Knowledge and Data Management White Papers
Unsupervised Learning of Dependency Structure for Language Modeling
Overview This paper presents a Dependency Language Model (DLM) that captures linguistic constraints via a dependency structure, i.e., a set of probabilistic dependencies that express the relations between headwords of each phrase in a sentence by an acyclic, planar, undirected graph. The contributions are three-fold. First, the authors incorporate the dependency structure into an n-gram language model to capture long distance word dependency. Second, the authors present an unsupervised learning method that discovers the dependency structure of a sentence using a bootstrapping procedure. Finally, the authors evaluate the proposed models on a realistic application (Japanese Kana-Kanji conversion).
| Publisher | Microsoft | File Format | |
|---|---|---|---|
| Date Published | May 2003 | ||
| Format | White Papers | ||
| Topics | |||
-
Did you find this white paper useful? 1 out of 2 users found this white paper useful
White Paper RSS
Download
Register
