GAN-BElectra: Enhanced Multi-class Sentiment Analysis with Limited Labeled Data

Riyadh, Md; Shafiq, Omair

doi:10.1080/08839514.2022.2083794

Cited by 4 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning and its various applications are prime examples of such domains. A plethora of recent research now focuses on leveraging machine learning to perform various tasks, such as Sentiment Analysis (e.g., [191]- [193]), Emotion-Cause Analysis [90], [194], [195], persuasion (e.g., [196]- [198]), predicting future events, (e.g., [199]) image generation from the text (e.g., [200]). Machine learning is also being utilized in many industries on a routine basis and it is contributing to novel consumer products such as autonomous cars, personalized virtual assistants, etc.…”

Section: Introductionmentioning

confidence: 99%

“…These LMs can generate meaningful texts based on the prompt provided without requiring any further training. A process named fine-tuning [120] is typically performed to use these models in specific downstream tasks such as question answering, summarization, and sentiment analysis [226]- [230]. This fine-tuning process provides a way to control text generation for different outcomes [128].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Human Emotion and Sentiment in Natural Language Understanding and Generation using Large Language Models with Limited to No Labeled Data

Riyadh¹

View full text Add to dashboard Cite

Natural Language Processing (NLP) aims to utilize computational resources to comprehend and generate human language. Emotion and sentiment are integral parts of human beings, and they are often reflected in human language. Consequently, these two closely related ideas are of paramount importance to NLP. In this thesis, we focus on several NLP tasks related to human emotion and sentiment. Particularly, we focus on the domains of Sentiment Analysis and Emotion-Cause Analysis (ECA). Like most other NLP tasks, machine learning technologies are frequently leveraged to perform various NLP tasks in these two domains. A common challenge in applying machine learning technology to context-dependent tasks like Sentiment Analysis is that they require a large amount of labeled data to develop a performant model. In this thesis, we develop several techniques leveraging Transformer-based large language models (LLMs) to perform various NLP tasks within these two domains in a limited to no labeled data setting. Specifically, we devise two technical architectures to perform multi-class Sentiment Analysis with limited labeled data. We introduce two new NLP tasks within the domain of ECA, which are also the first Natural Language Generation (NLG) tasks in this domain. We devise technical solutions to perform these NLG tasks, one with limited labeled data, and the other with no labeled data. We publish a new dataset for one of these novel NLG tasks. Lastly, we propose leveraging conversational LLMs for the automatic evaluation of open-ended NLG tasks, which also does not require any new training or labeled data.

show abstract