Papers by Masood Gheasi
Augmenting pre-trained language models with audio feature embedding for argumentation mining in political debates (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing studies on the integration of multimodality with text and audio in natural language processing tasks have focused on the use of image and text for emotion recognition, fake news detection and document image classification. |
| Approach: | They propose to integrate audio features with text in a task of argumentation mining using a previously reported dataset and an audio-enhanced version. |
| Outcome: | The proposed model outperforms text-based models on a dataset of 28,850 utterances on 'argumentation mining' with limited data. |