Improving Slot Filling by Utilizing Contextual Information
Amir Pouran Ben Veyseh, Franck Dernoncourt, Thien Huu Nguyen · 2020
Slot Filling (SF) is one of the sub-tasks of Spoken Language Understanding (SLU) which aims to extract semantic constituents from a given natural language utterance.It is formulated as a sequence labeling task.Recently, it has been shown that contextual information is vital for this task.However, existing models employ contextual information in a restricted manner, e.g., using self-attention.Such methods fail to distinguish the effects of the context on the word representation and the word label.To address this issue, in this paper, we propose a novel method to incorporate the contextual information in two different levels, i.e., representation level and task-specific (i.e., label) level.Our extensive experiments on three benchmark datasets on SF show the effectiveness of our model leading to new state-of-theart results on all three benchmark datasets for the task of SF.