuracy (80% F-measure). These results suggest that textual cues can be complementary tools in inferring types for dynamic languages. 



(PDF) Evaluation of Type Inference with Textual Cues. Available from: https://www.researchgate.net/publication/323627639_Evaluation_of_Type_Inference_with_Textual_Cues [accessed Sep 07 2018].},

keywords = {Java Language, SVM, Textual Features, Type Prediction},

pubstate = {published},

tppubtype = {conference}

}