Improving Slot Filling by Utilizing Contextual Information

Amir Pouran Ben Veyseh, Franck Dernoncourt, Thien Huu Nguyen


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.
Anthology ID:
2020.nlp4convai-1.11
Volume:
Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI
Month:
July
Year:
2020
Address:
Online
Editors:
Tsung-Hsien Wen, Asli Celikyilmaz, Zhou Yu, Alexandros Papangelis, Mihail Eric, Anuj Kumar, Iñigo Casanueva, Rushin Shah
Venue:
NLP4ConvAI
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
90–95
Language:
URL:
https://aclanthology.org/2020.nlp4convai-1.11
DOI:
10.18653/v1/2020.nlp4convai-1.11
Bibkey:
Cite (ACL):
Amir Pouran Ben Veyseh, Franck Dernoncourt, and Thien Huu Nguyen. 2020. Improving Slot Filling by Utilizing Contextual Information. In Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI, pages 90–95, Online. Association for Computational Linguistics.
Cite (Informal):
Improving Slot Filling by Utilizing Contextual Information (Pouran Ben Veyseh et al., NLP4ConvAI 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2020.nlp4convai-1.11.pdf
Video:
 http://slideslive.com/38929627
Data
ATISSNIPS