Word Association and MI-TRigger-based Language Modeling

There exists strong word association in natural language. Based on mutual information, this paper proposes a new MI-Trigger-based modeling approach to capture the preferred relationships between words over a short or long distance. Both the distance-independent(DI) and distancedependent(DD) MI-Trigger-based models are constructed within a window. It is found that proper MI-Trigger modeling is superior to word bigram model and the DD MI-Trigger models have better performance than the DI MI-Trigger models for the same window size. It is also found that the number of the trigger pairs in an MITrigger model can be kept to a reasonable size without losing too much of its modeling power. Finally, it is concluded that the preferred relationships between words are useful to language disambiguation and can be modeled efficiently by the MI-Trigger-based modeling approach.

• Type: Conference
• Year: 1998
• Where: ACL
• Authors: Guodong Zhou, Kimteng Lua
• Keywords: ACL 1998, ACL 2007, MI-Trigger Models, MI-Trigger-based Modeling Approach, Preferred Relationships