@inproceedings{4452bdc106494c83abbe9c707b5e8999,
title = "Deriving local relational surface forms from dependency-based entity embeddings for unsupervised spoken language understanding",
abstract = "Recent works showed the trend of leveraging web-scaled structured semantic knowledge resources such as Freebase for open domain spoken language understanding (SLU). Knowledge graphs provide sufficient but ambiguous relations for the same entity, which can be used as statistical background knowledge to infer possible relations for interpretation of user utterances. This paper proposes an approach to capture the relational surface forms by mapping dependency-based contexts of entities from the text domain to the spoken domain. Relational surface forms are learned from dependency-based entity embeddings, which encode the contexts of entities from dependency trees in a deep learning model. The derived surface forms carry functional dependency to the entities and convey the explicit expression of relations. The experiments demonstrate the efficiency of leveraging derived relational surface forms as local cues together with prior background knowledge.",
keywords = "Entity embeddings, Relation detection, Semantic knowledge graph, Spoken dialogue systems (SDS), Spoken language understanding (SLU)",
author = "Chen, {Yun Nung} and Dilek Hakkani-Tur and Gokan Tur",
note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2014 IEEE Workshop on Spoken Language Technology, SLT 2014 ; Conference date: 07-12-2014 Through 10-12-2014",
year = "2014",
month = apr,
day = "1",
doi = "10.1109/SLT.2014.7078581",
language = "English (US)",
series = "2014 IEEE Workshop on Spoken Language Technology, SLT 2014 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "242--247",
booktitle = "2014 IEEE Workshop on Spoken Language Technology, SLT 2014 - Proceedings",
address = "United States",
}