Improving Slot Filling By Utilizing Contextual Information

Abstract

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-the-art results on all three benchmark datasets for the task of SF.

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keyveyseh2019improving

Related papers

• A Novel Bi-directional Interrelated Model For Joint Intent Detection And Slot Filling (2019)12.33
• Multi-domain Adversarial Learning For Slot Filling In Spoken Language Understanding (2017)0.00
• Recent Advances In End-to-end Spoken Language Understanding (2019)8.09
• Attentive Contextual Carryover For Multi-turn End-to-end Spoken Language Understanding (2021)7.16
• Joint Learning Of Word And Label Embeddings For Sequence Labelling In Spoken Language Understanding (2019)3.58
• Bridging The Gap Between Clean Data Training And Real-world Inference For Spoken Language Understanding (2021)0.00
• Knowledge-aware Audio-grounded Generative Slot Filling For Limited Annotated Data (2023)0.00
• Cm-net: A Novel Collaborative Memory Network For Spoken Language Understanding (2019)13.28