arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.05019cs.CLcs.LG
收藏

使用多任务学习的多模态嵌入用于情感识别

Multi-modal embeddings using multi-task learning for emotion recognition

Aparna Khare, Srinivas Parthasarathy, Shiva Sundaram

摘要:

像word 2 vec、GloVe和ELMo这样的通用嵌入在自然语言任务中取得了很大的成功。嵌入通常是从基于一般任务(如skip-gram模型和自然语言生成)构建的模型中提取的。在本文中,我们将工作从自然语言理解扩展到使用音频,视觉和文本信息进行机器学习任务的多模态架构。我们网络中的嵌入是使用多任务训练的Transformer模型的编码器提取的。在嵌入生成框架中,我们使用了人物识别和自动语音识别作为任务。我们调整和评估了情感识别下游任务的嵌入,并证明了在CMU-MOSEI数据集上,嵌入可以用来改善以前的最先进的结果。

英文摘要:

General embeddings like word2vec, GloVe and ELMo have shown a lot of success in natural language tasks. The embeddings are typically extracted from models that are built on general tasks such as skip-gram models and natural language generation. In this paper, we extend the work from natural language understanding to multi-modal architectures that use audio, visual and textual information for machine learning tasks. The embeddings in our network are extracted using the encoder of a transformer model trained using multi-task training. We use person identification and automatic speech recognition as the tasks in our embedding generation framework. We tune and evaluate the embeddings on the downstream task of emotion recognition and demonstrate that on the CMU-MOSEI dataset, the embeddings can be used to improve over previous state of the art results.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑