We explore the benefits that multitask learning offer to speech processing as we train models on dual objectives with automatic speech recognition and intent classification or sentiment classification. Our models, although being of modest size, show improvements over models trained end-to-end on intent classification. We compare different settings to find the optimal disposition of each task module compared to one another. Finally, we study the performance of the models in low-resource scenario by training the models with as few as one example per class. We show that multitask learning in these scenarios compete with a baseline model trained on text features and performs considerably better than a pipeline model. On sentiment classification, we match the performance of an end-to-end model with ten times as many parameters. We consider 4 tasks and 4 datasets in Dutch and English.
翻译:我们探索多任务学习对语言处理的好处,因为我们在用自动语音识别和意图分类或情绪分类的双重目标模式上培训模型。我们的模式虽然规模不大,但比经过培训的意向分类的终端到终端模型有所改进。我们比较了不同的环境,以找到每个任务模块的最佳配置,而不同的任务模块之间的最佳配置。最后,我们通过每类仅举一个例子来培训模型来研究低资源情景模式的性能。我们显示,在这些情景中,多任务学习与经过文字特征培训的基线模型竞争,其表现比编审模式好得多。在情绪分类方面,我们把终端到终端模型的性能与十倍的参数相匹配。我们考虑荷兰语和英语的4项任务和4个数据集。