LLM-Driven Multimodal Opinion Expression Identification
This addresses the need for more accurate opinion expression identification in applications like voice assistants and depression diagnosis, though it appears incremental as it builds on existing tasks with multimodal data.
This study tackled the problem of identifying opinion expressions by extending it to multimodal inputs combining text and speech, and introduced a new LLM-driven method that achieved state-of-the-art results with a 9.20% improvement over existing methods.
Opinion Expression Identification (OEI) is essential in NLP for applications ranging from voice assistants to depression diagnosis. This study extends OEI to encompass multimodal inputs, underlining the significance of auditory cues in delivering emotional subtleties beyond the capabilities of text. We introduce a novel multimodal OEI (MOEI) task, integrating text and speech to mirror real-world scenarios. Utilizing CMU MOSEI and IEMOCAP datasets, we construct the CI-MOEI dataset. Additionally, Text-to-Speech (TTS) technology is applied to the MPQA dataset to obtain the CIM-OEI dataset. We design a template for the OEI task to take full advantage of the generative power of large language models (LLMs). Advancing further, we propose an LLM-driven method STOEI, which combines speech and text modal to identify opinion expressions. Our experiments demonstrate that MOEI significantly improves the performance while our method outperforms existing methods by 9.20\% and obtains SOTA results.