Supervised Domain Enablement Attention for Personalized Domain Classification
Lists
Only you see this
Abstract
In large-scale domain classification for natural language understanding, leveraging each user's domain enablement information, which refers to the preferred or authenticated domains by the user, with attention mechanism has been shown to improve the overall domain classification performance. In this paper, we propose a supervised enablement attention mechanism, which utilizes sigmoid activation for the attention weighting so that the attention can be computed with more expressive power without the weight sum constraint of softmax attention. The attention weights are explicitly encouraged to be similar to the corresponding elements of the ground-truth's one-hot vector by supervised attention, and the attention information of the other enabled domains is leveraged through self-distillation. By evaluating on the actual utterances from a large-scale IPDA, we show that our approach significantly improves domain classification performance.
BibTeX
@inproceedings{kim2018supervised,
author = {Joo-Kyung Kim and Young-Bum Kim},
title = {{Supervised Domain Enablement Attention for Personalized Domain Classification}},
booktitle = {Conference on Empirical Methods in Natural Language Processing},
year = {2018},
doi = {10.18653/v1/d18-1106},
}Loading related content...