TU Darmstadt / ULB / TUbiblio

Graph-Based Semi-Supervised Conditional Random Fields For Spoken Language Understanding Using Unaligned Data

Aliannejadi, Mohammad and Kiaeeha, Masoud and Khadivi, Shahram and Ghidary, Saeed Shiry (2014):
Graph-Based Semi-Supervised Conditional Random Fields For Spoken Language Understanding Using Unaligned Data.
In: Australasian Language Technology Association Workshop, p. 98, [Conference or Workshop Item]

Abstract

We experiment graph-based SemiSupervised Learning (SSL) of Conditional Random Fields (CRF) for the application of Spoken Language Understanding (SLU) on unaligned data. The aligned labels for examples are obtained using IBM Model. We adapt a baseline semisupervised CRF by defining new feature set and altering the label propagation algorithm. Our results demonstrate that our proposed approach significantly improves the performance of the supervised model by utilizing the knowledge gained from the graph.

Item Type: Conference or Workshop Item
Erschienen: 2014
Creators: Aliannejadi, Mohammad and Kiaeeha, Masoud and Khadivi, Shahram and Ghidary, Saeed Shiry
Title: Graph-Based Semi-Supervised Conditional Random Fields For Spoken Language Understanding Using Unaligned Data
Language: German
Abstract:

We experiment graph-based SemiSupervised Learning (SSL) of Conditional Random Fields (CRF) for the application of Spoken Language Understanding (SLU) on unaligned data. The aligned labels for examples are obtained using IBM Model. We adapt a baseline semisupervised CRF by defining new feature set and altering the label propagation algorithm. Our results demonstrate that our proposed approach significantly improves the performance of the supervised model by utilizing the knowledge gained from the graph.

Title of Book: Australasian Language Technology Association Workshop
Divisions: Zentrale Einrichtungen
Zentrale Einrichtungen > University and State Library Darmstadt (ULB)
Date Deposited: 31 Dec 2016 14:29
Identification Number: TUD-CS-2014-1045
Related URLs:
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)

View Item View Item