Search Results for author:
Found 38 papers, 5 papers with code
Multi-Task Learning to Capture Changes in Mood Over Time
This paper investigates the impact of using Multi-Task Learning (MTL) to predict mood changes over time for each individual (social media user).
uOttawa at LegalLens-2024: Transformer-based Classification Experiments
Our results were 86. 3% in the L-NER subtask and 88. 25% in the L-NLI subtask.
HateSieve: A Contrastive Learning Framework for Detecting and Segmenting Hateful Content in Multimodal Memes
Amidst the rise of Large Multimodal Models (LMMs) and their widespread application in generating and interpreting complex content, the risk of propagating biased and harmful memes remains significant.
Co-Regularized Adversarial Learning for Multi-Domain Text Classification
Multi-domain text classification (MDTC) aims to leverage all available resources from multiple domains to learn a predictive model that can generalize well on these domains.
Maximum Batch Frobenius Norm for Multi-Domain Text Classification
Multi-domain text classification (MDTC) has obtained remarkable achievements due to the advent of deep learning.
Towards Category and Domain Alignment: Category-Invariant Feature Enhancement for Adversarial Domain Adaptation
Adversarial domain adaptation has made impressive advances in transferring knowledge from the source domain to the target domain by aligning feature distributions of both domains.
Context-Sensitive Visualization of Deep Learning Natural Language Processing Models
The modified texts that produce the largest difference in the target classification output neuron are selected, and the combination of removed words are then considered to be the most influential on the model's output.
Conditional Adversarial Networks for Multi-Domain Text Classification
We provide theoretical analysis for the CAN framework, showing that CAN's objective is equivalent to minimizing the total divergence among multiple joint distributions of shared features and label predictions.
Mixup Regularized Adversarial Networks for Multi-Domain Text Classification
Using the shared-private paradigm and adversarial training has significantly improved the performances of multi-domain text classification (MDTC) models.
Dual Adversarial Training for Unsupervised Domain Adaptation
Domain adaptation sets out to address this problem, aiming to leverage labeled data in the source domain to learn a good predictive model for the target domain whose labels are scarce or unavailable.
Dual Mixup Regularized Learning for Adversarial Domain Adaptation
Second, samples from the source and target domains alone are not sufficient for domain-invariant feature extracting in the latent space.
Multi-Task, Multi-Channel, Multi-Input Learning for Mental Illness Detection using Social Media Text
We illustrate the effectiveness of using multi-task learning with a multi-channel convolutional neural network as the shared representation and use additional inputs identified by researchers as indicatives in detecting mental disorders to enhance the model predictability.
Semantics and Homothetic Clustering of Hafez Poetry
Our labels are the only semantic clustering alternative to the previously existing, hand-labeled, gold-standard classification of Hafez poems, to be used for literary research.
Introduction to the Special Issue on Language in Social Media: Exploiting Discourse and Other Contextual Information
This special issue contributes to a deeper understanding of the role of these interactions to process social media data from a new perspective in discourse interpretation.
Cyberbullying Intervention Based on Convolutional Neural Networks
This paper describes the process of building a cyberbullying intervention interface driven by a machine-learning based text-classification service.
Cyber-aggression Detection using Cross Segment-and-Concatenate Multi-Task Learning from Text
In this paper, we propose a novel deep-learning architecture for text classification, named cross segment-and-concatenate multi-task learning (CSC-MTL).
Authorship Identification for Literary Book Recommendations
Book recommender systems can help promote the practice of reading for pleasure, which has been declining in recent years.
uOttawa at SemEval-2018 Task 1: Self-Attentive Hybrid GRU-Based Network
We propose a novel attentive hybrid GRU-based network (SAHGN), which we used at SemEval-2018 Task 1: Affect in Tweets.
Deep Learning for Depression Detection of Twitter Users
Mental illness detection in social media can be considered a complex task, mainly due to the complicated nature of mental disorders.
Natural Language Inference with External Knowledge
Modeling informal inference in natural language is very challenging.
Neural Natural Language Inference Models Enhanced with External Knowledge
With the availability of large annotated data, it has recently become feasible to train complex models such as neural-network-based inference models, which have shown to achieve the state-of-the-art performance.
Ranked #20 on
Natural Language Inference
on SNLI
Recurrent Neural Network-Based Sentence Encoder with Gated Attention for Natural Language Inference
The RepEval 2017 Shared Task aims to evaluate natural language understanding models for sentence representation, in which a sentence is represented as a fixed-length vector with neural networks and the quality of the representation is tested with a natural language inference task.
Ranked #69 on
Natural Language Inference
on SNLI
Natural Language Inference
Natural Language Understanding
+1
Monitoring Tweets for Depression to Detect At-risk Users
To achieve our goal, we trained a user-level classifier that can detect at-risk users that achieves a reasonable precision and recall.
A Dataset for Multi-Target Stance Detection
Current models for stance classification often treat each target independently, but in many applications, there exist natural dependencies among targets, e. g., stance towards two or more politicians in an election or towards several brands of the same product.
Local-Global Vectors to Improve Unigram Terminology Extraction
The present paper explores a novel method that integrates efficient distributed representations with terminology extraction.
Enhanced LSTM for Natural Language Inference
Reasoning and inference are central to human and artificial intelligence.
Ranked #30 on
Natural Language Inference
on SNLI
