• Publications
  • Influence
Emotion Detection on TV Show Transcripts with Sequence-based Convolutional Neural Networks
A corpus for text-based emotion detection on multiparty dialogue as well as deep neural models that outperform the existing approaches for document classification and four types of sequence-based convolutional neural network models with attention that leverage the sequence information encapsulated in dialogue are introduced.
Segmentation of brain MR images using a proper combination of DCS based method with MRF
Dynamic Classifier Selection Markov Random Field (DCSMRF) algorithm for supervised segmentation of brain MR images into three main tissues such as White Matter, Gray Matter and Cerebrospinal Fluid is introduced.
CRAB: Class Representation Attentive BERT for Hate Speech Identification in Social Media
CRAB (Class Representation Attentive BERT), a neural model for detecting hate speech in social media that benefits from two semantic representations: trainable token-wise and sentence-wise class representations, and contextualized input embeddings from state-of-the-art BERT encoder.
Active Learning for Product Type Ontology Enhancement in E-commerce
This work proposes an active learning framework that efficiently utilizes domain experts' knowledge for PT discovery and shows the quality and coverage of the resulting PTs in the experiment results.
De-Biased Modeling of Search Click Behavior with Reinforcement Learning
The proposed De-biased Reinforcement Learning Click model relaxes previously made assumptions about the users' examination behavior and resulting latent states, leading to improved modeling performance and showing the potential for using DRLC for improving Web search quality.
APRF-Net: Attentive Pseudo-Relevance Feedback Network for Query Categorization
This work proposes a novel deep neural model named Attentive Pseudo Relevance Feedback Network (APRF-Net) to enhance the representation of rare queries for query categorization, and demonstrates the effectiveness of the approach by collecting search queries from a large commercial search engine, and comparing it to state-of-the-art deep learning models for text classification.