DSTC8-AVSD: Multimodal Semantic Transformer Network with Retrieval Style Word Generator

Abstract

Audio Visual Scene-aware Dialog (AVSD) is the task of generating a response for a question with a given scene, video, audio, and the history of previous turns in the dialog. Existing systems for this task employ the transformers or recurrent neural network-based architecture with the encoder-decoder framework. Even though these techniques show superior performance for this task, they have significant limitations: the model easily overfits only to memorize the grammatical patterns; the model follows the prior distribution of the vocabularies in a dataset. To alleviate the problems, we propose a Multimodal Semantic Transformer Network. It employs a transformer-based architecture with an attention-based word embedding layer that generates words by querying word embeddings. With this design, our model keeps considering the meaning of the words at the generation stage. The empirical results demonstrate the superiority of our proposed model that outperforms most of the previous works for the AVSD task.

arXiv commentPresented at DSTC Workshop @ AAAI 2020

References in corpus (4)

• Adam: A Method for Stochastic Optimization
• Sequence to Sequence Learning with Neural Networks
• The Eighth Dialog System Technology Challenge
• Audio Visual Scene-Aware Dialog (AVSD) Challenge at DSTC7

Cited by in corpus (6)

• Information-Theoretic Text Hallucination Reduction for Video-grounded Dialogue
• Learning Reasoning Paths over Semantic Graphs for Video-grounded Dialogues
• HEAR: Hearing Enhanced Audio Response for Video-grounded Dialogue
• TMT: A Transformer-based Modal Translator for Improving Multimodal Sequence Representations in Audio Visual Scene-aware Dialog
• $C^3$: Compositional Counterfactual Contrastive Learning for Video-grounded Dialogues
• VGNMN: Video-grounded Neural Module Network to Video-Grounded Language Tasks