TECO: Improving Multimodal Intent Recognition with Text Enhancement through Commonsense Knowledge Extraction

TL;DR

This paper introduces TECO, a novel method that enhances multimodal intent recognition by extracting and integrating commonsense knowledge to improve textual and non-verbal modality fusion.

Contribution

The paper proposes a new approach, TECO, for enriching textual features with commonsense knowledge and better aligning multimodal data for improved intent recognition.

Findings

Significant performance improvements over baseline methods

Effective extraction of relations from generated and retrieved knowledge

Enhanced fusion of visual, acoustic, and textual modalities

Abstract

The objective of multimodal intent recognition (MIR) is to leverage various modalities-such as text, video, and audio-to detect user intentions, which is crucial for understanding human language and context in dialogue systems. Despite advances in this field, two main challenges persist: (1) effectively extracting and utilizing semantic information from robust textual features; (2) aligning and fusing non-verbal modalities with verbal ones effectively. This paper proposes a Text Enhancement with CommOnsense Knowledge Extractor (TECO) to address these challenges. We begin by extracting relations from both generated and retrieved knowledge to enrich the contextual information in the text modality. Subsequently, we align and integrate visual and acoustic representations with these enhanced text features to form a cohesive multimodal representation. Our experimental results show substantial improvements over existing baseline methods.