activity
20032026
most citedA Multi-task Approach for Named Entity Recognition in Social Media Data

150 citations · 457 across the 69 of their papers we have counts for

collaborators
Showing 2021Show all

7 papers · 1 filter

cs.CL2021

Exploring Conditional Text Generation for Aspect-Based Sentiment Analysis

Siva Uday Sampreeth Chebolu, Franck Dernoncourt, Nedim Lipka +1

Aspect-based sentiment analysis (ABSA) is an NLP task that entails processing user-generated reviews to determine (i) the target being evaluated, (ii) the aspect category to which…

cs.CL2021

From None to Severe: Predicting Severity in Movie Scripts

Yigeng Zhang, Mahsa Shafaei, Fabio Gonzalez +1

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 or…

cs.CL2021★ 1 cited

Data Augmentation for Cross-Domain Named Entity Recognition

Shuguang Chen, Gustavo Aguilar, Leonardo Neves +1

Current work in named entity recognition (NER) shows that data augmentation techniques can produce more robust models. However, most existing techniques focus on augmenting in-doma…

cs.CL2021

Mitigating Temporal-Drift: A Simple Approach to Keep NER Models Crisp

Shuguang Chen, Leonardo Neves, Thamar Solorio

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' statist…

cs.CY2021

White Paper -- Objectionable Online Content: What is harmful, to whom, and why

Thamar Solorio, Mahsa Shafaei, Christos Smailis +5

This White Paper summarizes the authors' discussion regarding objectionable content for the University of Houston (UH) Research Team to outline a strategy for building an extensive…

cs.LG2021★ 3 cited

A Case Study of Deep Learning Based Multi-Modal Methods for Predicting the Age-Suitability Rating of Movie Trailers

Mahsa Shafaei, Christos Smailis, Ioannis A. Kakadiaris +1

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 contain…

cs.CL2021★ 1 cited

Learning to Emphasize: Dataset and Shared Task Models for Selecting Emphasis in Presentation Slides

Amirreza Shirani, Giai Tran, Hieu Trinh +5

Presentation slides have become a common addition to the teaching material. Emphasizing strong leading words in presentation slides can allow the audience to direct the eye to cert…