Papers with fully connected layers

4 papers
Investigating Audio, Video, and Text Fusion Methods for End-to-End Automatic Personality Prediction (P18-2)

Copied to clipboard

Challenge: Using stacked Convolutional Neural Networks, we can predict personality traits from video clips with different channels for audio, text, and video data.
Approach: They propose a tri-modal architecture to predict Big Five personality trait scores from video clips with different channels for audio, text, and video data.
Outcome: The proposed model outperforms the best individual modality with 9.4% accuracy over the best channel.
Attention for Implicit Discourse Relation Recognition (L18-1)

Copied to clipboard

Challenge: Existing approaches to implicit discourse relation recognition reach F1 scores of 9.95% to 37.67% . a neural network exploits the strong correlation between pairs of words that implicitly signal a discourse relation.
Approach: They propose a neural network which exploits strong correlation between pairs of words . they use an encoder-decoder model with attention to detect a latent discourse relation .
Outcome: The proposed model outperforms state-of-the-art models on fine-grained classification and fine-granular classification while computing parameters without pooling and fully connected layers.
An Instruction Tuning-Based Contrastive Learning Framework for Aspect Sentiment Quad Prediction with Implicit Aspects and Opinions (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for aspect-based sentiment analysis have not explored how to effectively leverage the knowledge of pre-trained language models to handle implicit aspects and opinions.
Approach: They propose a framework leveraging Instruction Tuning and Supervised Contrastive Learning to improve aspect sentiment quad prediction for implicit aspects and opinions.
Outcome: The proposed framework significantly outperforms existing methods on benchmark datasets.
Boosting Prompt-Based Self-Training With Mapping-Free Automatic Verbalizer for Multi-Class Classification (2023.findings-emnlp)

Copied to clipboard

Challenge: Recent prompt-based fine-tuning techniques have garnered considerable interest as a core technique for few-shot text classification tasks.
Approach: They propose a prompt-based fine-tuning approach that reformulates the fine-uning objective to align with the Masked Language Modeling objective.
Outcome: The proposed method has shown superior performance on five multi-class classification datasets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations