Related papers: Analyzing the Generalizability of Deep Contextuali…

Sentiment analysis, also referred to as opinion mining, primarily tries to extract opinion from any text-based data. In the context of movie reviews and critics, sentimental analysis can be a helpful tool to predict whether a movie review…

Accurate and interpretable detection of depressive language in social media is useful for early interventions of mental health conditions, and has important implications for both clinical practice and broader public health efforts. In this…

Recently BERT has been adopted for document encoding in state-of-the-art text summarization models. However, sentence-based extractive models often result in redundant or uninformative phrases in the extracted summaries. Also, long-range…

Reinforcement learning (RL) can be used to improve the policy (denoiser) of diffusion large language models (dLLMs), while being hindered by the intractability of the policy likelihood. A dominant and efficient family of methods replaces…

In today's fast-paced world, the rates of stress and depression present a surge. Social media provide assistance for the early detection of mental health conditions. Existing methods mainly introduce feature extraction approaches and train…

Though achieving impressive results on many NLP tasks, the BERT-like masked language models (MLM) encounter the discrepancy between pre-training and inference. In light of this gap, we investigate the contextual representation of…

Many works proposed methods to improve the performance of Neural Machine Translation (NMT) models in a domain/multi-domain adaptation scenario. However, an understanding of how NMT baselines represent text domain information internally is…

Large Language Models (LLMs) continue to set new standards in knowledge-intensive and complex reasoning tasks, yet their high computational demands limit widespread adoption. While distilling large models into smaller ones offers a…

Managing extensive context remains a critical bottleneck for Large Language Models (LLMs), particularly in applications like long-document question answering and autonomous agents where lengthy inputs incur high computational costs and…

Pretrained contextualized text representation models learn an effective representation of a natural language to make it machine understandable. After the breakthrough of the attention mechanism, a new generation of pretrained models have…

The success of bidirectional encoders using masked language models, such as BERT, on numerous natural language processing tasks has prompted researchers to attempt to incorporate these pre-trained models into neural machine translation…

Transliteration is very common on social media, but transliterated text is not adequately handled by modern neural models for various NLP tasks. In this work, we combine data augmentation approaches with a Teacher-Student training scheme to…

The classification of statements provided by individuals during police interviews is a complex and significant task within the domain of natural language processing (NLP) and legal informatics. The lack of extensive domain-specific datasets…

Detecting emotions in limited text datasets from under-resourced languages presents a formidable obstacle, demanding specialized frameworks and computational strategies. This study conducts a thorough examination of deep learning techniques…

In this paper, we propose Stacked DeBERT, short for Stacked Denoising Bidirectional Encoder Representations from Transformers. This novel model improves robustness in incomplete data, when compared to existing systems, by designing a novel…

This study explores using Natural Language Processing (NLP) to analyze candidate comments for identifying problematic test items. We developed and validated machine learning models that automatically identify relevant negative feedback,…

Estimating causal treatment effects in observational settings is frequently compromised by selection bias arising from unobserved confounders. While traditional econometric methods struggle when these confounders are orthogonal to…

Adjective phrases like "a little bit surprised", "completely shocked", or "not stunned at all" are not handled properly by currently published state-of-the-art emotion classification and intensity prediction systems which use pre-dominantly…

This work presents a detailed comparison of the performance of deep learning models such as convolutional neural networks (CNN), long short-term memory (LSTM), gated recurrent units (GRU), their hybrids, and a selection of shallow learning…

Recent years have witnessed increasing interests in prompt-based learning in which models can be trained on only a few annotated instances, making them suitable in low-resource settings. When using prompt-based learning for text…