EUROSPEECH 2001 Scandinavia
7th European Conference on Speech Communication and Technology

Aalborg, Denmark
September 3-7, 2001


Improvement of a Structured Language Model: Arbori-context Tree

Shinsuke Mori, Masafumi Nishimura, Nobuyasu Itoh

IBM Research, Tokyo Research Laboratory, IBM Japan, Japan

In this paper we present an extention of a context tree for a structured language model (SLM), which we call an arbori-context tree. The state-of-the-art SLM predicts the next word from a fixed partial tree of the history tree, such as two exposed heads, etc. An arbori-context tree allows us to select an optimum partial tree of a history tree for the next word prediction depending on the effectiveness in the similar way that a context tree selects the length of the history (n of n-gram). The experiment we conducted showed that the test set perplexity of the SLM based on an arbori-context tree (79.98) was lower than that of the SLM with a fixed history (101.56).

Full Paper

Bibliographic reference.  Mori, Shinsuke / Nishimura, Masafumi / Itoh, Nobuyasu (2001): "Improvement of a structured language model: arbori-context tree", In EUROSPEECH-2001, 713-716.