Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI 2020
DOI: 10.18653/v1/2020.nlp4convai-1.11
|View full text |Cite
|
Sign up to set email alerts
|

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 addres… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
1
1
1

Relationship

1
2

Authors

Journals

citations
Cited by 3 publications
(1 citation statement)
references
References 17 publications
0
1
0
Order By: Relevance
“…3 ) that consists of knowledge acquisition, knowledge representation, knowledge incorporation and data-driven ML model layers. In the knowledge acquisition layer, multi-source domain knowledge can be extracted through an information filter [ 72 ] or approaches based on natural language-processing technologies such as entity extraction [ 73 ], relation extraction [ 74 ] and entity–relation extraction [ 75 ]. Then, the knowledge representation layer represents the extracted knowledge in the form of feature importance [ 76 ], relation rules [ 77 ], a physics model [ 78 ] or a knowledge graph [ 79 ].…”
Section: A Synergistic Data Quantity Governance Flow With Incorporati...mentioning
confidence: 99%
“…3 ) that consists of knowledge acquisition, knowledge representation, knowledge incorporation and data-driven ML model layers. In the knowledge acquisition layer, multi-source domain knowledge can be extracted through an information filter [ 72 ] or approaches based on natural language-processing technologies such as entity extraction [ 73 ], relation extraction [ 74 ] and entity–relation extraction [ 75 ]. Then, the knowledge representation layer represents the extracted knowledge in the form of feature importance [ 76 ], relation rules [ 77 ], a physics model [ 78 ] or a knowledge graph [ 79 ].…”
Section: A Synergistic Data Quantity Governance Flow With Incorporati...mentioning
confidence: 99%